Ovis-Image: Vision-Language Image Generation Model

Ovis-Image is AIDC-AI's vision-language image generation model, featuring a diffusion model with Ovis 2.5 text encoder.

O

Ovis-Image

Image GenerationVision-LanguageDiffusionOpen Source

Vision-language image generation model by AIDC-AI, packaged by Comfy-Org. Includes the Ovis image diffusion model (BF16) and Ovis 2.5 text encoder for visual-language-conditioned image generation.

Comfy-Org HFHF Org
DeveloperAIDC-AI
Release Date2025-07
ArchitectureDiffusion Model + Vision-Language Text Encoder
LicenseApache-2.0
Componentsovis_image_bf16 (diffusion), ovis_2.5 (text encoder)
PrecisionBF16
CapabilitiesText-to-image generation with visual-language understanding

Guides and workflows related to this model series.

No articles found.