ComfyUI launches Comfy API: deploy workflow JSONs as autoscaling endpoints
PurzBeats · x · 2026-10-01
ComfyUI has officially launched Comfy API, aimed at developers productizing ComfyUI workflows:
- Submit a workflow JSON and the platform resolves and pins all dependencies — custom nodes, models, LoRAs, Python deps, plus the ComfyUI version itself — into a versioned Build
- Each build cuts an immutable release, so what you test is exactly what ships
- Deploys as an autoscaling inference endpoint on RTX PRO 6000, H100, H200, or B200 GPUs
In effect, ComfyUI is upgraded from a local tool into a hosted media-generation inference stack, removing the engineering overhead of dependency resolution and deployment.
Related event: ComfyUI Launches Comfy API for One-Click Workflow Deployment(3 posts)→
More from Infra
- Pareto partners with Engy to bring Bittensor SN10 inference optimization to external customers — markjeffrey · 2026-10-01
- Respan launches Span-01 router: 37% cheaper than best single model at matching accuracy — ycombinator · 2026-10-01
- RTX 3090 power can be dialed down to 120W for inference, saving power and heat — QuixiAI · 2026-10-01
- AI as compiler: model writes PTX directly, 1.37x speedup on FlashAttention over Triton — Azaliamirh · 2026-10-01
- Dell ships first Vera Rubin NVL72 rack-scale systems in volume, citing unprecedented NVIDIA partnership — yenkel · 2026-10-01
- Shibaura Tech's Ozaki Scheme II lands in CUDA 13.4, squeezing FP64 from AI-focused GPUs — udmrzn · 2026-10-01