Downloads · 30 days
0
vgt_internvl3_1_6B_sft
hustvl/vgt_internvl3_1_6B_sft
vgt_internvl3_1_6B_sft is a text-to-image model from hustvl. Use it when you need an image from a text prompt. The card lists the license as mit.
Access
Public
Updated Apr 2, 2026
Repo size
5.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth5.5 GB · 100%
At a glance
- Task
- Text-to-Image
- License
- mit
- Access
- Public
- Created
- Nov 21, 2025
- Updated
- Apr 2, 2026
- SHA
- 9c06baa9
Model card
From the Hugging Face model README
VGT: Visual Generation Tuning
Official model card for VGT.
Code, setup, checkpoints, usage, and the latest documentation are maintained in the GitHub repository:
Available Checkpoints
- VGT-InternVL3-1.6B-Pretrain
- VGT-InternVL3-1.6B-SFT
- VGT-Qwen2.5-VL-1.6B-Pretrain
- VGT-Qwen2.5-VL-1.6B-SFT
Paper
License
MIT
- Task
- Text-to-Image
- License
- mit
- Created
- Nov 21, 2025
- Updated
- Apr 2, 2026