Leffa:高保真模特虚拟试穿与人物姿势调整,Meta开源的可控人物图像生成模型

Leffa: High-fidelity model virtual fitting and character pose adjustment, Meta open source controllable character image generation model

Comprehensive Introduction Leffa is a unified framework for generating controllable character images, enabling precise manipulation of character appearance (e.g., virtual fitting) and pose (e.g., pose transfer). The framework significantly reduces distortion of fine-grained details by directing the target query to focus on the correct reference key in the attention layer, with ...
6mos ago
01.5K
MMAudio:为视频画面生成同步音效与配乐,视频到音频的多模态联合训练工具

MMAudio: generating synchronized sound effects and soundtracks for video footage, video-to-audio multimodal co-training tool

General Introduction MMAudio is an open-source project aiming to generate high-quality synchronized audio through joint multimodal training. Developed by Ho Kei Cheng et al. at the Chinese University of Hong Kong, the project's main function is to generate synchronized audio based on video and/or text input.MM...
6mos ago
01.5K