bconstantine / SketchColourLinks
SketchColour receives colored first frame and entire scene in sketch format, then colors each frame based on the reference. Evaluated on the SAKUGA dataset, SketchColour outperforms previous state-of-the-art video colourization methods across all metrics, despite using only half the training data of competing models.
☆31Updated 6 months ago
Alternatives and similar repositories for SketchColour
Users that are interested in SketchColour are comparing it to the libraries listed below
Sorting:
- Gradio UI for training video models using finetrainers☆33Updated 8 months ago
- ☆17Updated last year
- Video2Video Framework for ComfyUI☆63Updated last year
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 10 months ago
- ComfyUI integration for Unreal Engine 5☆46Updated 3 weeks ago
- ComfyUI implementation of Motion-I2V☆41Updated last year
- Additional non-node based UI for Comfy☆84Updated last week
- This repository is an implementation that recreates the SketchGuidance feature of "ToonCrafter".☆90Updated last year
- HunyuanVideo: A Systematic Framework For Large Video Generation Model☆48Updated last year
- A custom node for ComfyUI that adds cinematic and movie scene styles to video generation prompts. This node helps create more dynamic and…☆46Updated last year
- Official Implementation of "Instance Segmentation of Scene Sketches Using Natural Image Priors" (SIGGRAPH 2025)☆85Updated 3 months ago
- Awesome curated collection of images and prompts generated by z-image-turbo state-of-the-art open-source image generation and editing mod…☆129Updated 2 weeks ago
- ☆43Updated last year
- ☆46Updated last month
- Model code for inferencing T5☆66Updated 9 months ago
- Transform ComfyUI into a Universal AI Vibe Coding Agent — From Code to Productivity Automation☆29Updated 7 months ago
- A system for Prompt generation to improve Text-to-Image performance.☆88Updated last month
- Lets make video diffusion practical!☆52Updated 8 months ago
- An upscaler node for flow-matching models like Qwen, applying the DemoFusion approach☆49Updated this week
- ComfyUI wrapper for Kokoro-onnx☆36Updated 11 months ago
- Wrapper for X-Portrait for running in ComfyUI☆86Updated 8 months ago
- ☆23Updated last year
- ☆38Updated last year
- ToonOut, a fork of BiRefNet focused on background removal for anime images. We open-source our dataset & our weights. See our paper at: h…☆73Updated 3 months ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated last year
- Cosmos1GP for the GPU Poor by DeepBeepMeep☆81Updated 10 months ago
- ☆32Updated last year
- ☆27Updated last year
- Official implementation of DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation☆119Updated 11 months ago
- ☆92Updated last year