diffusers

diffusers copied to clipboard

how can i know what the model base are

1

from transformers import DiffusionPipeline base_model_id = "anything-v3-fp16-pruned.safetensors" pipeline = DiffusionPipeline.from_pretrained( base_model_id, model_dir=model_dir, use_safetensors=True, )

xalteropsx

[ko] Translating docs(Conceptual Guides) to Korean.

3

Hello! Thank you for creating a wonderful repository. I would like to start translation about these four documents in Korean. - [ ] [Philosophy](https://github.com/huggingface/diffusers/blob/main/docs/source/en/conceptual/philosophy.md) - [ ] [Diffusers’ Ethical Guidelines](https://github.com/huggingface/diffusers/blob/main/docs/source/en/conceptual/ethical_guidelines.md)...

mreraser

Combining community pipeline for image generation

3

### Describe the bug I cannot use both stable diffusion XL [reference ](https://github.com/Mikubill/sd-webui-controlnet/discussions/1236) and [Instant ID](https://github.com/InstantID/InstantID) in the same pipeline. I get `'FrozenDict' object has no attribute 'block_out_channels'"` ### Reproduction...

Fqlox

add PAG support

10

we are interested in integrating [PAG](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) into diffusers and want to use this PR to understand its compatibility and meaningful use cases. A few cases we know it should be...

yiyixuxu

### Model/Pipeline/Scheduler description Existing methods for facial identity transfer for diffusion denoising image generation models face challenges in achieving high fidelity and detailed identity (ID) consistency, primarily due to insufficient...

clarencechen

Add the SDE variant of DPM-Solver and DPM-Solver++ to DPM Single Step

21

Following up on our conversation at https://github.com/huggingface/diffusers/issues/4167#issuecomment-1648464442 Uses the same approach as https://github.com/huggingface/diffusers/pull/3344/files **Note:** This PR is not ready to merge yet, since it's not clear whether to use `sigma_s0`...

cmdr2

PyTorch 2.3.0 Incompatibility with Current Diffusers Library

5

### Describe the bug When running the StableDiffusionXLPipeline with a specific model file (Clay_SDXL.safetensors), inference works correctly on CPU but results in a segmentation fault when run on GPU. Below...

JethroChow

get stuck when save_state using DeepSpeed backend under training train_text_to_image_lora

16

### Describe the bug When using DeepSpeed backend, training is ok but get stuck in `accelerator.save_state(save_path)`. If use MULTI_GPU, the process is OK. The training script is ``` accelerate launch...

better629

### Model/Pipeline/Scheduler description ```diff # pip install mulankit from diffusers import StableDiffusionPipeline + import mulankit pipe = StableDiffusionPipeline.from_pretrained('Lykon/dreamshaper-8') + pipe = mulankit.transform(pipe, 'mulanai/mulan-lang-adapter::sd15_aesthetic.pth') image = pipe('一只蓝色的🐶 in the 바다').images[0] ```...

Zeqiang-Lai

Official callback tests

10

# What does this PR do? Tests for the official callbacks introduced in #7761 - [X] official callback test - [ ] multiple official callbacks test - [X] SD tests...

asomoza