diffusers

diffusers copied to clipboard

[don't merge] open-sora test pipeline

3

# What does this PR do? A test implementation for open-sora. ```bash pip install git+https://github.com/huggingface/diffusers.git@st-dit ``` ```py import torch from diffusers import OpenSoraPipeline from diffusers.utils import export_to_gif pipe = OpenSoraPipeline.from_pretrained("diffusers/open-sora-pipe-test",...

patil-suraj

Inference speed

3

What is the fastest way to do inference with sdxl and sd1.5 these days without suffering on quality? Seen a lot of 3rd party libs like openvivo , stable fast...

rishabh063

refactor video processor (part # 7776)

1

part of https://github.com/huggingface/diffusers/pull/7776 I refactored the `preprocess` for both image and video processor a few notes: * we do not need to accept list of list of 4d (the current...

yiyixuxu

[docs] add doc for PixArtSigmaPipeline

4

# What does this PR do? This PR adds docs for PixArtSigmaPipeline. Cc: @sayakpaul @yiyixuxu

lawrence-cj

**Is your feature request related to a problem? Please describe.** In text2img/img2img pipelines, we use Classifier-free guidance (CFG) to enhance the effect of the condition, which requires 2n computations of...

soryxie

you can implement flashface in img2img pipeline or inpainting https://github.com/ali-vilab/FlashFace

loboere

Fix image upcasting

3

Thanks for the opportunity to fix #7854 # What does this PR do? This PR proposes to fix `image` upcasting before `vae.encode()` when using `fp16` and `vae.config.force_upcast==True` with `xformers` or...

tolgacangoz

Expanded init fields in StableDiffusionPipeline cause incompatibilities with many/most inherited pipelines

11

### Describe the bug class `StableDiffusionPipeline` has its init section as: ```py def __init__( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, tokenizer: CLIPTokenizer, unet: UNet2DConditionModel, scheduler: KarrasDiffusionSchedulers, safety_checker: StableDiffusionSafetyChecker, feature_extractor: CLIPImageProcessor, image_encoder:...

vladmandic

Stable Cascade Image to Image Pipeline

5

Are there any plans for Image2Image pipeline for the StableCascade model ?

ekurtulus

fix the failing CPU offload test for combined pipelines. "cuda" should be sufficient here

yiyixuxu