This workflow automates the conversion of a single sprite image into game-ready assets. It uses Wan 2.2 to generate a smooth, looping animation from a reference image, then extracts a specific number of frames to...
Runtime profile
Source description
This workflow automates the conversion of a single sprite image into game-ready assets. It uses Wan 2.2 to generate a smooth, looping animation from a reference image, then extracts a specific number of frames to ensure a clean animation cycle. These frames are processed through a Nearest-Exact downscaler to reach a sharp 64x64 pixel resolution, preserving the chunky pixel art aesthetic without the usual AI blur. Finally, it automatically stitches the frames into a perfectly aligned horizontal sprite sheet ready for immediate use in any 2D game engine. Use a 480 X 480 input image.
Estimated VRAM requirement
Estimate unavailable
10.6 GB across 1 of 5 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Sprite sheet generator converts one 480 X 480 sprite image into game-ready assets. It generates a looping animation, extracts frames, downsizes them to 64x64 pixels, and stitches them into a horizontal sprite sheet for a 2D game engine.
Wan 2.2 generates a smooth, looping animation from the reference image.
The workflow extracts a specific number of frames, applies Nearest-Exact downscaling, and stitches the frames into a horizontal sprite sheet.
Input: one 480 X 480 sprite image.
Outputs include 64x64-pixel frames and a horizontal sprite sheet intended for a 2D game engine.
The workflow is published by Fellowricky on Civitai.
Its listed base model is Wan Video 2.2 I2V-A14B.
The listed model files include clip_vision_h.safetensors, umt5_xxl_fp16.safetensors, wan_2.1_vae.safetensors, and Wan2_2-I2V-A14B-HIGH_fp8_e5m2_scaled_KJ.safetensors.
Other listed files and node packs are Wan2_2-I2V-A14B-LOW_fp8_e5m2_scaled_KJ.safetensors, ComfyUI_Comfyroll_CustomNodes, comfyui_essentials, and comfyui-easy-use.
Additional node packs are comfyui-kjnodes, comfyui-tooling-nodes, comfyui-videohelpersuite, and rgthree-comfy.
Nearest-Exact downscaling is used to preserve the chunky pixel art aesthetic.
Before use, verify that clip_vision_h.safetensors, wan_2.1_vae.safetensors, Wan2_2-I2V-A14B-HIGH_fp8_e5m2_scaled_KJ.safetensors, and Wan2_2-I2V-A14B-LOW_fp8_e5m2_scaled_KJ.safetensors are available.
Suggestion · not verified
Before use, verify that was-ns is available.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 914 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Requirements
13 requirementsVision model · Unknown
Text encoder · 10.6 GB · SAFETENSORS · Unknown
VAE · Unknown
Wan2_2-I2V-A14B-HIGH_fp8_e5m2_scaled_KJ.safetensors
Not resolvedCheckpoint · Unknown
Wan2_2-I2V-A14B-LOW_fp8_e5m2_scaled_KJ.safetensors
Not resolvedCheckpoint · Unknown
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
was-ns
Not resolvedNode pack · Registry