diffusers

diffusers copied to clipboard

Mixture-of-Experts partial diffusion implementation for base SD 1.x / 2.x pipelines

32

# What does this PR do? This pull request ports our denoising_start code to the text2img pipeline, and the denoising_start and denoising_end code from the img2img pipeline. This brings legacy...

bghira

error in StableCascadeDecoderPipeline.from_pretrained

9

### Describe the bug When I used "StableCascadeDecoderPipeline.from_pretrained", the error accured "AttributeError: module diffusers.pipelines.stable_cascade has no attribute StableCascadeUNet". Can someone help me? @DN6 @ ### Reproduction from diffusers import StableCascadeDecoderPipeline...

hahaha-cc

AnyText: Multilingual Visual Text Generation And Editing

13

### Model/Pipeline/Scheduler description From the [repository](https://github.com/tyxsspa/AnyText): > AnyText comprises a diffusion pipeline with two primary elements: an auxiliary latent module and a text embedding module. The former uses inputs like...

sayakpaul

Train IP Adapter

6

There isn't an example of how to train or finetune your own IP Adapter model currently. It would be helpful to have an implementation of the how to train/finetune the...

AMohamedAakhil

Request proper examples on how to training a diffusion models with diffusers on large scale dataset like LAION

6

Hi, I do not see any examples in diffusers/examples on how to training a diffusion models with diffusers on large scale dataset like LAION. However, it is important since many...

Luciennnnnnn

Dreambooth SDXL LoRA - Update PEFT for DoRA

4

The sdxl script assumes the presence of a dora related property that does not exist until peft 0.9.0 # What does this PR do? Recent updates to the sdxl dreambooth...

shawnrushefsky

[Pipeline] Add LEDITS++ pipelines

4

# What does this PR do? We add a set of pipelines implementing the [LEDITS++](https://leditsplusplus-project.static.hf.space/index.html) image editing method. We provide an implementation for [StableDiffusion](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py), [SD-XL](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py) and [DeepFloyd-IF](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py). Additionally, we made...

manuelbrack

Type hint for `callback_on_step_end` in pipeline `__call__` is incorrect

3

### Describe the bug As far as I can tell, the type hint `callback_on_step_end` for all pipelines (as seen in [this search](https://github.com/search?q=repo%3Ahuggingface%2Fdiffusers+%22callback_on_step_end%3A+Optional%22&type=code)) is incorrect. Taking the SDXL pipeline as an...

philpax

LCM Distill Scripts Fix Bug when Initializing Target U-Net

2

# What does this PR do? This PR initializes the `target_unet` target model config from `unet` rather than `teacher_unet` in the LCM full model distillation scripts. This ensures that if...

dg845

Llmga diffusers

2

# What does this PR do? This is a copy of the llma diffusers code rebased onto 0.24 when they copied it over. Fixes # (issue) ## Before submitting -...

jmikedupont2