ComfyUI Node
ColorMNet Video Colorization (New)
A ComfyUI node in ColorMNet/Video with 10 inputs and 2 outputs.
ColorMNet Video Colorization (New)
- video_frames
- reference_image
- colorized_frames
- performance_report
◄target_width768►
◄target_height432►
◄memory_modebalanced►
◄feature_encoderresnet50►
◄use_fp16true►
◄use_torch_compilefalse►
◄text_guidance►
◄text_guidance_weight0.30►
CategoryColorMNet/Video
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| video_frames | IMAGE | Batch of video frames to be colorized [N, H, W, 3] | |
| reference_image | IMAGE | Color reference image that provides the color palette | |
| target_width | INT | 76864–2048 | Output width - must be multiple of 32 (will be adjusted automatically) |
| target_height | INT | 43264–2048 | Output height - must be multiple of 32 (will be adjusted automatically) |
| memory_mode | COMBO | balanced | Memory management strategy: 'low_memory' for large videos, 'high_quality' for best results, 'balanced' for general use |
| feature_encoder | COMBO | resnet50 | Feature extraction model: resnet50 (ColorMNet default), vgg19 (fast), dinov2_vitb (recommended, 40-60% better), dinov2_vitl (best quality), clip_vitb (text-guided) |
| use_fp16 | BOOLEAN | true | Use half-precision (FP16) for faster processing with lower VRAM usage (minimal quality impact) |
| use_torch_compile | BOOLEAN | false | Enable torch.compile optimization for 15-25% speedup (increases first-run compilation time) |
| text_guidanceopt | STRING | Text prompt to guide colorization (only for clip_vitb encoder). Examples: 'warm sunset colors', 'vibrant anime style', 'cold winter landscape' | |
| text_guidance_weightopt | FLOAT | 0.300–1 | How much the text guidance influences colorization (0=no effect, 1=maximum effect) |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| colorized_frames | IMAGE | — |
| performance_report | STRING | — |