svjack's repositories

1Prompt1Story

(ICLR 2025) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

CartoonSegmentation

Instance segmentation for cartoon/anime characters and some visual techniques building around it.

Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0

DiffusionAsShader

[arXiv 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

FastVideo

FastVideo is a lightweight framework for accelerating large video diffusion models.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

HunyuanVideo-I2V

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0

HunyuanVideoGP

HunyuanVideo GP: Large Video Generation Model - GPU Poor version

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

joycaption

JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

leapfusion-hunyuan-image2video

A novel approach to hunyuan image-to-video sampling

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

Light-A-Video

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Language:PythonStargazers:0Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

LTX-Video

Official repository for LTX-Video

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

magi

Generate a transcript for your favourite Manga: Detect manga characters, text blocks and panels. Order panels. Cluster characters. Match texts to their speakers. Perform OCR.

Stargazers:0Issues:0Issues:0

midi-model

Midi event transformer for symbolic music generation

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

MotionClone

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Language:PythonStargazers:0Issues:0Issues:0
Language:PythonLicense:BSD-2-ClauseStargazers:0Issues:0Issues:0

musiclang_predict

AI Prediction api of the MusicLang package

Language:PythonLicense:GPL-3.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:0Issues:0

Show-o

[ICLR 2025] Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

SkyReels-V1

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

star-vector

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Stargazers:0Issues:1Issues:0

VideoModelStudio

Gradio webapp to train AI Video models using Finetrainers

Language:PythonStargazers:0Issues:0Issues:0

Wan2GP

Wan 2.1 for the GPU Poor

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

YuE

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Language:PythonStargazers:0Issues:0Issues:0