10BC0 Fantasy AIGC Family · GitHub
[go: up one dir, main page]

Skip to content
@Fantasy-AMAP

Fantasy AIGC Family

Fantasy AIGC Family, AMAP, Alibaba Group

Fantasy AIGC Family

Fantasy AIGC Family is an open-source initiative exploring Human-centric AI, World Modeling, and Human-World Interaction, aiming to bridge perception, understanding, and generation in the real and digital worlds.

🔥🔥🔥 News!!

  • 🎉 Nov, 2025: FantasyTalking2 and FantasyHSI are accepted by AAAI 2026.
  • 👋 Aug, 2025: We release the inference code and model weights of FantasyPortrait.
  • 🎉 Jul, 2025: FantasyTalking is accepted by ACM MM 2025.
  • 👋 Apr, 2025: We release the inference code and model weights of FantasyTalking, FantasyID.

✨✨✨ Members

FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

Project Conference arXiv GitHub GitHub Stars HuggingFace Model HuggingFace Space ModelScope

The first Wan-based high-fidelity audio-driven avatar system that synchronizes facial expressions, lip motion, and body gestures in dynamic scenes through dual-stage audio-visual alignment and controllable motion modulation.

🗣️ FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

Project Conference arXiv GitHub

A novel Timestep-Layer Adaptive Multi-Expert Preference Optimization (TLPO) method enhances the quality of audio-driven avatar in three dimensions: lip-sync, motion naturalness, and visual quality.

🗿 FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework

Project Conference arXiv GitHub

A graph-based multi-agent framework that grounds video generation within 3D world dynamics, enabling digital humans to perceive, plan, and act autonomously, thus serving as the technical bridge that links human modeling to world modeling through unified perception–action reasoning.

🤡 FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers

Project arXiv GitHub GitHub Stars

A novel expression-driven video-generation method that pairs emotion-enhanced learning with masked cross-attention, enabling the creation of high-quality, richly expressive animations for both single and multi-portrait scenarios.

🌏 FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction

Project arXiv GitHub

A unified world model integrating video priors and geometric grounding for synthesizing explorable and geometrically consistent 3D scenes.

🆔 FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation

Project arXiv GitHub GitHub Stars HuggingFace Model ModelScope

A tuning-free text-to-video model that leverages 3D facial priors, multi-view augmentation, and layer-aware guidance injection to deliver dynamic, identity-preserving video generation.

🌟🌟🌟 Our wishes.

  1. Giving Back to the Community: In our daily work, we benefit immensely from the resources, expertise, and support of the open source community, and we aim to give back by making our own projects open source.
  2. Attracting More Contributors: By open sourcing our code, we invite developers worldwide to collaborate—making our models smarter, our engineering more robust, and extending benefits to even more users.
  3. Building an Open Ecosystem: We believe that open source brings together diverse expertise to create a collaborative innovation platform—driving technological progress, industry growth, and broader societal impact.

Pinned Loading

  1. fantasy-talking fantasy-talking Public

    [ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

    Python 1.6k 125

  2. fantasy-portrait fantasy-portrait Public

    FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers

    Python 491 34

  3. fantasy-talking2 fantasy-talking2 Public

    [AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

    62 2

  4. fantasy-hsi fantasy-hsi Public

    [AAAI 2026] FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework

    11 3

Repositories

Showing 7 of 7 repositories

Top languages

Loading…

Most used topics

Loading…

0