Our next-generation MLLMs for native-resolution vision and advanced reasoning
AI & ML interests
None defined yet.
Recent Activity
Organization Card
Welcome to AIDC-AI 🌍
AIDC-AI is the AI team at Alibaba International Digital Commerce Group. Here, we will open-source our research in the fields of language models, vision models, and multimodal models.
spaces
14
Running
on
Zero
102
Ovis2.5 2B
📚
Lightweight vision for efficient deployment
Running
on
Zero
150
Ovis2.5 9B
📊
High-accuracy vision & reasoning for complex tasks
Running
on
Zero
6
Ovis2 34B GPTQ Int4
📚
Stays powerful, with much lighter VRAM usage
Running
on
Zero
165
Ovis U1 3B
🎨
Demo for multimodal understanding and generation
Running
on
Zero
6
CHATS
🚀
The demo for CHATS-SDXL text-to-image generation model
Running
on
Zero
124
Ovis2 16B
🦫
See, read, and reason—better together.
models
39
AIDC-AI/Ovis2.5-2B
Image-Text-to-Text
•
3B
•
Updated
•
4.64k
•
167
AIDC-AI/Ovis2.5-9B
Image-Text-to-Text
•
9B
•
Updated
•
1.39k
•
240
AIDC-AI/CHATS-SD1d5
Text-to-Image
•
Updated
•
33
•
2
AIDC-AI/Ovis2-1B
Image-Text-to-Text
•
1B
•
Updated
•
485k
•
92
AIDC-AI/Ovis2-2B
Image-Text-to-Text
•
2B
•
Updated
•
17.4k
•
59
AIDC-AI/Ovis2-4B
Image-Text-to-Text
•
5B
•
Updated
•
1.28M
•
61
AIDC-AI/Ovis2-16B
Image-Text-to-Text
•
16B
•
Updated
•
109k
•
100
AIDC-AI/Ovis2-34B
Image-Text-to-Text
•
35B
•
Updated
•
9.1k
•
150
AIDC-AI/Ovis2-8B
Image-Text-to-Text
•
9B
•
Updated
•
117k
•
73
AIDC-AI/Ovis1.6-Gemma2-9B
Image-Text-to-Text
•
10B
•
Updated
•
18.1k
•
276