Type | Workflows |
Stats | 154 0 |
Reviews | (2) |
Published | May 1, 2025 |
Base Model | |
Hash | AutoV2 1B8F4474EC |
Description
An image to video ComfyUI workflow with the video model Wan 2.1 It is based at the default workflow from the ComfyUI example page. But with some modifications. The workflow includes Florence, which analyzes the image and writes a prompt for it. It also includes a Lora.
https://comfyanonymous.github.io/ComfyUI_examples/wan/
Note that upscaling better happens in an extra step. You can find example upscaling workflows in my article about video upscaling in comfyui: https://www.tomgoodnoise.de/index.php/video-upscaling-in-comfyui/
There are some collapsed Note nodes besides the important nodes. Click at them to expand them.
The Note nodes contain further informations. And in case of the models also links to the models, and where to put them.
Howto
Drag an initial image into the image node, adjust the prompt, and press queue. The rest should fit.
Time
The example video in 480p and made with the low precision fp8 version of Wan 2.1 rendered in slow 45 minutes plus some overhead for preparation. Wan video is slow.
Requirements
This workflow was generated with 16 gb vram. Minimum requirement is 12 gb vram. And you should not have fewer than 32 gb system ram.