diffusers

diffusers copied to clipboard

JAX Integration

9

## JAX Integration This issue will be used as a tracker to integrate Stable Diffusion in JAX natively to `diffusers`. This will enable many cool use cases noteably running stable...

patrickvonplaten

VQ-Diffusion

17

### Model/Pipeline/Scheduler description VQ-Diffusion is based on a VQ-VAE whose latent space is modeled by a conditional variant of the recently developed Denoising Diffusion Probabilistic Model (DDPM). It produces significantly...

patrickvonplaten

Error for the 16gb gpu dreambooth training

5

### Describe the bug I can train without the prior preservation fine if I try to train with it I get “UNet2DConditionModel' object has no attribute 'enable_gradient_checkpointing'” I also get...

UglyStupidHonest

Can pretrained autoencoder stage be used for any new dataset training?

5

In the latent diffusion paper authors mention that: "A notable advantage of this approach is that we need to train the universal autoencoding stage only once and can therefore reuse...

Revist

How to resume from checkpoint.

1

I followed Colab for training. May I know how to resume the training. Thanks and regards

BakingBrains

Rename variables from single letter to better naming

19

Pretty much all code in https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/resnet.py still corresponds to the copy-pasted version from the beginning. While weight names shouldn't be renamed, we should rename all single letter variables to more...

patrickvonplaten

refactor(scripts): `params` and `conv_shortcut`

5

Signed-off-by: Ryan Russell This one has functional implications. @pcuenca -- I don't believe either of these `scripts` were doing what they were intended to do. - `create_ldm_bert_config()` -- Was calling...

ryanrussell

[Community] cancelable and asynchronous pipelines

20

In [#developers-corner](https://discord.com/channels/1002292111942635562/1011228667659178055/1016173296930271282) we have a request for cancellation support in the pipeline API. That could also be something to consider in the context of a more asynchronous API in general;...

keturn

[New Pipeline] Add Grad TTS

7

Note: This is still WIP So far I've added all the text and model utils to two separate files in the GradTTS pipeline folder. I've also added the `LinearAttention` function...

Vaibhavs10

Incorrect type annotations on `StableDiffusionPipeline`

3

### Describe the bug `StableDiffusionPipeline::__call__` has some parameters annotated as `Optional` when they really aren't (i.e. they shouldn't be `None`) A potential fix would be to just remove the `Optional`...

tasercake