diffusers

diffusers copied to clipboard

Merging Stable diffusion pipelines just makes sense

24

[Following the Philosophy](https://github.com/huggingface/diffusers/issues/307), it has been decided to keep different pipelines for Stable Diffusion for txt-to-img, img-to-img and inpainting. Here is the result: * PR #549 : **code duplicated 4...

leszekhanusz

Any Webui for local Dreambooth yet? I mean, to use DB to train.

5

Although I'm trying my best to dive into the who PY scene I'm at a loss. Has anyone made a Webui for DB training on your local yet? If so,...

Duemellon

converted models using convert_original_stable_diffusion_to_diffusers.py are not identical

3

### Describe the bug I have some ckpt files and I converted them using this script, while using it, there was a warning: ``` Some weights of the model checkpoint...

Neklioz

add stable_diffusion_walk notebook to example/community folder

9

Related issue: [205](https://github.com/huggingface/diffusers/issues/205) Hello, this pull request is for adding the notebook stable_diffusion_walk to community examples. this notebook is designed to be run on google colab free version. this notebook...

danielpatrickhug

Is there any outpainting pipe demo?

6

I would like to use it to outpainting images, can you help me

CrazyBoyM

Parallel dataloader for unconditional diffusion example

1

**Is your feature request related to a problem? Please describe.** The loading of the samples is sequential and without prefetching n the `train_unconditional.py` script. This results in an underutilization of...

Flova

build: show specifics of test failures in github checks

8

This uses https://github.com/marketplace/actions/junit-report-action so that the specifics of failed tests will be more visible in the GitHub UI, instead of just "process completed with exit code 1." - [ ]...

keturn

How can I transfer the self-trained model folder to a single ckpt model file?

15

I trained a model in local PC following this instruction: diffusers\examples\textual_inversion\README.md The output of the self-trained model is a folder：  I can use StableDiffusionPipeline.from_pretrained(“THE OUTPUT OF MODEL...

boyjunqiang

hight res stable diffusion gives repeated images

4

### Describe the bug I have tried to run SD on 1024x1024 and 1664x1664x resolutions, but the result is that I get almost always repeated objects in the generated picture....

batrlatom

Training memory optimizations not working on AMD hardware

17

### Describe the bug [Dreambooth training example](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) has a section about training on 16GB GPU. As Radeon Navi 21 series models all have 16GB available this in theory would increase...

errnoh