lllyasviel/stable-diffusion-webui-forge
1
0
Fork 0
mirror of https://github.com/lllyasviel/stable-diffusion-webui-forge.git synced 2026-01-26 19:09:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

rework model loader and configs

Browse Source
This commit is contained in:
layerdiffusion
2024-07-30 09:57:07 -06:00
parent 40dd61ba6c
commit c8156fcf41
181 changed files with 1853633 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
backend/huggingface/Kwai-Kolors/Kolors/model_index.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.18.0.dev0",
"force_zeros_for_empty_prompt": true,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"kolors",
"ChatGLMModel"
],
"tokenizer": [
"kolors",
"ChatGLMTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

22
backend/huggingface/Kwai-Kolors/Kolors/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,22 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.18.0.dev0",
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"beta_end": 0.014,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"interpolation_type": "linear",
"num_train_timesteps": 1100,
"prediction_type": "epsilon",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

42
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/config.json Normal file
View File

@@ -0,0 +1,42 @@
{
"_name_or_path": "THUDM/chatglm3-6b-base",
"model_type": "chatglm",
"architectures": [
"ChatGLMModel"
],
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
},
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"bias_dropout_fusion": true,
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1e-05,
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_layers": 28,
"original_rope": true,
"padded_vocab_size": 65024,
"post_layer_norm": true,
"rmsnorm": true,
"seq_length": 32768,
"use_cache": true,
"torch_dtype": "float16",
"transformers_version": "4.30.2",
"tie_word_embeddings": false,
"eos_token_id": 2,
"pad_token_id": 0
}

207
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,207 @@
{
"metadata": {
"total_size": 12487168064
},
"weight_map": {
"transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.final_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.output_layer.weight": "pytorch_model-00007-of-00007.bin",
"transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00007.bin"
}
}

12
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/tokenizer_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"name_or_path": "THUDM/chatglm3-6b-base",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
}
}

BIN
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/vocab.txt Normal file
View File

Binary file not shown.

12
backend/huggingface/Kwai-Kolors/Kolors/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"name_or_path": "THUDM/chatglm3-6b-base",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
}
}

BIN
backend/huggingface/Kwai-Kolors/Kolors/tokenizer/vocab.txt Normal file
View File

Binary file not shown.

72
backend/huggingface/Kwai-Kolors/Kolors/unet/config.json Normal file
View File

@@ -0,0 +1,72 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": 4096,
"encoder_hid_dim_type": "text_proj",
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 5632,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": true
}

31
backend/huggingface/Kwai-Kolors/Kolors/vae/config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.18.0.dev0",
"_name_or_path": "./vae",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

41
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/model_index.json Normal file
View File

@@ -0,0 +1,41 @@
{
"_class_name": "HunyuanDiTPipeline",
"_diffusers_version": "0.29.0.dev0",
"feature_extractor": [
null,
null
],
"requires_safety_checker": true,
"safety_checker": [
null,
null
],
"scheduler": [
"diffusers",
"DDPMScheduler"
],
"text_encoder": [
"transformers",
"BertModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"BertTokenizer"
],
"tokenizer_2": [
"transformers",
"T5Tokenizer"
],
"transformer": [
"diffusers",
"HunyuanDiT2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

21
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"_class_name": "DDPMScheduler",
"_diffusers_version": "0.29.0.dev0",
"beta_end": 0.03,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"num_train_timesteps": 1000,
"prediction_type": "v_prediction",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null,
"variance_type": "fixed_small"
}

33
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder/config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"directionality": "bidi",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 47020
}

32
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"T5EncoderModel"
],
"classifier_dropout": 0.0,
"d_ff": 5120,
"d_kv": 64,
"d_model": 2048,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 32,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "T5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"use_cache": true,
"vocab_size": 250112
}

226
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/model.safetensors.index.json Normal file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 6679834624
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

37
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,37 @@
{
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

57
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,57 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 77,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}

47020
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/vocab.txt Normal file
View File

File diff suppressed because it is too large Load Diff

23
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

39
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/tokenizer_config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 0,
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

20
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/transformer/config.json Normal file
View File

@@ -0,0 +1,20 @@
{
"_class_name": "HunyuanDiT2DModel",
"_diffusers_version": "0.29.0.dev0",
"activation_fn": "gelu-approximate",
"attention_head_dim": 88,
"cross_attention_dim": 1024,
"cross_attention_dim_t5": 2048,
"hidden_size": 1408,
"in_channels": 4,
"learn_sigma": true,
"mlp_ratio": 4.3637,
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_layers": 40,
"patch_size": 2,
"pooled_projection_dim": 1024,
"sample_size": 128,
"text_len": 77,
"text_len_t5": 256
}

33
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/vae/config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.29.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": false,
"in_channels": 3,
"latent_channels": 4,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

35
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/model_index.json Normal file
View File

@@ -0,0 +1,35 @@
{
"_class_name": "StableDiffusionXLInpaintPipeline",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
"force_zeros_for_empty_prompt": true,
"requires_aesthetics_score": false,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

18
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,18 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.21.0.dev0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"interpolation_type": "linear",
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

25
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder/config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"vocab_size": 49408
}

25
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder_2/config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder_2",
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"vocab_size": 49408
}

48895
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

78
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/unet/config.json Normal file
View File

@@ -0,0 +1,78 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "valhalla/sdxl-inpaint-ema",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"decay": 0.9999,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"inv_gamma": 1.0,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"min_decay": 0.0,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"optimization_step": 37000,
"out_channels": 4,
"power": 0.6666666666666666,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": null,
"update_after_step": 0,
"use_ema_warmup": false,
"use_linear_projection": true
}

32
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/vae/config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": false,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

42
backend/huggingface/lllyasviel/control_v11p_sd15_canny/config.json Normal file
View File

@@ -0,0 +1,42 @@
{
"_class_name": "ControlNetModel",
"_diffusers_version": "0.16.0.dev0",
"_name_or_path": "/home/patrick/controlnet_v1_1/control_v11p_sd15_canny",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"class_embed_type": null,
"conditioning_embedding_out_channels": [
16,
32,
96,
256
],
"controlnet_conditioning_channel_order": "rgb",
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_class_embeds": null,
"only_cross_attention": false,
"projection_class_embeddings_input_dim": null,
"resnet_time_scale_shift": "default",
"upcast_attention": false,
"use_linear_projection": false
}

41
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/model_index.json Normal file
View File

@@ -0,0 +1,41 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.27.0.dev0",
"feature_extractor": [
null,
null
],
"force_zeros_for_empty_prompt": true,
"image_encoder": [
null,
null
],
"scheduler": [
"diffusers",
"EDMDPMSolverMultistepScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

19
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,19 @@
{
"_class_name": "EDMDPMSolverMultistepScheduler",
"_diffusers_version": "0.27.0.dev0",
"algorithm_type": "dpmsolver++",
"dynamic_thresholding_ratio": 0.995,
"euler_at_final": false,
"final_sigmas_type": "zero",
"lower_order_final": true,
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"rho": 7.0,
"sample_max_value": 1.0,
"sigma_data": 0.5,
"sigma_max": 80.0,
"sigma_min": 0.002,
"solver_order": 2,
"solver_type": "midpoint",
"thresholding": false
}

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder/config.json Normal file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"vocab_size": 49408
}

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder_2/config.json Normal file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"vocab_size": 49408
}

48895
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

38
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/tokenizer_config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "!",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

72
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/unet/config.json Normal file
View File

@@ -0,0 +1,72 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": true
}

43
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/vae/config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"latents_mean": [
-1.6574,
1.886,
-1.383,
2.5155
],
"latents_std": [
8.4927,
5.9022,
6.5498,
5.2299
],
"scaling_factor": 0.5
}

36
backend/huggingface/runwayml/stable-diffusion-inpainting/config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.6.0.dev0",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"center_input_sample": false,
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"out_channels": 4,
"sample_size": 64,
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
]
}

20
backend/huggingface/runwayml/stable-diffusion-inpainting/feature_extractor/preprocessor_config.json Normal file
View File

@@ -0,0 +1,20 @@
{
"crop_size": 224,
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "CLIPFeatureExtractor",
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"resample": 3,
"size": 224
}

32
backend/huggingface/runwayml/stable-diffusion-inpainting/model_index.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "StableDiffusionInpaintPipeline",
"_diffusers_version": "0.6.0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"safety_checker": [
"stable_diffusion",
"StableDiffusionSafetyChecker"
],
"scheduler": [
"diffusers",
"DDIMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

177
backend/huggingface/runwayml/stable-diffusion-inpainting/safety_checker/config.json Normal file
View File

@@ -0,0 +1,177 @@
{
"_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
"architectures": [
"StableDiffusionSafetyChecker"
],
"initializer_factor": 1.0,
"logit_scale_init_value": 2.6592,
"model_type": "clip",
"projection_dim": 768,
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 77,
"min_length": 0,
"model_type": "clip_text_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"prefix": null,
"problem_type": null,
"projection_dim": 512,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.22.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 49408
},
"text_config_dict": {
"hidden_size": 768,
"intermediate_size": 3072,
"num_attention_heads": 12,
"num_hidden_layers": 12
},
"torch_dtype": "float32",
"transformers_version": null,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 224,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "clip_vision_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_hidden_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"problem_type": null,
"projection_dim": 512,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.22.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false
},
"vision_config_dict": {
"hidden_size": 1024,
"intermediate_size": 4096,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"patch_size": 14
}
}

13
backend/huggingface/runwayml/stable-diffusion-inpainting/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"_class_name": "DDIMScheduler",
"_diffusers_version": "0.6.0.dev0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"num_train_timesteps": 1000,
"set_alpha_to_one": false,
"steps_offset": 1,
"trained_betas": null,
"skip_prk_steps": true
}

25
backend/huggingface/runwayml/stable-diffusion-inpainting/text_encoder/config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.22.0.dev0",
"vocab_size": 49408
}

48895
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

34
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"name_or_path": "openai/clip-vit-large-patch14",
"pad_token": "<|endoftext|>",
"special_tokens_map_file": "./special_tokens_map.json",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/runwayml/stable-diffusion-inpainting/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

36
backend/huggingface/runwayml/stable-diffusion-inpainting/unet/config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.6.0.dev0",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"center_input_sample": false,
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"out_channels": 4,
"sample_size": 64,
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
]
}

29
backend/huggingface/runwayml/stable-diffusion-inpainting/vae/config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.6.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 256,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

20
backend/huggingface/runwayml/stable-diffusion-v1-5/feature_extractor/preprocessor_config.json Normal file
View File

@@ -0,0 +1,20 @@
{
"crop_size": 224,
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "CLIPFeatureExtractor",
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"resample": 3,
"size": 224
}

32
backend/huggingface/runwayml/stable-diffusion-v1-5/model_index.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "StableDiffusionPipeline",
"_diffusers_version": "0.6.0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"safety_checker": [
"stable_diffusion",
"StableDiffusionSafetyChecker"
],
"scheduler": [
"diffusers",
"PNDMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

175
backend/huggingface/runwayml/stable-diffusion-v1-5/safety_checker/config.json Normal file
View File

@@ -0,0 +1,175 @@
{
"_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
"architectures": [
"StableDiffusionSafetyChecker"
],
"initializer_factor": 1.0,
"logit_scale_init_value": 2.6592,
"model_type": "clip",
"projection_dim": 768,
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 77,
"min_length": 0,
"model_type": "clip_text_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.22.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 49408
},
"text_config_dict": {
"hidden_size": 768,
"intermediate_size": 3072,
"num_attention_heads": 12,
"num_hidden_layers": 12
},
"torch_dtype": "float32",
"transformers_version": null,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 224,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "clip_vision_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_hidden_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.22.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false
},
"vision_config_dict": {
"hidden_size": 1024,
"intermediate_size": 4096,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"patch_size": 14
}
}

13
backend/huggingface/runwayml/stable-diffusion-v1-5/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"_class_name": "PNDMScheduler",
"_diffusers_version": "0.6.0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"num_train_timesteps": 1000,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"trained_betas": null,
"clip_sample": false
}

25
backend/huggingface/runwayml/stable-diffusion-v1-5/text_encoder/config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.22.0.dev0",
"vocab_size": 49408
}

48895
backend/huggingface/runwayml/stable-diffusion-v1-5/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/runwayml/stable-diffusion-v1-5/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

34
backend/huggingface/runwayml/stable-diffusion-v1-5/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"name_or_path": "openai/clip-vit-large-patch14",
"pad_token": "<|endoftext|>",
"special_tokens_map_file": "./special_tokens_map.json",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/runwayml/stable-diffusion-v1-5/tokenizer/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

36
backend/huggingface/runwayml/stable-diffusion-v1-5/unet/config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.6.0",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"center_input_sample": false,
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"out_channels": 4,
"sample_size": 64,
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
]
}

2
backend/vae/configs/sd15.json → backend/huggingface/runwayml/stable-diffusion-v1-5/vae/config.json
View File

@@ -1,5 +1,6 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.6.0",
"act_fn": "silu",
"block_out_channels": [
128,
@@ -19,7 +20,6 @@
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.18215,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",

27
backend/huggingface/stabilityai/stable-cascade-prior/feature_extractor/preprocessor_config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"crop_size": {
"height": 224,
"width": 224
},
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "CLIPImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"shortest_edge": 224
}
}

23
backend/huggingface/stabilityai/stable-cascade-prior/image_encoder/config.json Normal file
View File

@@ -0,0 +1,23 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPVisionModelWithProjection"
],
"attention_dropout": 0.0,
"dropout": 0.0,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"image_size": 224,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"model_type": "clip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2"
}

29
backend/huggingface/stabilityai/stable-cascade-prior/model_index.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_class_name": "StableCascadePriorPipeline",
"_diffusers_version": "0.27.0.dev0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"image_encoder": [
"transformers",
"CLIPVisionModelWithProjection"
],
"prior": [
"diffusers",
"StableCascadeUNet"
],
"resolution_multiple": 42.67,
"scheduler": [
"diffusers",
"DDPMWuerstchenScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizerFast"
]
}

64
backend/huggingface/stabilityai/stable-cascade-prior/prior/config.json Normal file
View File

@@ -0,0 +1,64 @@
{
"_class_name": "StableCascadeUNet",
"_diffusers_version": "0.27.0.dev0",
"block_out_channels": [
2048,
2048
],
"block_types_per_layer": [
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
]
],
"clip_image_in_channels": 768,
"clip_seq": 4,
"clip_text_in_channels": 1280,
"clip_text_pooled_in_channels": 1280,
"conditioning_dim": 2048,
"down_blocks_repeat_mappers": [
1,
1
],
"down_num_layers_per_block": [
8,
24
],
"dropout": [
0.1,
0.1
],
"effnet_in_channels": null,
"in_channels": 16,
"kernel_size": 3,
"num_attention_heads": [
32,
32
],
"out_channels": 16,
"patch_size": 1,
"pixel_mapper_in_channels": null,
"self_attn": true,
"switch_level": [
false
],
"timestep_conditioning_type": [
"sca",
"crp"
],
"timestep_ratio_embedding_dim": 64,
"up_blocks_repeat_mappers": [
1,
1
],
"up_num_layers_per_block": [
24,
8
]
}

64
backend/huggingface/stabilityai/stable-cascade-prior/prior_lite/config.json Normal file
View File

@@ -0,0 +1,64 @@
{
"_class_name": "StableCascadeUNet",
"_diffusers_version": "0.27.0.dev0",
"block_out_channels": [
1536,
1536
],
"block_types_per_layer": [
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
]
],
"clip_image_in_channels": 768,
"clip_seq": 4,
"clip_text_in_channels": 1280,
"clip_text_pooled_in_channels": 1280,
"conditioning_dim": 1536,
"down_blocks_repeat_mappers": [
1,
1
],
"down_num_layers_per_block": [
4,
12
],
"dropout": [
0.1,
0.1
],
"effnet_in_channels": null,
"in_channels": 16,
"kernel_size": 3,
"num_attention_heads": [
24,
24
],
"out_channels": 16,
"patch_size": 1,
"pixel_mapper_in_channels": null,
"self_attn": true,
"switch_level": [
false
],
"timestep_conditioning_type": [
"sca",
"crp"
],
"timestep_ratio_embedding_dim": 64,
"up_blocks_repeat_mappers": [
1,
1
],
"up_num_layers_per_block": [
12,
4
]
}

6
backend/huggingface/stabilityai/stable-cascade-prior/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_class_name": "DDPMWuerstchenScheduler",
"_diffusers_version": "0.27.0.dev0",
"s": 0.008,
"scaler": 1.0
}

25
backend/huggingface/stabilityai/stable-cascade-prior/text_encoder/config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 49406,
"dropout": 0.0,
"eos_token_id": 49407,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"vocab_size": 49408
}

48895
backend/huggingface/stabilityai/stable-cascade-prior/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/stabilityai/stable-cascade-prior/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

98396
backend/huggingface/stabilityai/stable-cascade-prior/tokenizer/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/stabilityai/stable-cascade-prior/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

1
backend/huggingface/stabilityai/stable-cascade-prior/tokenizer/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

83
backend/huggingface/stabilityai/stable-cascade/decoder/config.json Normal file
View File

@@ -0,0 +1,83 @@
{
"_class_name": "StableCascadeUNet",
"_diffusers_version": "0.27.0.dev0",
"block_out_channels": [
320,
640,
1280,
1280
],
"block_types_per_layer": [
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
]
],
"clip_image_in_channels": null,
"clip_seq": 4,
"clip_text_in_channels": null,
"clip_text_pooled_in_channels": 1280,
"conditioning_dim": 1280,
"down_blocks_repeat_mappers": [
1,
1,
1,
1
],
"down_num_layers_per_block": [
2,
6,
28,
6
],
"dropout": [
0,
0,
0.1,
0.1
],
"effnet_in_channels": 16,
"in_channels": 4,
"kernel_size": 3,
"num_attention_heads": [
0,
0,
20,
20
],
"out_channels": 4,
"patch_size": 2,
"pixel_mapper_in_channels": 3,
"self_attn": true,
"switch_level": null,
"timestep_conditioning_type": [
"sca"
],
"timestep_ratio_embedding_dim": 64,
"up_blocks_repeat_mappers": [
3,
3,
2,
2
],
"up_num_layers_per_block": [
6,
28,
6,
2
]
}

83
backend/huggingface/stabilityai/stable-cascade/decoder_lite/config.json Normal file
View File

@@ -0,0 +1,83 @@
{
"_class_name": "StableCascadeUNet",
"_diffusers_version": "0.27.0.dev0",
"block_out_channels": [
320,
576,
1152,
1152
],
"block_types_per_layer": [
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
],
[
"SDCascadeResBlock",
"SDCascadeTimestepBlock",
"SDCascadeAttnBlock"
]
],
"clip_image_in_channels": null,
"clip_seq": 4,
"clip_text_in_channels": null,
"clip_text_pooled_in_channels": 1280,
"conditioning_dim": 1280,
"down_blocks_repeat_mappers": [
1,
1,
1,
1
],
"down_num_layers_per_block": [
2,
4,
14,
4
],
"dropout": [
0,
0,
0.1,
0.1
],
"effnet_in_channels": 16,
"in_channels": 4,
"kernel_size": 3,
"num_attention_heads": [
0,
9,
18,
18
],
"out_channels": 4,
"patch_size": 2,
"pixel_mapper_in_channels": 3,
"self_attn": true,
"switch_level": null,
"timestep_conditioning_type": [
"sca"
],
"timestep_ratio_embedding_dim": 64,
"up_blocks_repeat_mappers": [
2,
2,
2,
2
],
"up_num_layers_per_block": [
4,
14,
4,
2
]
}

25
backend/huggingface/stabilityai/stable-cascade/model_index.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_class_name": "StableCascadeDecoderPipeline",
"_diffusers_version": "0.27.0.dev0",
"decoder": [
"diffusers",
"StableCascadeUNet"
],
"latent_dim_scale": 10.67,
"scheduler": [
"diffusers",
"DDPMWuerstchenScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizerFast"
],
"vqgan": [
"wuerstchen",
"PaellaVQModel"
]
}

6
backend/huggingface/stabilityai/stable-cascade/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_class_name": "DDPMWuerstchenScheduler",
"_diffusers_version": "0.27.0.dev0",
"s": 0.008,
"scaler": 1.0
}

25
backend/huggingface/stabilityai/stable-cascade/text_encoder/config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 49406,
"dropout": 0.0,
"eos_token_id": 49407,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"vocab_size": 49408
}

48895
backend/huggingface/stabilityai/stable-cascade/tokenizer/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/stabilityai/stable-cascade/tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

98396
backend/huggingface/stabilityai/stable-cascade/tokenizer/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/stabilityai/stable-cascade/tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

1
backend/huggingface/stabilityai/stable-cascade/tokenizer/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

14
backend/huggingface/stabilityai/stable-cascade/vqgan/config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"_class_name": "PaellaVQModel",
"_diffusers_version": "0.27.0.dev0",
"_name_or_path": "warp-ai/wuerstchen",
"bottleneck_blocks": 12,
"embed_dim": 384,
"in_channels": 3,
"latent_channels": 4,
"levels": 2,
"num_vq_embeddings": 8192,
"out_channels": 3,
"scale_factor": 0.3764,
"up_down_scale_factor": 2
}

20
backend/huggingface/stabilityai/stable-diffusion-2-1/feature_extractor/preprocessor_config.json Normal file
View File

@@ -0,0 +1,20 @@
{
"crop_size": 224,
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "CLIPFeatureExtractor",
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"resample": 3,
"size": 224
}

33
backend/huggingface/stabilityai/stable-diffusion-2-1/model_index.json Normal file
View File

@@ -0,0 +1,33 @@
{
"_class_name": "StableDiffusionPipeline",
"_diffusers_version": "0.8.0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"requires_safety_checker": false,
"safety_checker": [
null,
null
],
"scheduler": [
"diffusers",
"DDIMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

14
backend/huggingface/stabilityai/stable-diffusion-2-1/scheduler/scheduler_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"_class_name": "DDIMScheduler",
"_diffusers_version": "0.8.0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"num_train_timesteps": 1000,
"prediction_type": "v_prediction",
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"trained_betas": null
}

Some files were not shown because too many files have changed in this diff Show More