Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A generative world for general-purpose robotics & embodied AI learning.

OneTrainer is a one-stop solution for all your stable diffusion training needs.

[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

AITuberKit is chat application with AI character.

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

for tile the image for advanced control or modification

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

A custom node set for Video Frame Interpolation in ComfyUI.

Code release for Best-of-N Jailbreaking

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Retro Games in Gym

Cross-platform, sophisticated frontend for the libretro API. Licensed GPLv3.

Reinforcement Learning for Elden Ring on Windows11

Faster Whisper transcription with CTranslate2

An up-to-date list of danbooru tags for use with image gen models (SwarmUI/tag-complete format)

Divide and Conquer Node Suite

Memory-optimized training scripts for video models based on Diffusers

Code for FreeScale, a tuning-free method for higher-resolution visual generation

Star Citizen's Linux Users Group Helper Script

Framework for estimating temporal properties of music tracks.