diffusers

diffusers copied to clipboard

[feature] Proposal for supporting callbacks

2

# What does this PR do? Fixes #7736. This is a work-in-progress attempt at a proposal for officially supporting callbacks in diffusers. It is inspired by the design of transformers...

a-r-r-o-w

[Refactor] Better align `from_single_file` logic with `from_pretrained`

5

# What does this PR do? Single file loading is still far from ideal. We should aim to align the behaviour as close to from_pretrained as possible (with the goal...

DN6

[Model Card] standardize advanced diffusion training sd15 lora

5

# What does this PR do? Fixes #6891 for [Advanced Diffusion Training with LoRA](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py) Notebook example: [Jupyter notebook](https://huggingface.co/abby101/test-model-card-template-dreambooth-sd15-lora-adv/blob/main/test-model-card-template-dreambooth-sd15-lora-adv.ipynb) Example model card: [Model Card](https://huggingface.co/abby101/test-model-card-template-dreambooth-sd15-lora-adv) ## Before submitting - [ ] This...

chiral-carbon

[Model Card] standardize advanced diffusion training sdxl lora

14

# What does this PR do? Fixes #6891 for [Advanced Diffusion Training SDXL with LoRA](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py) Notebook example: [Jupyter notebook](https://huggingface.co/abby101/test-model-card-template-dreambooth-sdxl-lora-adv/blob/main/test-model-card-template-dreambooth-sdxl-lora-adv.ipynb) Example model card: [Model Card](https://huggingface.co/abby101/test-model-card-template-dreambooth-sdxl-lora-adv) ## Before submitting - [ ]...

chiral-carbon

Accelerate error when training with train_dreambooth_lora_sdxl_advanced.py

7

### Describe the bug Encountered this error with zero information, when using 'train_dreambooth_lora_sdxl_advanced.py', Traceback (most recent call last): File "/usr/local/bin/accelerate", line 8, in sys.exit(main()) File "/usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate_cli.py", line 46, in main...

nayan-dhabarde

Training Lora Fails after latest update

4

### Describe the bug After updating to latest the script to train a lora fails, I'll attach the error below. ### Reproduction accelerate launch train_dreambooth_lora_sdxl_advanced.py \ --pretrained_model_name_or_path=$MODEL_NAME \ --pretrained_vae_model_name_or_path=$VAE_PATH \...

pedropaf

Add B-Lora training option to the advanced dreambooth lora script

4

Adds an option to train a dreambooth lora targeting using a single ref image + targeting specific unet blocks only, subsequently allowing for easy combination of style/content LoRAs, as proposed...

linoytsaban

move long-prompt weighting code to utils

42

Long-prompt weighting pipeline can't be used with other pipelines e.g. StableDiffusionKDiffusionPipeline this PR moves long-prompt weighting code to utils so that long-prompt weighting can be used with any pipeline: ```...

noskill

Converting safetensors file with "_pickle.UnpicklingError: invalid load key, ' '."

1

### Describe the bug I'm trying to convert safetensors files on civitai to diffusers using the convert_original_stable_diffusion_to_diffusers.py script, and I'm getting ' ' error, my pytorch version is 2.22 and...

hoyAng96

Analysis of Classifier-Free Guidance Weight Schedulers

7

### Model/Pipeline/Scheduler description The paper's authors performs an analysis and proposes 1 line change in order to make Classifier-Free Guidance looks better  I personally run some test to confirm...

rootonchair