Model Details
Full Model IDIDEA-Research/Rex-Omni
Pipeline / Taskimage-text-to-text
Librarytransformers
Downloads (all-time)29.2K
Likes58
Last Modified10/16/2025
Author / OrgIDEA-Research
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("image-text-to-text", model="IDEA-Research/Rex-Omni")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
transformerssafetensorsqwen2_5_vlimage-text-to-textvisionobject-detectionmultimodalocrkeypoint-detectionvisual-promptingopen-set-detectionobject-pointingconversationalenarxiv:2510.12798arxiv:2506.04034arxiv:2503.08507arxiv:2411.18363arxiv:2411.14347arxiv:2405.10300arxiv:2311.13596base_model:Qwen/Qwen2.5-VL-3B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-3B-Instructlicense:othertext-generation-inferenceendpoints_compatibleregion:us
More image-text-to-text Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: image-text-to-text
This model is designed for the image-text-to-text task. Explore more models for this use case.
All image-text-to-text Models →📊 Popularity
⬇ Downloads29.2K
❤️ Community Likes58
🛠️ Requirements
- →Install: pip install transformers
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.