diffusers

diffusers copied to clipboard

Create VAE feature extractor class

4

We currently do not have a unified API that makes sure that for pipelines that accept image inputs that image input and output format always stay the same. This PR...

patrickvonplaten

[Pipelines] On adding Pix2Pix Zero

6

[Pix2Pix Zero](https://pix2pixzero.github.io/) presents a wonderful idea for editing the objects in a generated image with finer controls. Some really amazing results:   The code for Pix2Pix Zero is available...

sayakpaul

Loading checkpoint dreambooth fine tuned sd from local disk

3

hi team, Im making many experiments fine tuning SD with dreambooth and I want to load the models directly from my local disk, im using the code from : https://github.com/nateraw/stable-diffusion-videos...

javismiles

Possible to use vit-B/32 instead of vit-L/14 for SD fine-tuning on Dreambooth?

3

I am wondering if I can change the default clip model to run my training and if so, how?

stpg06

Add option to set dtype in pipeline.to() method

3

Adds an option to set pipeline dtype along with the device using the pipeline `to()` method. I added some basic tests to check it does not affect the results, and...

1lint

[testing] tiny stable diffusion pipe throws error when used with safety checker

2

### Describe the bug The tiny stable diffusion pipeline we use for some tests throws an error when used with the safety checker. It currently doesn't throw an error in...

williamberman

CLIP Guided Image2Image

9

The CLIP guided text2img is pretty good. Would be nice to be able to use it for img2img

dblunk88

The module with `PipelineTesterMixin` already sets this. We shouldn't repeatedly set this in all tests and instead consolidate where we set it

williamberman

DEISMultistepScheduler missing get_velocity function

1

### Describe the bug scheduling_deis_multistep is almost a drop in replacement for scheduling_ddpm however it lacks the get_velocity function from scheduling_ddpm. In the project I am working on the lack...

saunderez

Update pipeline_stable_diffusion_inpaint_legacy.py resize to integer multiple of 8 instead of 32 for init image and mask

2

Hi! It seems like there is no more need to resize the init image and mask so rough - it's possible to use resolutions that are not multiples of 32....

Laveraaa