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 7 months ago
Alternatives and similar repositories for SketchColour
Users that are interested in SketchColour are comparing it to the libraries listed below
Sorting:
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 11 months ago
- ☆13Updated last year
- Gradio UI for training video models using finetrainers☆33Updated 9 months ago
- Official Implementation of "Instance Segmentation of Scene Sketches Using Natural Image Priors" (SIGGRAPH 2025)☆88Updated 4 months ago
- ☆23Updated last year
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (ICCV, 2025)☆52Updated 3 weeks ago
- ☆27Updated last year
- Gradio Demo for ComfyDeploy☆55Updated last year
- ☆46Updated 2 months ago
- FLUX.1-dev LoRA Outfit Generator can create an outfit by detailing the color, pattern, fit, style, material, and type.☆69Updated last year
- Awesome curated collection of images and prompts generated by z-image-turbo state-of-the-art open-source image generation and editing mod…☆171Updated last month
- ☆92Updated 2 years ago
- 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
- Additional non-node based UI for ComfyUI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio☆95Updated this week
- Experimental method to use reference video to drive motion in generations without training in ComfyUI.☆37Updated last year
- Lets make video diffusion practical!☆52Updated 9 months ago
- Video2Video Framework for ComfyUI☆63Updated last year
- Cosmos1GP for the GPU Poor by DeepBeepMeep☆81Updated 11 months ago
- Official implementation of DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation☆119Updated last year
- Official implementation of "Single Image Iterative Subject-driven Generation and Editing".☆101Updated 8 months ago
- ToonOut, a fork of BiRefNet focused on background removal for anime images. We open-source our dataset & our weights. See our paper at: h…☆80Updated 4 months ago
- ☆20Updated 2 years ago
- ☆14Updated last year
- ☆13Updated last year
- ☆17Updated 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
- ComfyUI wrapper for Kokoro-onnx☆37Updated last year
- ☆43Updated last year
- AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation☆38Updated last year