diffusers

diffusers copied to clipboard

Fix for "no lora weight found module" with some loras

3

# What does this PR do? When using some LoRAs, for example [sd_xl_offset_example-lora_1.0.safetensors](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_offset_example-lora_1.0.safetensors) with blockwise scales we get this error: ``` RuntimeError: No LoRA weight found for module down_blocks.0.resnets.0.conv1 ```...

asomoza

Error when using blockwise scales with sd_xl_offset_example-lora_1.0.safetensors

3

### Describe the bug When loading the [sd_xl_offset_example-lora_1.0.safetensors](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_offset_example-lora_1.0.safetensors) from the [official repository](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/) and setting the scales by blocks, it throws this error: `RuntimeError: No LoRA weight found for module down_blocks.0.resnets.0.conv1`...

asomoza

[docs] Files and formats

3

This PR attempts to clarify the difference between file types (`safetensors`, `ckpt`, `bin`) and storage layout (multifolder, single file) to avoid confusion when discussing "Diffusers" format and "single file" format....

stevhliu

Bump jinja2 from 3.1.3 to 3.1.4 in /examples/research_projects/realfill

1

Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.3 to 3.1.4. Release notes Sourced from jinja2's releases. 3.1.4 This is the Jinja 3.1.4 security release, which fixes security issues and bugs but does not otherwise...

dependabot[bot]

diffusers0.19.3

1

### Describe the bug diffusers0.19.3，in pipeline_controlnet.py， in \__call__(),`cross_attention_kwargs: Optional[Dict[str, Any]] = None,`, but pipe(cross_attention_kwargs={"scale": 0.8}) has problem: File "/lib/python3.8/site-packages/diffusers/models/attention_processor.py", line 322, in forward return self.processor( TypeError: __call__() got an unexpected...

icedCoffe001

How to let diffusers use local code for pipelineinstead of download it online everytime We use it?

6

I tried to use the instaflowpipeline from example/community to.run my test However, even after i git cloned the repository to my environment it still Keep trying to Download the latest...

Kevin-shihello-world

### Describe the bug Scenery: Developing a face editing server using fastapi+celery+diffusers, each request will generate a celery task. Concurrence: 2 workers for fastapi, 1 worker for celery Diffusers usage:...

weiweiwang

CombinedPipeline fails to accept bfloat16 image tensor as input

14

`StableCascadeCombinedPipeLine` accepts an `images` argument that can be a PIL image, a torch tensor, or a list of either. Unfortunately, I can't get it to accept a bfloat16 type for...

Michael-F-Ellis

DreamBooth: Not applying accelerator.accumulate on text_encoder

4

### Describe the bug At [examples/dreambooth/train_dreambooth_lora_sdxl.py#L1618](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_sdxl.py#L1618), only `unet` is applied with `accelerator.accumulate()`. ```python for step, batch in enumerate(train_dataloader): with accelerator.accumulate(unet): # HERE pixel_values = batch["pixel_values"].to(dtype=vae.dtype) prompts = batch["prompts"] ``` However,...

immortalCO

There may be a mistake in apply_forward_hook

3

### Describe the bug After I put different models of my own diffusion pipeline based on _DiffusionPipeline_ to different devices, in case the model's inputs and weights are not on...

InuyashaLee