Skip to content

GitLab

Switch branch/tag
  1. 27 Nov, 2023 1 commit
  3. 23 Nov, 2023 2 commits
  5. 22 Nov, 2023 1 commit
  7. 21 Nov, 2023 4 commits
    • Andrés Romero's avatar
      ControlNet+Adapter pipeline, and ControlNet+Adapter+Inpaint pipeline (#5869) · 93f1a14c
      Andrés Romero authored 
      

* ControlNet+Adapter pipeline, and +Inpaint pipeline


---------
Co-authored-by: default avatarandres <andres@hax.ai>
      93f1a14c
    • Patrick von Platen's avatar
      [Lora] Seperate logic (#5809) · 13d73d93
      Patrick von Platen authored 
      * [Lora] Seperate logic

* [Lora] Seperate logic

* [Lora] Seperate logic

* add comments to explain the code better

* add comments to explain the code better
      13d73d93
    • Linoy Tsaban's avatar
      Add features to the Dreambooth LoRA SDXL training script (#5508) · 6fac1369
      Linoy Tsaban authored 
      

* Additions:
- support for different lr for text encoder
- support for Prodigy optimizer
- support for min snr gamma
- support for custom captions and dataset loading from the hub

* adjusted --caption_column behaviour (to -not- use the second column of the dataset by default if --caption_column is not provided)

* fixed --output_dir / --model_dir_name confusion

* added --repeats, --adam_weight_decay_text_encoder
+ some fixes

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* - import compute_snr from diffusers/training_utils.py
- cluster adamw together
- when using 'prodigy', if --train_text_encoder == True and --text_encoder_lr != --learning rate, changes the lr of the text encoders optimization params to be --learning_rate (otherwise errors)

* shape fixes when custom captions are used

* formatting and a little cleanup

* code styling

* --repeats default value fixed, changed to 1

* bug fix - removed redundant lines of embedding concatenation when using prior_preservation (that duplicated class_prompt embeddings)

* changed dataset loading logic according to the following usecases (to avoid unnecessary dependency on datasets)-
1. user provides --dataset_name
2. user provides local dir --instance_data_dir that contains a metadata .jsonl file
3. user provides local dir --instance_data_dir that contains only images
in cases [1,2] we import datasets and use load_dataset method, in case [3] we process the data same as in the original script setting

* styling fix

* arg name fix

* adjusted the --repeats logic

* -removed redundant arg and 'if' when loading local folder with prompts
-updated readme template
-some default val fixes
-custom caption tests

* image path fix for readme

* code style

* bug fix

* --caption_column arg

* readme fix

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarLinoy Tsaban <linoy@huggingface.co>
      6fac1369
    • co63oc's avatar
      Update README.md (#5855) · ee519cfe
      co63oc authored
      ee519cfe
  9. 20 Nov, 2023 4 commits
  11. 17 Nov, 2023 1 commit
  13. 15 Nov, 2023 1 commit
  15. 14 Nov, 2023 4 commits
  17. 13 Nov, 2023 5 commits
  19. 11 Nov, 2023 1 commit
  21. 10 Nov, 2023 2 commits
  23. 09 Nov, 2023 1 commit
  25. 06 Nov, 2023 1 commit
  27. 01 Nov, 2023 1 commit
  29. 31 Oct, 2023 3 commits
  31. 30 Oct, 2023 1 commit
  33. 27 Oct, 2023 1 commit
  35. 26 Oct, 2023 1 commit
  37. 25 Oct, 2023 3 commits
    • Ran Ran's avatar
      Add from_pt flag to enable model from PT (#5501) · 8959c5b9
      Ran Ran authored 
      * Add from_pt flag to enable model from PT

* Format the file

* Reformat the file
      8959c5b9
    • Patrick von Platen's avatar
      make style · d420d713
      Patrick von Platen authored
      d420d713
    • Logan's avatar
      Add a new community pipeline (#5477) · a1fad828
      Logan authored 
      

* Add a new community pipeline

examples/community/latent_consistency_img2img.py

which can be called like this

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
                "SimianLuo/LCM_Dreamshaper_v7", custom_pipeline="latent_consistency_txt2img", custom_revision="main")

            # To save GPU memory, torch.float16 can be used, but it may compromise image quality.
pipe.to(torch_device="cuda", torch_dtype=torch.float32)

img2img=LatentConsistencyModelPipeline_img2img(
    vae=pipe.vae,
    text_encoder=pipe.text_encoder,
    tokenizer=pipe.tokenizer,
    unet=pipe.unet,
    #scheduler=pipe.scheduler,
    scheduler=None,
    safety_checker=None,
    feature_extractor=pipe.feature_extractor,
    requires_safety_checker=False,
)

img = Image.open("thisismyimage.png")

result = img2img(prompt,img,strength,num_inference_steps=4)

* Apply suggestions from code review

Fix name formatting for scheduler
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* update readme (and run formatter on latent_consistency_img2img.py)

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      a1fad828
  39. 23 Oct, 2023 2 commits