Any-to-Any - a wo-datacraft Collection

wo-datacraft 's Collections

Audio Generation

Image Classification

Image Generation

Speech Generation

Speech Recognition

Text Generation - General

Text Generation - Reasoning

Text Generation - Vision

Toolkit - AI Papers

Toolkit - Datasets

Toolkit - Embeddings

Toolkit - Prompting Papers

Toolkit - Segmentation

Toolkit - Utilities

Video Generation

Any-to-Any

updated 27 days ago

OmniGen2/OmniGen2

Any-to-Any • Updated Sep 27, 2025 • 5.94k • 426
Qwen/Qwen3-Omni-30B-A3B-Captioner

Any-to-Any • 32B • Updated Sep 22, 2025 • 16.4k • 197
Qwen/Qwen3-Omni-30B-A3B-Instruct

Any-to-Any • 35B • Updated Sep 22, 2025 • 700k • 847
Qwen/Qwen3-Omni-30B-A3B-Thinking

Any-to-Any • 32B • Updated Sep 22, 2025 • 17.5k • 272
Running on Zero

Featured

427

OmniGen2

👀

427

OmniGen2: Unified Image Understanding and Generation.
Running

56

Qwen3 Omni Captioner Demo

🐠

56

Generate captions from audio
Running

Featured

249

Qwen3 Omni Demo

⚡

249

Chat with AI via text, voice, image or video; get spoken replies