diffusers

diffusers copied to clipboard

Support convert LoRA safetensors into diffusers format

7

This PR hanldes https://github.com/huggingface/diffusers/issues/2363 and part of https://github.com/huggingface/diffusers/issues/2326. In summary, given a LoRA weight in safetensors format, we can merge it into a stable diffusion model in diffusers. It is...

haofanwang

[WIP] Sample images when checkpointing.

21

I based this on the in progress sampling in https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py due to the suggestion on https://github.com/huggingface/diffusers/pull/2030 that that was a good example to follow. Unfortunately, this code doesn't work at...

LucasSloan

Apply ruff flake8-comprehensions rules.

4

Fix #2424 Enables flake8-comprehension checks in ruff and adds the automatically generated fixes. This should strictly improve performance by removing unnecessary lookups, iterations, and function calls. It should also help...

Skylion007

add OnnxStableDiffusionUpscalePipeline pipeline

16

I think I have a working implemention of an `OnnxStableDiffusionUpscalePipeline`, which extends `StableDiffusionUpscalePipeline` to be compatible with `OnnxRuntimeModel`. I'm hoping to get some feedback on whether this is the right...

ssube

### Model/Pipeline/Scheduler description We are working on the training script for [Muse](https://muse-model.github.io/) by google, the progress can be seen [here](https://github.com/lucidrains/muse-maskgit-pytorch/pull/25). I'm trying to make it in the huggingface format as...

isamu-isozaki

[Pipelines] Add a ControlNet pipeline

34

### Model/Pipeline/Scheduler description [ControlNet](https://github.com/lllyasviel/ControlNet) by @lllyasviel is a neural network structure to control diffusion models by adding extra conditions. It has integration with Stable Diffusion and [8 pre-trained models](https://huggingface.co/lllyasviel/ControlNet/tree/main/models) that...

apolinario

stabilityai/stable-diffusion-2 is missing fp16 files

1

antgame11

Remove explicit message argument in deprecate

1

Leaving message in will lead to "got an unexpected keyword argument" error `deprecate` does not have explicit message argument stated https://github.com/huggingface/diffusers/blob/main/src/diffusers/utils/deprecation_utils.py#L8 Error Message: 

alvanli

**Is your feature request related to a problem? Please describe.** Enable flake8-comprehensions which is particularly trivial since the ruff linter was recently installed. It removes useless or inefficient Python comprehensions...

Skylion007

checkpoint_merger community pipeline: add block weighted and module-specific alpha options

4

Some enhancements for the checkpoint_merger community pipeline cc @Abhinay1997 * Different modules can be merged with different alphas via the `module_override_alphas` kwarg (eg `{'unet': 0.2, 'text_encoder': 0.6}`) * Block-weighted merges,...

damian0815