ComfyUI (@ComfyUI) / X

Pinned

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It

00:00

Trellis.2 and Pixal3D are now native in ComfyUI core No custom nodes. No CUDA extensions. No PyTorch downgrade. No non-commercial license traps. Plus a rebuilt 3D pipeline: Load/Preview/Save 3D nodes, mesh post-processing, and PBR texturing that bakes normals + AO for a full

00:00

ComfyUI Tutorial for Beginners: Text-to-Image & Image-to-Image Workflows One graph, two workflows and Module 2 is where you build it node by node instead of loading someone else's. We start from a blank canvas and wire every connection, then change a single value and turn the

00:00

SAM 3D Body is open-source, so it can be run locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, links below 👇

00:00

Gemini Omni 1.1 Flash is live in ComfyUI via Partner Nodes. Google's multimodal video model, one node, five task types: → text-to-video → image-to-video → reference-to-video → edit → extend Up to 4K. Audio generated with every clip. Editing is conversational — "make this

00:00

11