
TVPaint Animation
The digital solution for your professional 2D animation projects.

State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

π€ Diffusers is a modular, open-source library built on PyTorch for state-of-the-art diffusion models, enabling image, audio, and 3D structure generation. The library prioritizes usability, simplicity, and customizability, offering pretrained models and interchangeable noise schedulers. It supports both simple inference and custom training workflows. Diffusers includes diffusion pipelines for quick inference with minimal code, various noise schedulers to control diffusion speed and output quality, and pretrained models combinable with schedulers for building custom diffusion systems. It facilitates the creation of end-to-end diffusion-based applications, offering flexibility in model architecture and training techniques. The library is designed for developers to easily integrate and experiment with different diffusion models and algorithms.
π€ Diffusers is a modular, open-source library built on PyTorch for state-of-the-art diffusion models, enabling image, audio, and 3D structure generation.
Explore all tools that specialize in generate photorealistic images. This domain focus ensures π€ Diffusers delivers optimized results for this specific requirement.
Explore all tools that specialize in audio generation. This domain focus ensures π€ Diffusers delivers optimized results for this specific requirement.
Allows users to swap different noise schedulers within a diffusion pipeline, enabling experimentation with varying diffusion speeds and output qualities.
The library is designed with a modular architecture, making it easy to swap out individual components like models and schedulers.
Offers a wide range of pretrained diffusion models that can be used as building blocks for generating images, audio, and 3D structures.
Supports training custom diffusion models with different training techniques, allowing users to fine-tune models for specific tasks.
Provides guides on optimizing diffusion models to run faster and consume less memory, making them suitable for deployment in resource-constrained environments.
Install π€ Diffusers using pip: `pip install --upgrade diffusers[torch]`
Import the necessary modules: `from diffusers import DiffusionPipeline`
Load a pretrained diffusion model: `pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)`
Move the pipeline to the GPU: `pipeline.to("cuda")`
Generate an output using the pipeline: `image = pipeline("An image of a squirrel in Picasso style").images[0]`
Process and display/save the generated output.
All Set
Ready to go
Verified feedback from other users.
"Diffusers is highly regarded for its flexibility, ease of use, and the quality of generated outputs, though performance can be a concern depending on hardware."
Post questions, share tips, and help other users.

The digital solution for your professional 2D animation projects.

Empowering independent artists with digital music distribution, publishing administration, and promotional tools.

Convert creative micro-blogs into high-performance web presences using generative AI and Automattic's core infrastructure.

Fashion design technology software and machinery for apparel product development.

Instantly turns any text to natural sounding speech for listening online or generating downloadable audio.

Professional studio-quality AI headshot generator for individuals and teams.