ComfyUI-SayMaker

ComfyUI-SayMaker

ComfyUI nodes that run SayMaker's image and video models from a graph: generate an image, edit one, or animate it into a clip with Veo 3.1, Kling 3.0, Seedance 2.0 or MiniMax H3. One API key covers the whole shelf, including Nano Banana 2, GPT Image 2.5 and Seedream 5.0. No local GPU, no model downloads.

| Node | Inputs | Outputs | |---|---|---| | SayMaker Generate Image | prompt, aspect ratio, model | IMAGE, url | | SayMaker Edit Image | IMAGE, instruction, model | IMAGE, url | | SayMaker Image to Video | IMAGE, prompt, model, duration | path of the saved MP4 (in ComfyUI's output folder), url |

Install

ComfyUI Manager: search ComfyUI-SayMaker. Or clone into custom_nodes:

cd ComfyUI/custom_nodes
git clone https://github.com/hanshs474/ComfyUI-SayMaker

No extra Python dependencies: the client uses the standard library, and the nodes use the torch, numpy and Pillow that ComfyUI already ships.

API key

Sign up on saymaker.ai (new accounts get sign-up credits), create a key at saymaker.ai/settings/apikeys, and either paste it into the node's api_key field or set SAYMAKER_API_KEY before starting ComfyUI.

Models

• Images: saymaker-image-v1 (cheapest), nano-banana-2-lite (default for edits), nano-banana-2, gpt-image-2-5-flare, seedream-5-pro, qwen-image-3-pro
• Video: minimax-h3-fast (runs on a free account), veo-3-1, kling-3-0, seedance-2, seedance-2-5, wan-3-0. The ones beyond minimax-h3-fast need a plan or a credit pack (pricing).

For an edit, the instruction names the change and what must stay ("keep the label unchanged"). That second half is what decides whether the edit holds.

Runs on a free account wait in a queue before they start, and video takes minutes; the node blocks until the file is ready. Change seed to force a new run with the same inputs. Every run also lands in your library at saymaker.ai/history.

MIT licensed.