lllyasviel/huggingface_guess
1
0
Fork 0
mirror of https://github.com/lllyasviel/huggingface_guess.git synced 2026-01-26 15:29:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1 from graemeniedermayer/main

Browse Source 
adding SD3.5
This commit is contained in:
lllyasviel
2024-10-28 21:51:38 -07:00
committed by GitHub
parent 84826248b4 e3ad534de8
commit 70942022b6
1 changed files with 35 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
huggingface_guess/model_list.py
View File

@@ -588,6 +588,40 @@ class SD3(BASE):
return result
class SD35(BASE):
huggingface_repo = "stabilityai/stable-diffusion-3.5-large"
unet_config = {
"in_channels": 16,
"pos_embed_scaling_factor": None,
}
sampling_settings = {
"shift": 3.0,
}
unet_extra_config = {}
latent_format = latent.SD3
memory_usage_factor = 1.2
text_encoder_key_prefix = ["text_encoders."]
unet_target = 'transformer'
def clip_target(self, state_dict={}):
result = {}
pref = self.text_encoder_key_prefix[0]
if "{}clip_l.transformer.text_model.final_layer_norm.weight".format(pref) in state_dict:
result['clip_l'] = 'text_encoder'
if "{}clip_g.transformer.text_model.final_layer_norm.weight".format(pref) in state_dict:
result['clip_g'] = 'text_encoder_2'
if "{}t5xxl.transformer.encoder.final_layer_norm.weight".format(pref) in state_dict:
result['t5xxl'] = 'text_encoder_3'
return result
class StableAudio(BASE):
unet_config = {
@@ -713,6 +747,6 @@ class FluxSchnell(Flux):
}
models = [Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, HunyuanDiT, HunyuanDiT1, Flux, FluxSchnell]
models = [Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD35, SD3, StableAudio, AuraFlow, HunyuanDiT, HunyuanDiT1, Flux, FluxSchnell]
models += [SVD_img2vid]