Official repository for LTX-Video
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
LTX-Video Support for ComfyUI
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.
Flash Diffusion — accelerating conditional diffusion models (AAAI 2025 Oral)
OpenMusic: SOTA Text-to-music (TTM) Generation
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions (NeurIPS 2025)
[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation
Dump ntds.dit really fast
[ICLR 2026] Official implementation of JavisDiT and JavisDiT++ series.
MoH: Multi-Head Attention as Mixture-of-Head Attention
🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX
SCoPE: Sightline-Coordinate Positional Encoding for 3D-Aware Video Generation
Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
HyperMotion is a pose guided human image animation framework based on a large-scale video diffusion Transformer.
To associate your repository with the dit topic, visit your repo's landing page and select "manage topics."