zhao68733

Kandinsky AI

Open-source multimodal tool: text/image/video generation & inpainting.

Kandinsky AI is an open-source multimodal tool supporting text-to-image, image-to-image and video generation, with inpa…

OmniHuman‑1.5

OmniHuman-1.5 is an AI model that generates film-grade videos from a single image, audio, and optional text prompts. It supports multi-character scenes, emotional expression, free camera control, and

OmniHuman-1.5 is an advanced AI model that creates film-grade digital human videos from just a single image, audio clip…

Humo AI

Multi-modal input, human-centric video with consistent subject & audio-visual sync

HuMo AI is a human-centric video generation tool co-developed by Tsinghua University and Bytedance. It supports multi-m…

Humo AI

Multi-modal input, human-centric video with consistent subject & audio-visual sync

Supports multi-modal input (text/image/audio) with three modes (TI/TA/TIA), enabling human-centric videos with consiste…

Seedream 4.5

Seedream 4.5, powered by full-model scaling, excels at subject locking, detail preservation and dense text rendering for consistent, high-fidelity visuals.

Seedream 4.5 achieves all-round upgrades through full-model scaling. It excels at stably locking main subjects in multi…