diffusion-models

Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"

Official implementation of the NeurIPS 2023 paper "Photoswap: Personalized Subject Swapping in Images"

[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

High-quality Text-to-Audio Generation with Efficient Diffusion Transformer

Official code repository of < CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph >

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

Colab notebook for Stable Diffusion Hyper-SDXL.

Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".

[CVPR 2023] LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

FASHN VTON v1.5: Efficient Maskless Virtual Try-On in Pixel Space

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation

[ICCV 2023] Official PyTorch implementation of the paper "InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion"

[CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation

Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.

Official implementation for "Story2Board: A Training‑Free Approach for Expressive Storyboard Generation"

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

[CVPR 2025] FaithDiff for Classic Film Rejuvenation, Old Photo Revival, Social Media Restoration, Image Enhancement and AIGC Enhancement.

[ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching