ComfyUI
ComfyUI, node-based local stable diffusion / image-and-video generation interface. Runs entirely on your GPU.
Release history
ComfyUI 0.33.1
Fixes KSamplerAdvanced nested latent handling, adds Minimax Music 3 and Bria image tools, improves VRAM management across platforms
ComfyUI 0.32.0
ComfyUI 0.32.0 adds LTX 2.5 support, optimizes memory handling for H3 models, and improves nested tensor debugging for complex workflows
ComfyUI 0.31.0
Reduces pinned memory on Linux systems without swap partitions
ComfyUI 0.29.2
Frontend improvements and new API/partner nodes for extending ComfyUI's extensibility and integration capabilities
ComfyUI 0.29.0
Streams video transcode instead of buffering all frames in memory
ComfyUI 0.28.0
Fixes Qwen3-VL tokenizer crash with custom embeddings; Adds AGENTS.md documentation
ComfyUI 0.27.0
Adds int8 convrot model support
ComfyUI 0.26.0
ComfyUI adds Qwen3-VL text generation, SCAIL-2 multireference, Boogu image editing, Kling V3-Turbo, Luma Rays 3.2, and job cancellation API endpoints
ComfyUI 0.25.1
ComfyUI added Kling V3-Turbo model support through partner nodes for faster video generation workflows
ComfyUI 0.25.0
ComfyUI adds audio consolidation, 3D preview nodes, partner integrations (Bria, Krea, Gemini), and performance optimizations for inference workflows
ComfyUI 0.24.0
Fixes dtype handling for birefnet and dino3 models, upgrade if using those
ComfyUI 0.23.0
MediaPipe face detection, multi-threaded model loading for faster startup, OAuth 2.1 support, and logic nodes shipped to improve performance and API standardization
ComfyUI 0.22.0
Audio processing nodes now handle None inputs gracefully
ComfyUI 0.21.1
Added Flux2, HiDream-O1, and Claude nodes, fixed fp8 safetensors saving and LTXV video alignment, improved memory usage