Downloads · 30 days
10
6% of all-time downloads
gpt-image-edit-finetune-t5-only
UCSC-VLAA/gpt-image-edit-finetune-t5-only
gpt-image-edit-finetune-t5-only is a image-to-image model from UCSC-VLAA. Use it when you need one image transformed into another. It is set up for transformers. The card lists the license as apache-2.0.
- Original Text encoders: T5 & CLIP text encoder (checkpoint bundle still includes Qwen-VL weights from codebase UniWorld-V1, but inference uses only T5 + CLIP text encoder)
All-time downloads
181
Public
Parameters
20.4B
40.9 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors40.7 GB · 100%
At a glance
- Task
- Image-to-Image
- Library
- transformers
- License
- apache-2.0
- Model type
- univa_qwen2p5vl
- Access
- Public
- Created
- Jul 31, 2025
- Updated
- Jul 31, 2025
- SHA
- 9eac1886
Model card
From the Hugging Face model README
GPT-Image-Edit-T5-only: Fine-Tuned on GPT-Image-Edit-1.5M
- Original Text encoders: T5 & CLIP text encoder
(checkpoint bundle still includes Qwen-VL weights from codebase UniWorld-V1, but inference uses only T5 + CLIP text encoder)
- Task
- Image-to-Image
- Library
- transformers
- Type
- univa_qwen2p5vl
- License
- apache-2.0
- Created
- Jul 31, 2025
- Updated
- Jul 31, 2025