diffusers

diffusers copied to clipboard

StableDiffusionPipeline.from_single_file() with CKPT fails: "UnpicklingError: Weights only load failed"

12

### Describe the bug Trying to load local CKPT file using the "from_single_file()" method fails. Works fine with .safetensors file from same repo (Runway ML SD). ### Reproduction ```import torch...

whydna

Remove redundant comparison inside the diffusion loop of stable video diffusion pipeline

7

**Is your feature request related to a problem? Please describe.** I found that the inside the `__call__` of stable video diffusion keeps doing async memcpy between host to device as...

dianyo

Modify apply_overlay for inpainting with padding_mask_crop (Inpainting area: "Only Masked")

8

# What does this PR do? First of all, thanks for your great work. Here is my personal understanding. If there are any mistakes, feel free to correct me! Regardless...

clarkkent0618

Error when setting num_single_layers=0 while training flux-controlnet on a multi-GPU server using a single GPU

6

### Describe the bug While training flux-controlnet on a multi-GPU server and restricting the training to a single GPU, setting **_num_single_layers=0_** leads to an error: [rank0]: Parameter indices which did...

wangherr

[SD3 ControlNet] bug in pipeline 'controlnet_pooled_projections'

4

### Describe the bug Hi, I think I found an issue that causes a misalignment between training and inference in SD3 ControlNet. https://github.com/huggingface/diffusers/blob/a3e8d3f7deed140f57a28d82dd0b5d965bd0fb09/src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet.py#L977 I think the if-else block starting there...

tobiasfshr

[flux dreambooth lora training] make LoRA target modules configurable + small bug fix

1

new feature for the Flux dreambooth lora training script: - make LoRA target modules configurable through `--lora_blocks` - change the current default target modules to not be attention layers only...

linoytsaban

[LoRA] make `set_adapters()` robust on silent failures.

4

# What does this PR do? Currently, if we do ```py scales = {"text_encoder": 0.0, "text_encoder_2": 0.0, "unet": 0.0} pipe.set_adapters("optimus", adapter_weights=scales) ``` where `pipe` is an instance of the `FluxPipeline`...

sayakpaul

[Tests] clean up and refactor gradient checkpointing tests

2

# What does this PR do? Gradient checkpointing is an essential component of model training. We need to ensure it's implemented properly. If we had them implemented properly we could...

sayakpaul

[Core] Set `weights_only=True` nicely when we use `torch.load()`.

8

# What does this PR do? See internal discussion: https://pytorch.slack.com/archives/CN963QVJB/p1722612785082449. Can propagate this PR to `examples/` and `scripts/` after I have an approval.

sayakpaul

adds the pipeline for pixart alpha controlnet

24

this PR adds the controlnet pipeline for the pixart alpha diffusion model the following example uses the HED edge to control the generation. ``` import torch import torchvision.transforms as T...

raulc0399