This ComfyUI workflow is designed to convert video footage into a temporally stable normal map, which is particularly useful for enhancing 3D modeling and animation projects. By leveraging nodes such as the NormalCrafterNode and VHS_LoadVideo, the workflow processes each frame of the video to extract and generate a normal map that maintains consistency across frames. This temporal stability is crucial for applications where seamless transitions between frames are necessary, such as in video games or cinematic visual effects.
The workflow begins by loading the video using the VHS_LoadVideo node, which extracts individual frames and prepares them for processing. The NormalCrafterNode then takes these frames and computes the normal maps, ensuring that the lighting and shading information is accurately represented. The VHS_VideoCombine node is used to reassemble the processed frames back into a video format, while the VHS_VideoInfo node provides metadata about the video, such as frame rate and resolution. This combination of nodes makes the workflow highly effective for creating high-quality normal maps from video content, which can be used to add depth and realism to 3D environments.
FAQ
Frequently Asked Questions
Seedance 2.0: Reference to Video


Nano Banana 2 Lite: Text to Image

Seedream 5.0 Pro: Image Edit

Krea-2: Text to Image
4K Seedance 2.0 - Reference to Video


Z-Image-Turbo Text to Image
Grok: Image Edit
Nano Banana 2 Lite: Image Edit
Grok: Video generation

Seedance2.0 4K: Reference to Video

Grok Imagine Image Quality: Generation
LTX 2.3 - Lipdub LoRA + Voice Clone
Seedance 2.0 Mini: Reference to Video
SCAIL-2: Character Replacement

Ideogram v4: Text to Image
Googly Eyes

Seedance 2.0 - Viral Videos Character Swap
Gemini Omni Flash: Image to Video

Nano Banana 2: Image Edit


cinematic_annotate_video
HappyHorse 1.1: Text to Video
HappyHorse 1.1: Image to Video
Beeble SwitchX: Video Edit

3x3 Contact Sheet
Restore Archival Footage - LTX 2.3 Dearchive LoRA















