ComfyUI
by Comfy Org · Runtime · Image
promising
Widely used way to run image models locally; its new speed claims are untested
Rewrote LLM text-generation hot path for Qwen3.x; same checkpoints generate up to 2x faster on the same GPU, same quality
AccessOpen codePricefree local (Comfy Desktop); Cloud from $20/monthRuns onWindows, macOS, LinuxLicenseGPL-3.0
Why we say so
AI Search and Fahd Mirza both got Qwen Image, MiniMax H3 Image and MOSS Image running through ComfyUI templates or workflows after updating. The 0.45.0 claims of up to 2x faster text generation (Qwen3.5 9B from 106 to 219 tok/s on an RTX 5090) come only from Comfy Org, with no independent check yet.
Evidence
- Nov 15MiniMax-H3-Image runs via ComfyUI by downloading model, VAE and text files into the models folders plus a provided workflow
- Nov 11New W4A8 GEMV tensor-core kernel with interleaved weights and scales, fused RMSNorm/SwiGLU prologues; M=8 verify rows cost about as much as M=1
- Oct 20Ships MOSS Image text-to-image and layout-guided workflow templates after updating; layout node needs Nodes 2.0 enabled
- Sep 22Qwen Image 2.1 ships with ComfyUI templates for text-to-image, edit and background removal
- Aug 23ComfyUI open-sourced Comfy MCP, letting agents like Codex see local workflows, models, nodes and GPU and build workflows from prompts
Show all 6
- Aug 5Updated ComfyUI includes MiniMax H3 text-, image- and reference-to-video templates alongside cloud API versions