* fix error reported 'find_unused_parameters' running in mutiple GPUs or NPUs
* fix code check of importing module by its alphabetic order
---------
Co-authored-by: jiaqiw <wangjiaqi50@huawei.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* 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: Patrick von Platen <patrick.v.platen@gmail.com>
* update readme (and run formatter on latent_consistency_img2img.py)
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Added mark_step for sdxl to run with pytorch xla. Also updated README with instructions for xla
* adding soft dependency on torch_xla
* fix some styling
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* fix(gligen_inpaint_pipeline): 🐛 Wrap the timestep() 0-d tensor in a list to convert to 1-d tensor. This avoids the TypeError caused by trying to directly iterate over a 0-dimensional tensor in the denoising stage
* test(gligen/gligen_text_image): unit test using the EulerAncestralDiscreteScheduler
---------
Co-authored-by: zhen-hao.chu <zhen-hao.chu@vitrox.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Min-SNR Gamma: correct the fix for SNR weighted loss in v-prediction by adding 1 to SNR rather than the resulting loss weights
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Timestep bias for fine-tuning SDXL
* Adjust parameter choices to include "range" and reword the help statements
* Condition our use of weighted timesteps on the value of timestep_bias_strategy
* style
---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know
* SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know
* empty
---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* min-SNR gamma for Dreambooth training
* Align the mse_loss_weights style with SDXL training example
---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Resolve v_prediction issue for min-SNR gamma weighted loss function
* Combine MSE loss calculation of epsilon and velocity, with a note about the application of the epsilon code to sample prediction
* style
---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Fixed `get_word_inds` mistake/typo in P2P community pipeline
The function `get_word_inds` was taking a string of text and either a word (str) or a word index (int) and returned the indices of token(s) the word would be encoded to.
However, there was a typo, in which in the second `if` branch the word was checked to be a `str` **again**, not `int`, which resulted in an [example code from the docs](https://github.com/huggingface/diffusers/tree/main/examples/community#prompt2prompt-pipeline) to result in an error
