LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Python

cog-ByteDance-Phantom-HuMo

🎭Cogified HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning🗣️

PythonEmergingai-videoaudio-to-videobytedancecog

Stars

1

Forks

1

Contributors

1

Last push

9mo ago

Recent commits

Latest commits.

Update codebase with latest HuMo changes
075c16ezsxkib9mo ago
fix: remove build artifacts and symlink
1fb7c03zsxkib9mo ago
r8 init
54fa776zsxkib9mo ago
fix: map frontend modes to backend TA/TIA; auto-create silent audio for TA/TIA; toggle extract_audio_feat; ensure test_case aligns with backend mode
c400f46zsxkib9mo ago
fix: guard OmegaConf eval resolver registration to avoid double-registration in Cog runtime
78e67bczsxkib9mo ago

fix: use humo.common.config.load_config so __inherit__ is resolved before model creation

a9f364ezsxkib9mo ago

fix(config): instantiate WanModel with args=as_params and model_type=t2v to satisfy constructor and avoid assertion

10ba30czsxkib9mo ago

fix(config): default to text-only mode (T) and disable audio feature extraction; set model_type=t2v for WanModel

e2baedbzsxkib9mo ago

Top contributors

Builders behind this project.