diffusers

diffusers copied to clipboard

Cascade w/ new varnames produces funky images.

1

### Describe the bug Using Stable Cascade with the diffusers main branch and the HF PRs 2/44 as intended, it appears as though there's some misconfiguration that results in super...

Beinsezii

`DiffusionPipeline` cannot serialize or load custom huggingface `transformers` model

5

**Is your feature request related to a problem? Please describe.** Currently `DiffusionPipeline` class can only serialize official transformers models correctly and load them using `from_pretrained`. However, it does not work...

ChenchaoZhao

Support for Multimodal Diffusion Transformers (e.g. StableDiffusion3)

5

### Model/Pipeline/Scheduler description Yesterday StabilityAI published the details of their architecture MMDiT for the upcoming StableDiffusion3. https://stability.ai/news/stable-diffusion-3-research-paper Their approach differs quite much from the traditional Diffuser Transformers (like PixArt-alpha) in...

kabachuha

Issue: Error handling of invalid orders

20

### Describe the bug When I attempt to create an XYZ grid using all available Samplers (other than Default) with an SDXL model in the X axis, and [Sampler] solver...

LankyPoet

[Refactor] Stable Diffusion UNet Refactor Proposal

6

# What does this PR do? The The UNet2DConditionModel has become quite large is starting to become quite difficult to understand and maintain. In order to simplify this a bit,...

DN6

[Advanced DreamBooth LoRA SDXL] Support EDM-style training (follow up of #7126)

2

This PR adds support for EDM-style training to the advanced script, based off PR #7126

linoytsaban

[Fix Issue #1197 since 2022] Support pre-trained openai/guided-diffusion (ADM) with minimal code change

30

# What does this PR do? TLDR: This PR includes openai/guided-diffusion pre-trained models into diffusers, with a diverse family of pre-trained openai/guided-diffusion models, including pre-trained model with ImageNet, LSUN bedroom,...

tongdaxu

Enable ONNX export of GPU loaded SVD/SVD-XT UNet models

19

# What does this PR do? Unpack num_frames scalar if created as a (CPU) tensor in forward path Avoids mixed use of CPU and CUDA tensors which is unsupported by...

rajeevsrao

Update stable_diffusion_tensorrt_txt2img.py

23

# What does this PR do? Fixes #6984 ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if...

Bhavay-2001

Stable-Diffusion-Inpainting: Training Pipeline V1.5, V2

22

# What does this PR do? This functionality allows training/fine-tuning of the 9 channel inpainting models provided by - https://huggingface.co/stabilityai/stable-diffusion-2-inpainting - https://huggingface.co/runwayml/stable-diffusion-inpainting This is due to noticing that many inpainting...

cryptexis