diffusers

diffusers copied to clipboard

refactors pipelines inheriting from `StableDiffusionPipeline`

14

We have a couple of community pipelines that used `StableDiffusionPipeline` as the base class instead of `DiffusionPipeline`. Most of them are broken after we changed the signature of `StableDiffusionPipeline`. see...

yiyixuxu

Fix multi-prompt inference

4

Fix generation of multiple images with multiple prompts, e.g len(prompts)>1, num_images_per_prompt>1 # What does this PR do? Fixes # (issue) ## Before submitting - [x] This PR fixes a typo...

nikitabalabin

add a `from_pipe` method to `DiffusionPipeline`

3

motivated by https://github.com/huggingface/diffusers/issues/6531 first, let's create a `StableDiffusionPipeline` with IP-Adapter ```python from diffusers import DiffusionPipeline, StableDiffusionSAGPipeline, MotionAdapter, PIAPipeline, UNet2DConditionModel, StableDiffusionPipeline, AnimateDiffPipeline, EulerDiscreteScheduler, DDIMScheduler from diffusers.utils import load_image, export_to_gif import torch...

yiyixuxu

[WIP] Add inpainting training script

6

# What does this PR do? Add in-painting training script.

patil-suraj

[WIP] Add Adversarial Diffusion Distillation (ADD) Script

14

# What does this PR do? This PR adds an example script for adversarial diffusion distillation (ADD) ([paper](https://arxiv.org/pdf/2311.17042.pdf), [code](https://github.com/Stability-AI/generative-models)), a distillation + adversarial training method used to distill SD/SD-XL Turbo....

dg845

Enable Gradient Checkpointing for UNet2DModel (New)

1

# What does this PR do? This PR supports gradient checkpointing for `UNet2DModel`. Successor to PR #6718. ## Before submitting - [ ] This PR fixes a typo or improves...

dg845

Custom Diffusion: RuntimeError: expected mat1 and mat2 to have the same dtype, but got: c10::Half != float

16

### Describe the bug when running custom diffusion on my 20 photos repositories ... I run into this error that is related to data type difference.. ### Reproduction !accelerate launch...

rezkanas

Add Latte: Latent Diffusion Transformer for Video Generation

1

### Model/Pipeline/Scheduler description Latte is a text2video diffusion transformer (similar to Sora), improving past the DiT and PixArt-alpha text2image models The implementation is already based on diffusers (see [latte_t2v.py](https://github.com/Vchitect/Latte/blob/main/models/latte_t2v.py)), so...

kabachuha

Issue with reproducing ip_adapter_sdxl_controlnet_demo.ipynb example from doc

2

Hi all! I met an issue when I tried to use diffusers/hugging face syntax to reproduce an [example](https://github.com/tencent-ailab/IP-Adapter/blob/main/ip_adapter_sdxl_controlnet_demo.ipynb). I am obtaining different/worse result and wondering why...  Here my [gist](https://colab.research.google.com/gist/katarzynasornat/ff9bc215c39ab6d62e5d54b55305a591/ip_adapter_example.ipynb)...

katarzynasornat

Updated stable_diffusion_tensorrt_txt2img.py

10

# 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