diffusers

diffusers copied to clipboard

Modification on the PAG community pipeline

7

# What does this PR do? ## Perturbed-Attention Guidance This implementation is based on [Diffusers](https://huggingface.co/docs/diffusers/index). StableDiffusionPAGPipeline is a modification of StableDiffusionPipeline to support Perturbed-Attention Guidance (PAG). For more information about...

HyoungwonCho

Expansion proposal of `diffusers-cli env`

20

Coming from this discussion: #7345. Do you want me to add more or remove some of them? Also, I thought of adding GPU's model if available, but I guess it...

tolgacangoz

Load custom pipeline cause CUDA out of memory

1

### Describe the bug ``` inpaintingPipe = DiffusionPipeline.from_pretrained( 'runwayml/stable-diffusion-inpainting', torch_dtype = torch.float16, custom_pipeline = 'hd_painter' ) ``` OutOfMemoryError: CUDA out of memory. Tried to allocate 3.96 GiB. GPU 0 has...

crapthings

Loading model and LoRA in Python causes tensor shape mismatch

4

### Describe the bug Hi. Here, I am trying to do inpaint using **realisticStockPhoto** with **SDXL_FILM_PHOTOGRAPHY_STYLE** LoRA. ``` device = "cuda" model_path = "realisticStockPhoto_v20.safetensors" pipe = StableDiffusionInpaintPipeline.from_single_file(model_path,torch_dtype=torch.float16,safetensors=True).to(device) pipeline = AutoPipelineForText2Image.from_single_file("SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors",...

levoz92

fix: Fixed `requests.get()` function call by adding `timeout` parameter

2

# What does this PR do? Fixed `requests.get()` function call by adding 10 seconds `timeout`. Fixes #7730 ## Before submitting - [ ] This PR fixes a typo or improves...

Sai-Suraj-27

Noised Image

1

Hi, I'm using text_to_image_lora, and I found the variavle "X_T" is removed which prevent us feeding the noised image to diffusion. Do you think it is better to add this...

massyzs

IP-Adapter FaceID PLus How to use questions

4

https://github.com/huggingface/diffusers/blob/9ef43f38d43217f690e222a4ce0239c6a24af981/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py#L492 ## error msg: pipe.unet.encoder_hid_proj.image_projection_layers[0].clip_embeds = clip_embeds.to(dtype=torch.float16) AttributeError: 'list' object has no attribute 'to' hi！ I'm having some problems using the ip adapter FaceID PLus. Can you help me answer...

Honey-666

Add extra performance features for EMAModel, torch._foreach operations and better support for non-blocking CPU offloading

16

# What does this PR do? This adds a few extra things to EMAModel intended to reduce its overhead and allow overlapping compute and transfers better. First, I added a...

drhead

# What does this PR do? ## Problem In `UNet3DConditionModel`, there are modules like `transformer_in` and `temp_attentions` layers in down/up blocks. When adding LoRA to this module, and loading LoRA...

yhZhai

errors while trying to "convert_animatediff_motion_module_to_diffusers"

2

### Describe the bug i'm trying to use different motion adapter for animatediff . these ones especially : https://huggingface.co/ByteDance/AnimateDiff-Lightning/blob/main/animatediff_lightning_8step_comfyui.safetensors https://civitai.com/models/331718/bubbling-rings-or-animatediff-motion-lora when i try to convert the safetensors to diffusers i...

lulu1315