This repository provides Animon integration for ComfyUI, offering a set of custom nodes powered by the Animon API. With these nodes, you can generate videos from images, interpolate between start and end frames, and upscale videos — all with more flexibility and control than the Animon web interface.
We are actively working to bring more features and APIs to match the full capabilities of the Animon platform.
⚠️ Note: This extension requires a newer version of ComfyUI, as it depends on updated node definitions. It also utilizes official ComfyUI nodes likeSaveVideoto write video files to disk.
Currently, only custom nodes are supported. Support for official ComfyUI API nodes is in development and will be released soon.
Installation is manual for now. Integration with ComfyUI-Manager is planned.
-
Clone this repository into the
custom_nodesfolder of your ComfyUI directory:git clone https://github.com/IamCreateAI/ComfyUI-Animon.git
-
Install the required dependencies:
pip install -r requirements.txt
-
Start or restart ComfyUI to load the new nodes.
-
Obtain your API key from the Animon API Platform.
-
Open one of the example workflows (e.g.,
AnimonI2V), enter your API key, and run the workflow.
You can find several example workflows in the workflows folder. Try them out to explore different use cases!
Generates a video from a single first-frame image and a text prompt.
Generates a video using both a starting image and an ending image.
Notes:
- If using more than one image, you must upload them to the server first.
- This workflow demonstrates two upload methods:
Animon Upload Image– upload local image files directly.ComfyUI Load Image→Animon Upload Image (from Tensor)– load and upload images from tensors.
💡 Tip: The start and end frames can be the same image. In that case, you can reuse the
VIDEO_IDfrom a previous generation instead of uploading again.
Upscales a video to 1080P at 24 FPS.
Requirements:
- Input video must be smaller than 1080P.
- Input must contain no more than 360 frames.
This workflow combines both generation and upscaling in a seamless process: it first generates a video from an image and a text prompt, then upscales the resulting video to 1080P resolution, and finally outputs the high-resolution result.
Animon provides three types of nodes for use in ComfyUI:
- Key Node – for setting your API key.
- Generate Nodes – for generating videos.
- Upload Nodes – for uploading images/videos.
To add a node: Right-click in the ComfyUI workspace → Add Node → Animon → Node Name.
This node is used to input your Animon API key, available from the Animon API platform.
⚠️ Important:
Always remove your API key before sharing workflows.
If you forget, disable the key immediately via the Animon platform.
These nodes handle video generation. Currently supported: Image to Video, Start-End Frame to Video, Upscale Video.
You can choose the generation model in the node settings.
Supported Models
1-5andpro-1-5serials- Up to 81 frames at 16 FPS for 480P / 720P
pro-1-6serials- Up to 81 frames at 16 FPS for 480P / 720P / 1080P
When using multiple images or videos, you must upload them to the server before generation.
Use Animon Upload Image or Animon Upload Video like ComfyUI’s LoadImage or LoadVideo.
Then connect the resulting IMAGE_ID or VIDEO_ID to a generation node.
If you generate images/videos using other ComfyUI nodes (e.g., Stable Diffusion), use: Animon Upload Image (from Tensor) or Animon Upload Video (from Tensor).
These convert ComfyUI's internal IMAGE type into an IMAGE_ID or VIDEO_ID usable by Animon.
To reuse a video generated by Animon, use Animon Upload Video (from Bytes) and link VIDEO_BYTES from any Animon generation node.
💡 This method avoids re-encoding and is faster than uploading from tensor.
We welcome feedback, feature requests, and contributions!
Feel free to open an issue or pull request on GitHub.