ComfyUI Node: ColorMNet Video Colorization (New)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
ColorMNet/Video
Inputs
video_frames IMAGE
reference_image IMAGE
target_width INT
target_height INT
memory_mode
- balanced
- low_memory
- high_quality
feature_encoder
- resnet50
- vgg19
- dinov2_vits
- dinov2_vitb
- dinov2_vitl
- clip_vitb
use_fp16 BOOLEAN
use_torch_compile BOOLEAN
text_guidance STRING
text_guidance_weight FLOAT
Outputs
IMAGE
STRING
Extension: Reference-Based Video Colorization
Dual implementation of reference-based video colorization featuring ColorMNet (2024) with DINOv2 and Deep Exemplar (2019). Includes 4 nodes (2 video, 2 image), multiple feature encoders (VGG19, DINOv2, CLIP), advanced post-processing (color-matcher, WLS, guided, bilateral), and auto-installer for dependencies.
Authored by jonstreeter
Looking for a different node?
More nodes in Reference-Based Video Colorization
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.