diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Storage space can be an issue when training models, especially when using a Google collab and saving the model to a google drive so it isn't lost when the collab...
This pull request allows to log interim generation during Dreambooth. **Usage** add an argument `--generating_progress_steps `. The process generates an interim image per steps you choose. To be able to...
**What API design would you like to have changed or added to the library? Why?** API: UNet2DConditionModel Reason: When I use this module for a simple initialization, it tries to...
1. updated the pipeline for the latest diffuser version 0.10.2. 2. updated the readme of its usage.
Allow safety checker pipeline configuration that returns boolean array but does not black out images
**Is your feature request related to a problem? Please describe.** See this PR comment: https://github.com/huggingface/diffusers/pull/815#discussion_r994418216 TLDR: with recent changes in #815, developers have the ability to disable the safety checker....
Here is my training configuration : ``` accelerate launch train_dreambooth.py \ --pretrained_model_name_or_path="stabilityai/stable-diffusion-2-1" \ --pretrained_vae_name_or_path="stabilityai/sd-vae-ft-mse" \ --output_dir="./zwx/" \ --revision="fp16" \ --with_prior_preservation --prior_loss_weight=1.0 \ --seed=1337 \ --resolution=768 \ --train_batch_size=1 \ --train_text_encoder \...
### Describe the bug When I am using diffuser library to merge repaint pipeline logic with the SD-inpaint-pipeline-legacy, I observed an obvious performance drop which is very curious to me....
Starting to work on implementing [PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS](https://arxiv.org/pdf/2202.00512.pdf) This is very much a draft PR. So far I've included a toy example in a notebook....
Since https://github.com/huggingface/diffusers/pull/505 is merged, the resolution requirements for img2img are relaxed and could be a multiple of 8. Sample code: ```python import requests import torch from PIL import Image from...
Hi. When I am training a stable diffusion 2.1 768px model, I see this line in my CLI under Windows and Conda env: CUDA SETUP: Loading binary....... libbitsandbytes_cuda116.dll I wonder...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.