diff --git a/extensions_built_in/textual_inversion_trainer/config/train.example.yaml b/extensions_built_in/textual_inversion_trainer/config/train.example.yaml index 8b0f4734..90f3c0b1 100644 --- a/extensions_built_in/textual_inversion_trainer/config/train.example.yaml +++ b/extensions_built_in/textual_inversion_trainer/config/train.example.yaml @@ -1,70 +1,72 @@ --- job: extension config: - name: example_name + name: test_v1 process: - - type: 'image_reference_slider_trainer' - training_folder: "/mnt/Train/out/LoRA" + - type: 'textual_inversion_trainer' + training_folder: "out/TI" device: cuda:0 # for tensorboard logging - log_dir: "/home/jaret/Dev/.tensorboard" - network: - type: "lora" - linear: 8 - linear_alpha: 8 + log_dir: "out/.tensorboard" + embedding: + trigger: "your_trigger_here" + tokens: 12 + init_words: "man with short brown hair" + save_format: "safetensors" # 'safetensors' or 'pt' + save: + dtype: float16 # precision to save + save_every: 100 # save every this many steps + max_step_saves_to_keep: 5 # only affects step counts + datasets: + - folder_path: "/path/to/dataset" + caption_type: "txt" + default_caption: "[trigger]" + buckets: true + resolution: 512 train: noise_scheduler: "ddpm" # or "ddpm", "lms", "euler_a" - steps: 5000 - lr: 1e-4 - train_unet: true + noise_scheduler: "ddpm" # or "ddpm", "lms", "euler_a" + steps: 3000 + weight_jitter: 0.0 + lr: 5e-5 + train_unet: false gradient_checkpointing: true - train_text_encoder: true + train_text_encoder: false optimizer: "adamw" +# optimizer: "prodigy" optimizer_params: weight_decay: 1e-2 lr_scheduler: "constant" max_denoising_steps: 1000 - batch_size: 1 + batch_size: 4 dtype: bf16 xformers: true - skip_first_sample: true - noise_offset: 0.0 + min_snr_gamma: 5.0 +# skip_first_sample: true + noise_offset: 0.0 # not needed for this model: - name_or_path: "/path/to/model.safetensors" + # objective reality v2 + name_or_path: "https://civitai.com/models/128453?modelVersionId=142465" is_v2: false # for v2 models is_xl: false # for SDXL models is_v_pred: false # for v-prediction models (most v2 models) - save: - dtype: float16 # precision to save - save_every: 1000 # save every this many steps - max_step_saves_to_keep: 2 # only affects step counts sample: sampler: "ddpm" # must match train.noise_scheduler sample_every: 100 # sample every this many steps width: 512 height: 512 prompts: - - "photo of a woman with red hair taking a selfie --m -3" - - "photo of a woman with red hair taking a selfie --m -1" - - "photo of a woman with red hair taking a selfie --m 1" - - "photo of a woman with red hair taking a selfie --m 3" - - "close up photo of a man smiling at the camera, in a tank top --m -3" - - "close up photo of a man smiling at the camera, in a tank top--m -1" - - "close up photo of a man smiling at the camera, in a tank top --m 1" - - "close up photo of a man smiling at the camera, in a tank top --m 3" - - "photo of a blonde woman smiling, barista --m -3" - - "photo of a blonde woman smiling, barista --m -1" - - "photo of a blonde woman smiling, barista --m 1" - - "photo of a blonde woman smiling, barista --m 3" - - "photo of a Christina Hendricks --m -1" - - "photo of a Christina Hendricks --m -1" - - "photo of a Christina Hendricks --m 1" - - "photo of a Christina Hendricks --m 3" - - "photo of a Christina Ricci --m -3" - - "photo of a Christina Ricci --m -1" - - "photo of a Christina Ricci --m 1" - - "photo of a Christina Ricci --m 3" - neg: "cartoon, fake, drawing, illustration, cgi, animated, anime" + - "photo of [trigger] laughing" + - "photo of [trigger] smiling" + - "[trigger] close up" + - "dark scene [trigger] frozen" + - "[trigger] nighttime" + - "a painting of [trigger]" + - "a drawing of [trigger]" + - "a cartoon of [trigger]" + - "[trigger] pixar style" + - "[trigger] costume" + neg: "" seed: 42 walk_seed: false guidance_scale: 7 @@ -76,32 +78,15 @@ config: use_wandb: false # not supported yet verbose: false - slider: - datasets: - - pair_folder: "/path/to/folder/side/by/side/images" - network_weight: 2.0 - target_class: "" # only used as default if caption txt are not present - size: 512 - - pair_folder: "/path/to/folder/side/by/side/images" - network_weight: 4.0 - target_class: "" # only used as default if caption txt are not present - size: 512 - - -# you can put any information you want here, and it will be saved in the model -# the below is an example. I recommend doing trigger words at a minimum -# in the metadata. The software will include this plus some other information +# You can put any information you want here, and it will be saved in the model. +# The below is an example, but you can put your grocery list in it if you want. +# It is saved in the model so be aware of that. The software will include this +# plus some other information for you automatically meta: - name: "[name]" # [name] gets replaced with the name above - description: A short description of your model - trigger_words: - - put - - trigger - - words - - here - version: '0.1' - creator: - name: Your Name - email: your@email.com - website: https://yourwebsite.com - any: All meta data above is arbitrary, it can be whatever you want. \ No newline at end of file + # [name] gets replaced with the name above + name: "[name]" +# version: '1.0' +# creator: +# name: Your Name +# email: your@gmail.com +# website: https://your.website