diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler from diffusers.utils import load_image import torch base_model_path = "stable-diffusion-v1-5/stable-diffusion-v1-5" controlnet_path = "./output/checkpoint-12500/controlnet/" controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16) pipe = StableDiffusionControlNetPipeline.from_pretrained( base_model_path, controlnet=controlnet, torch_dtype=torch.float16 ) #...
# What does this PR do? We should handle logging (including the progress bar stuff) gracefully when operating under distributed setups. Before this PR: ```bash Loading pipeline components...: 0%| |...
# What does this PR do? Added support to load checkpoints from a single file where some modifications were required to `convert_wan_transformer_to_diffusers` method for it to work with `WanAnimateTransformer3DModel` best...
# What does this PR do? In the file `examples/server-async/utils/requestscopedpipeline.py`, add thread-safe wrappers for the tokenizer, VAE, and image processor. Introduce locking mechanisms to ensure thread safety during concurrent access....
## What does this PR do? Fixes duplicate timesteps issue in `DPMSolverMultistepScheduler` when using various sigma conversion methods (Karras, Lu, exponential, beta) combined with `beta_schedule="squaredcos_cap_v2"`. ## Before this PR -...
### Model/Pipeline/Scheduler description I have written and opened a PR for implementation of img2img pipeline for Z-Image. #12751 ### Open source status - [x] The model implementation is available. -...
# What does this PR do? Migrates the LoRA pipeline tests (`tests/lora/`) to pure `pytest` because it has multiple advantages. ## Summary of changes 1. Use proper `pytest` fixtures wherever...
# What does this PR do? Adds CP support to the `kernels`-based attention backends. Our CP support is quickly gaining traction. Currently, we have a few attention backends that are...
…_img2img.py The training script incorrectly accessed `Flux2ImageProcessor.image_processor` which doesn't exist as a class attribute, causing AttributeError when running Flux2 img2img DreamBooth training. Changes: - Initialize Flux2ImageProcessor instance in DreamBoothDataset.__init__ -...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.