Ovis Image Models by Alibaba
1 model2025
Last refreshed 2026-09-09. Next refresh: weekly.
Details
ResearcherAlibaba
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2025
Capabilities
MultimodalAll models
About
Alibaba AIDC-AI's text-to-image model family optimized for high-quality text rendering. Built on a diffusion visual decoder integrated with the Ovis 2.5 multimodal backbone, targeting accurate typography in generated images.
Decision facts
- Best fit
- image generationvision and multimodal workcoding
- Capability starting point
- Ovis Image with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- Qwen-Character
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Ovis ImageCurrent
Use when the workload needs image generation, 7B parameters, and multimodal inputs.
2025-11image generation7B parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Ovis Image | Use when the workload needs image generation, 7B parameters, and multimodal inputs. | 2025-11 | image generation7B parametersmultimodal inputs | Current |
Release Timeline
1 release group2025-11
1 current
Ovis Image
Currentimage generation7B parametersmultimodal inputs
Specifications(1 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| Ovis Image | 2025-11 | 7B | Yes |
