diffusers

diffusers copied to clipboard

Flax: trickle down `norm_num_groups`

4

`FlaxEncoder` receives it [here](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/vae_flax.py#L326), but then it's ignored. `FlaxResnetBlock2D` uses a [hardcoded value](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/vae_flax.py#L99). Discovered by @younesbelkada in https://github.com/huggingface/diffusers/pull/589#discussion_r975796548

pcuenca

[textual_inversion] Add an option for only saving the embeddings

17

The textual inversion example now saves by default only the learned embeddings, unless the command line arguments --save_full_model or --push_to_hub are used. (Implements #759)

allo-

inpainting doesn't work with CPU

5

### Describe the bug Using the inpainting example but trying to run it on the cpu instead of gpu (since i'm trying to push to hf space). Hitting this runtime...

krrishdholakia

Stable Diffusion image-to-image and inpaint using onnx.

8

Hi, I added Stable Diffusion image-to-image and inpaint using onnx. I used non-onnx versions as "templates" and translated them according to existing text-to-image onnx. The only problem is that this...

zledas

Stable Diffusion: providing a list of positive prompts and a list of negative prompts does not work as expected

1

### Describe the bug See this forum post: https://discuss.huggingface.co/t/stable-diffusion-bs-1-uses-negative-as-prompt/24130. In short: ```Python _ = pipe(["frog"]*2, negative_prompt=["bird"]*2) ``` Reaches this condition https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py#L247. As expected, `negative_prompt` is a list with the same...

pcuenca

Enhancement for dreambooth

2

compustar

CUDA out of memory when i want to train dreambooth

6

### Describe the bug I'm using T4 with colab free , when I start training it tells me cuda error, it happens when I activate prior_preservation.  Run training ```...

loboere

CI testing on `mps`

1

We should add a couple of simple tests that use the `mps` device to detect issues like #760. I'm not familiar with how the CI system is set up or...

pcuenca

Support for load hypernet finetune .pt file

4

does the txt2img pipe support load a finetune .pt file to improve the output performance of checkpoint model ?

CrazyBoyM

problem when training, The following values were not passed to `accelerate launch` and had defaults used instead:

1

The following values were not passed to `accelerate launch` and had defaults used instead: `--num_cpu_threads_per_process` was set to `6` to improve out-of-box performance To avoid this warning pass in values...

ivaxsirc