Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Create spritesheet from 1 full body image.
Runtime profile
Source description
Create spritesheet from 1 full body image.
Required workflows
To make a spritesheet from a single image, you need 3 workflows:
Pose Selector: https://civitai.com/models/1774551
WAN2.1 Seamless loop: https://civitai.com/models/1779212/wan21-seamless-loop-with-presets-low-vram-and-fast-lora-workflow
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Image to Sprite Sheet Workflow, LOW VRAM is for turning one full-body image and generated default, Run, Jump, and Sit pose images into WebP animations and a spritesheet containing their frames.
The process starts with a full-body image, then generates default, Run, Jump, and Sit poses with Pose Selector.
Correctly scaled pose images go into WAN2.1 Seamless loop; the animation backgrounds are removed and each frame is placed in a spritesheet with WebP Animation To SpriteSheet.
Inputs include one full-body image and the generated pose images.
Outputs include WebP animations and a spritesheet containing the animation frames.
The process uses Pose Selector, WAN2.1 Seamless loop, and WebP Animation To SpriteSheet, plus GIMP, Photoshop, or Paint.NET.
The workflow requires the ComfyUI-KJNodes and ComfyUI-RMBG node packs.
Keep all characters facing the same direction and rescale the generated pose images to 1 scale.
Suggestion · not verified
Use “Idle anim” for the default pose and “Jump anim” for the Jump pose.
Suggestion · not verified
Set the first and last frame to the same frame for the loop.
Suggestion · not verified
Flux.1 Kontext may change anatomy, so generated images may match one another while differing from the reference image.
License information is not specified.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 1131 downloads · Type Workflows · Base model Flux.1 Kontext
WebP Animation To SpriteSheet: https://civitai.com/models/1779346
and some image editing software (GIMP, Photoshop, Paint.NET)
How to use
Get full body image
In Pose Selector generate image in "default pos". Why? Because Flux Kontext changing anatomy, in the generated images anatomy will be the same, but it will differ from the reference image.
And generate Run, Jump and Sit poses.
All characters should look in one side, not like in my example, where "Run" pose looking in right side, but others in left.
You need to rescale generated pose images to 1 scale. Like that.
Pose images with correct scale, put in WAN2.1 Seamless loop
First frame and Last frame should be the same.
For default pose, you need to use "Idle anim" preset
For Jump pose, you need to use "Jump anim" preset
etc.
Ok, by now you have a good WebP animations. Next step, is to remove background from animation and put every frame in spritesheet, for that, use WebP Animation To SpriteSheet .
Done.
Estimated VRAM requirement
0 GB estimated
Requirements
2 requirementsNode pack · Registry
Node pack · Registry
