diffusers

diffusers copied to clipboard

Added ability to provide list of enabled embeddings for maybe_convert_prompt call

10

# What does this PR do? This PR adds the ability to provide a list of enabled embeddings for prompt conversion with the `TextualInversionLoaderMixin`. Right now, in order to disable...

kovalexal

I read from the hugging face docs that the parameter "num_class_images" refers to the "Minimal" class images for prior preservation loss. If with_prior_preservation = True and there are not enough...

sivaramakrishnan-rajaraman

[Pipeline] AnimateDiff SDXL

18

# What does this PR do? Fixes #6158. Attempt at integrating https://github.com/guoyww/AnimateDiff/tree/sdxl. Relevant discussion: https://github.com/huggingface/diffusers/pull/5928#issuecomment-1851737456 Continuation of #6195. Unfortunately, the code base from current main and the one in 6195...

a-r-r-o-w

Deprecate VQDiffusionScheduler

2

**What API design would you like to have changed or added to the library? Why?** Since the vq diffusion pipeline is deprecated in #6169 (sadly no docs can be found...

HydrogenC

[Community] MotionCtrl SVD

23

# What does this PR do? This PR adds support for the Stable Video Diffusion version of MotionCtrl as a community pipeline. This is the continuation of #6844 to keep...

a-r-r-o-w

update

12

# What does this PR do? - load_dataset data_dir Supports custom local datasets. Just like https://github.com/huggingface/diffusers/pull/5747#event-10922633415 - Update fingerprint hash parameters. Avoid irrelevant parameters causing repeated calculations in the map...

aihao2000

apple: support for MLX quantized linear in diffusers

1

**Is your feature request related to a problem? Please describe.** As an Apple MPS user, it always feels somewhat like we're second-class citizens with respect to the latest and greatest...

bghira

Fine-Grained Subject-Specific Attribute Control

8

### Model/Pipeline/Scheduler description [This paper](https://github.com/CompVis/attribute-control) shows you can control attributes of subjects in a text-to-image model. E.g., for the prompt "A cat and dog", you can change the attributes of...

UmerHA

[Pipeline] ReNoise: Real Image Inversion Through Iterative Noising

5

### Model/Pipeline/Scheduler description Achieving faithful image-to-noise inversion with Denoising Diffusion models remains a challenge, particularly for more recent models trained to generate images with a small number of denoising steps....

clarencechen

It is so confused to load textual-inversion sdxl embedding as inference prompt

16

### Describe the bug I trained a textual inversion model on SDXL pretrained model ( RealVisXL3.0 ), and then when I want to inference, I use this textual inversion model...

xinli2008