[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!

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors (ECCV2024)

Official inference repo for FLUX.1 models

[ECCV 2024] HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance

[NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolation

Image comparison slider. Compare images before and after. Supports React, Vue, Angular.

EXPERIMENT - exploring ideas to improve dx for models

Stable Diffusion WebUI in Docker

APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)