generative image/video diffusion inference
MLX-native Python library and CLI for running state-of-the-art generative image and video diffusion models locally on Apple Silicon.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you need PyTorch, broad model support, and training utilities instead of Apple-silicon-only MLX inference.
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Choose when you need the same diffusion models in pure C/C++ with no Python or Apple-only MLX dependency.
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose for simple latent-space prompt-morphing videos with older SD models rather than modern text-to-video diffusion inference.
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Pick when you want a batteries-included PyTorch WebUI for image/video generation rather than a scriptable MLX library.
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
Choose when you want an end-to-end generative movie studio inside Blender rather than a scriptable inference library.
PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.
A demo Swift app for Core ML Stable Diffusion, an end-user tool rather than a swappable library.
Swift app demonstrating Core ML Stable Diffusion
These projects were analysed and named mflux among their alternatives. The relationship is not symmetric — how mflux rates them is a separate judgement, made when mflux is analysed in its own right.
calls mflux “An Apple MLX-native diffusion runtime; choose it for memory-efficient on-device inference on Mac, but it is Apple-only and narrower.”
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.