ComfyUI

With ComfyUI, you plug the workflow into your pipeline once, and every round of feedback becomes a revision in minutes across every shot, not a rebuild. Deliver more versions and faster turnarounds

ComfyUI provides full control over every stage of the pipeline. Swap models, lock seeds, and apply masks. Share workflows with team members while maintaining consistency.

NVIDIA's RTX video effects now run natively inside ComfyUI. The new NVIDIA VFX node pack brings three GPU-accelerated tools to your node graph: → RTX Video Super Resolution: 19 modes to upscale, denoise, deblur, or enhance different kinds of source material → RTX Video Frame Generation: two methods for generating new frames inside existing footage → RTX Video HDR: convert SDR footage to HDR The models are lightweight, ship with the nodes, and run locally on NVIDIA RTX GPUs. Chained together (Super Resolution → Frame Generation → HDR), they give studios a fast finishing pass before footage moves downstream in the VFX pipeline. We’re also expanding EXR support with a new Convert Image Color Space node and EXR previews in Load Image and Save Image (Advanced). Starter workflows are included for image upscaling, video upscaling, frame generation, HDR conversion, and long-form HDR using loop nodes. Click the link in the comments to install from ComfyUI Manager, or try the full VFX pipeline on Comfy Cloud ⬇️

Comfy API is live Until now, shipping a ComfyUI workflow to production meant rebuilding its environment somewhere else. Renting GPUs, reinstalling every custom node and model, untangling Python dependencies, and writing your own scaling logic. Comfy API handles that for you: → Builder reads your workflow JSON, finds the models and custom nodes it needs, and helps resolve dependency conflicts → Each Build pins the ComfyUI version, nodes, models, and Python deps together → Releases are immutable, so the environment you test is the one you deploy → Endpoints autoscale, down to zero when idle or with warm workers when latency matters → GPU time is billed by the second on RTX PRO 6000, H100, H200, or B200 Your graph stays yours, the engine stays open source, and your Builds stay portable. Click the link below to deploy your first workflow today

The Blender video defines the camera movement and perspective, giving the generation a clear motion reference while Seedance 2.5 handles the final visual output. Prompt + workflow included. To try this workflow, link below 👇 https://lnkd.in/eGRmC3BC

ComfyUI for Animation: Concept Art to Any Angle Concept art → 3D proxy → any angle you want. One graph, two methods. Step 1: load your concept art. Tripo generates a 3D model and saves it as a GLB. Drag it into Load 3D and set material mode to Normal. Step 2 (stills): rotate the viewport to your angle. Load 3D outputs the view, and GPT Image 2 renders it back as a polished on-style illustration. Step 3 (camera moves): record a path in the viewport. That clip becomes the motion reference for Seedance 2.0, which generates the move through the stylized scene. Click the link below to run the workflow ⬇️