Seedance 2 in ComfyUI, make our own nodes!

Seedance 2.0 is an impressive AI video generation model, but it is too large to run directly on most local computers. In this video, I show you how to connect your local ComfyUI installation to Seedance 2.0 through an API and generate videos inside your familiar workflow. For this demonstration, I use Atlas Cloud. The model runs remotely, while ComfyUI sends the request, waits for the result, and automatically saves the generated video on your computer. The included custom nodes support three practical workflows: Text-to-Video generation Image-to-Video animation First-and-Last-Frame video generation Adjustable resolution, aspect ratio, and duration Optional audio generation Last-frame export for extending a scene Automatic video saving inside ComfyUI The first-and-last-frame workflow is particularly interesting because Seedance 2.0 can generate a coherent animated transition between two images while preserving a surprising amount of visual consistency. In the second part of the video, I show how much easier it has become to create your own ComfyUI custom nodes with AI-assisted programming. You do not need deep Python knowledge to start experimenting. You can describe what you want, let the AI read the API documentation, create the initial node structure, and then guide the process by reviewing requirements and fixing errors. I also explain the difference between basic vibe coding and a more structured agentic programming approach using project requirements documents, technical requirements documents, and clear implementation steps. Download Links Seedance 2.0 ComfyUI custom nodes and workflows: https://github.com/GeekatplayStudio/S... ⚠️ AFFILIATE DISCLOSURE: We may earn a commission from purchases made through the links below at no extra cost to you. My recommendations: Hitem3d: https://www.hitem3d.ai/?utm_source=af... TripoAI: http://studio.tripo3d.ai?via=geekatplay Meshy 3d AI: www.meshy.ai?via=geekatplay i10X. :https://i10x.ai?fpr=vladimir24 Topaz AI Video and Photo processing: https://topazlabs.com/ref/1514/ My Patreon webpage -   / geekatplay   Tutorials and packs - https://gumroad.com/geekatplay Tutorials website - https://www.geekatplay.com Photography - https://www.chopinephotography.com 00:00 Seedance 2.0 in ComfyUI Through API 01:09 How API-Based Video Generation Works 01:54 Connecting ComfyUI with an API Key 02:20 Creating an Atlas Cloud API Key 03:34 Adding the API Key to the ComfyUI Workflow 03:57 Three Seedance 2.0 Workflows Included 04:05 Image-to-Video Workflow 04:30 Seedance Parameters and Video Settings 04:54 Continue a Scene Using the Last Frame 05:20 How API Polling Works 06:18 Saving Generated Videos 06:41 Text-to-Video Example 06:59 Image-to-Video Example 07:08 First-and-Last-Frame Video Generation 07:26 Seedance Video Quality and Consistency 07:57 How Much Does API Video Generation Cost? 08:52 Download the Custom Nodes from GitHub 09:06 Installing the Nodes in ComfyUI 09:29 Create Your Own ComfyUI Nodes with AI 10:16 Vibe Coding vs Agentic Programming 11:03 Generating Custom Nodes with Visual Studio Code 11:19 Using GitHub AI or a Local Ollama Model 11:42 PRD, TRD, and Requirements Documents 12:53 Guiding AI Instead of Hoping for the Best 13:17 How to Fix Errors with AI Assistance 13:33 Download the Nodes or Build Your Own 14:00 Final Thoughts