diffusers

diffusers copied to clipboard

Categorical diffusion pipeline

1

### Model/Pipeline/Scheduler description Are there any plans for diffusion models other than Gaussian, e.g. categorical diffusion https://arxiv.org/abs/2102.05379 ### Open source status - [X] The model implementation is available - [X]...

ChenchaoZhao

Dreambooth inference result is not correct when training with xformer

14

I train dreambooth with xformer but the result is not correct (It’s correct without xformer). The model initialize from runwayml/stable-diffusion-v1-5, but the inference result is the same as the runwayml/stable-diffusion-v1-5....

mingqizhang

Cannot convert SD to diffusers

7

### Describe the bug Trying to convert a ckpt fine tuned from dreambooth (2.1 768) to diffusers yield the following error: KeyError: 'cond_stage_model.model.text_projection' This happens either locally or using a...

brurpo

Dynamic thresholding

2

Could be important for increased quality or robustness to "fried" areas.

pcuenca

Store cached models in location compatible with `huggingface-cli`

6

Reference: https://github.com/huggingface/huggingface_hub/issues/1259 `huggingface-cli scan-cache` doesn't see cached diffusers models. Are there any drawbacks to changing the cache folder?

pcuenca

Reference: https://github.com/huggingface/diffusers/pull/2302#issuecomment-1432873275

sayakpaul

Is there a training script for instruct pix2pix ?

3

Thanks for your great job. I found a test script for instruct pix2pix , but I cannot find the traning one. Where can I find it. Or do you plan...

tengshaofeng

Textual inv make save log both steps

19

Based on [this issue](https://github.com/huggingface/diffusers/issues/2174). Still a WIP. I'm trying to keep the logging functionality to be the same as the same functionality where every x amounts of steps, we log....

isamu-isozaki

Has anyone successfully used pre-trained models from guided diffusion with diffusers' pipeline and scheduler?

1

The models in diffusers outputs sample directly, while models in guided diffusion outputs mean and variance. Relative issue https://github.com/openai/guided-diffusion/issues/93#issue-1584632267

ntlm1686

Not copying the model in inference and assigning ema_weights seems incorrect.

3

### Describe the bug This recent commit https://github.com/huggingface/diffusers/commit/44f6bc81c764897406952bf75263b866de7c8cd3 regarding the PR #2166 removed copying the model while doing inference. Is this correct ? Aren't we substituting EMA weight to the...

dasayan05