diffusers

diffusers copied to clipboard

### Describe the bug In the diffusers [basic training tutorial](https://huggingface.co/docs/diffusers/tutorials/basic_training), setting the manual seed argument (`generator=torch.manual_seed(config.seed)`) in the pipeline call inside evaluate() function rewinds the dataloader shuffling, leading to overfitting...

yue-here

Stable Cascade fix INT8 compression with NNCF

8

# What does this PR do? Fixes NNCF compression with Stable Cascade. NNCF compresses model weight to 8 bit and reduces the model footprint by half. Full Stable Cascade model...

Disty0

It's time.

sayakpaul

Make IPAdapter compatible to `torch.compile`

9

# What does this PR do? Fixes #7985 ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if...

rootonchair

EulerDiscreteScheduler.set_timesteps() torch.from_numpy misuse error.

11

### Describe the bug In version 0.24.0, on line 283 of ``schedulers\scheduling_euler_discrete.py`` https://github.com/huggingface/diffusers/blob/76c645d3a641c879384afcb43496f0b7db8cc5cb/src/diffusers/schedulers/scheduling_euler_discrete.py#L283 An exception occurs when ``sigmas`` is a Tensor object and not a numpy array, when `self.config.interpolation_type ==...

Teriks

IPAdapter not compatible to torch.compile

2

### Describe the bug When use IPAdapter with torch.compile will return error message below: ``` torch._dynamo.exc.Unsupported: UNPACK_SEQUENCE NNModuleVariable() ``` Due to the use of this line https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/embeddings.py#L879 Which can be...

rootonchair

fix: ignore checkpoint when uploading

3

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

JeffersonQin

# What does this PR do? In the diffusers basic training tutorial, setting the manual seed argument (generator=torch.manual_seed(config.seed)) in the pipeline call inside the evaluate() function rewinds the random state...

yue-here

Fixes #7734 where some training info for DeepFloyd IF got lost when I refactored the DreamBooth docs.

stevhliu

yiyixuxu