Diffusers
Diffusers is an open-source Hugging Face library providing pretrained diffusion models, reusable components, and pipelines for generating or manipulating images, audio, video, and other data.
Build a Text-to-Image Generator (from Scratch)
Diffusers is an open-source software library providing implementations and pipelines for diffusion models and their image-generation workflows.
- How it is used
- Provides standardized interfaces for importing diffusion models and generating images from text prompts.
- How deep it goes
- Covers installation, pipeline use, U-Net inputs and outputs, and component roles while treating U-Net internals as a black box.
- Examples
- Demonstrates pretrained image generation, prompt batches, output grids, custom resolution, and classifier-free guidance.
- What you can do after
- Apply it via StableDiffusionPipeline to generate prompt-based images and configure precision, resolution, and guidance.
Read how Build a Text-to-Image Generator (from Scratch) explains diffusers →
Deep Learning with JAX
A library of pretrained and trainable diffusion-model pipelines for generating images, audio, video, and other outputs.
- How it is used
- Provides pretrained and trainable diffusion pipelines for generating images, audio, video, molecule structures, and other outputs.
- How deep it goes
- Demonstrates pipeline loading and configuration, while deferring detailed diffusion internals and model-training procedures.
- Examples
- Uses Stable Diffusion v1-5, a TPU backend check, FlaxStableDiffusionPipeline, bfloat16 parameters, and generated image outputs.
- What you can do after
- Apply it via FlaxStableDiffusionPipeline to load a pretrained model and begin generating images with JAX.
Related concepts
- Hugging Faceproduced by · Hugging Face is a platform and ecosystem for discovering, hosting, sharing, and using machine-learning models, datasets, applications, and related tools.
- Stable Diffusionused by · Stable Diffusion is a family of latent diffusion models that generates and edits images from text and other conditioning inputs.
- StableDiffusionPipelineused by · StableDiffusionPipeline is a Diffusers pipeline component that runs Stable Diffusion text-to-image generation from a prompt.
- noise scheduleused by · A noise schedule is a prescribed sequence of noise levels or coefficients governing noise addition and removal across diffusion timesteps.
- Pythonuses · Python is a high-level, general-purpose, dynamically typed programming language known for readable syntax and automatic memory management.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.