Search Results for "identity"

HunyuanCustom is a multimodal video customization framework by Tencent Hunyuan, aimed at generating customized videos featuring particular subjects (people, characters) under flexible conditions, while maintaining subject/identity consistency. It supports conditioning via image, audio, video, and text, and can perform subject replacement in videos, generate avatars speaking given audio, or combine multiple subject images. The architecture builds on HunyuanVideo, with added modules for identity reinforcement and modality-specific condition injection. Text-image fusion module based on LLaVA for improved multimodal understanding. ...

HunyuanVideo-I2V is a customizable image-to-video generation framework from Tencent Hunyuan, built on their HunyuanVideo foundation. It extends video generation so that given a static reference image plus an optional prompt, it generates a video sequence that preserves the reference image’s identity (especially in the first frame) and allows stylized effects via LoRA adapters. The repository includes pretrained weights, inference and sampling scripts, training code for LoRA effects, and support for parallel inference via xDiT. Resolution, video length, stability mode, flow shift, seed, CPU offload etc. Parallel inference support using xDiT for multi-GPU speedups. ...

...It is designed to create minute-level, multi-shot video stories from structured prompts while preserving continuity across scenes. The system uses a paired cross-modal memory bank to maintain visual identity and voice consistency over longer sequences. It also uses a distilled DMD generator to reduce inference cost and improve generation speed compared with heavier multi-step pipelines. JoyAI-Echo focuses on text-to-video and multi-shot long-video generation, while image-to-video support is not part of the current release scope. It is most useful for research and experimental video workflows that need synchronized audio, coherent characters, and editable story-level generation.

HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces, enabling multiple characters to be animated in a scene. Character image injection module for better consistency between training and inference conditioning. ...

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch. They combine pseudo-3d convolutions (axial convolutions) and temporal attention and show much better temporal fusion. The pseudo-3d convolutions isn't a new concept. It has been explored before in other contexts, say for protein contact prediction as "dimensional hybrid residual networks". The gist of the paper comes down to, take a SOTA text-to-image model (here they use DALL-E2, but the same learning...