https://huggingface.co/SeFi-Image/
The checkpoint is distributed under the Creative Commons Attribution-NonCommercial 4.0 International license (CC BY-NC 4.0). It is for non-commercial use only.
SeFi-Image is intended for research and creative text-to-image generation, including prompt following, bilingual text rendering, style exploration, and model development. The Base checkpoints are suitable starting points for fine-tuning and analysis. Turbo checkpoints are intended for fast generation. The RL checkpoint is intended for stronger alignment-oriented generation.
| Family | Model | Checkpoint | TR | TE | VAE | Steps | Guidance | time (285H) | test v1 | test v2 | test v3 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Base | SeFi-Image-1B-Base | SeFi-Image/SeFi-Image-1B-Base | 1.1 | 2.1 | 0.08 | 50 | 4.0 | 2m 18.09s | SeFi Image 1B Base | SeFi Image 1B Base test v2 | SeFi Image 1B Base test v3 |
|
| Base | SeFi-Image-2B-Base | SeFi-Image/SeFi-Image-2B-Base | 2.1 | 2.1 | 0.08 | 50 | 4.0 | 3m 50.27s | SeFi Image 2B Base |
| ||
| Base | SeFi-Image-5B-Base | SeFi-Image/SeFi-Image-5B-Base | 4.9 | 4.4 | 0.08 | 50 | 4.0 | 8m 5.20s | SeFi Image 5B Base |
| ||
| RL | SeFi-Image-5B-RL | SeFi-Image/SeFi-Image-5B-RL | 4.9 | 4.4 | 0.08 | 50 | 4.0 | 8m 2.03s | SeFi Image 5B RL | SeFi Image 5B RL test v2 | SeFi Image 5B RL test v3 |
|
| Turbo | SeFi-Image-1B-turbo | SeFi-Image/SeFi-Image-1B-turbo | 1.1 | 2.1 | 0.08 | 4 | 1.0 | SeFi Image 1B Turbo | SeFi Image 1B Turbo test v2 | SeFi Image 1B Turbo test v3 |
| |
| Turbo | SeFi-Image-2B-turbo | SeFi-Image/SeFi-Image-2B-turbo | 2.1 | 2.1 | 0.08 | 4 | 1.0 | 10.86s | SeFi Image 2B Turbo |
| ||
| Turbo | SeFi-Image-5B-turbo | SeFi-Image/SeFi-Image-5B-turbo | 4.9 | 4.4 | 0.08 | 4 | 1.0 | SeFi Image 5B Turbo | SeFi Image 5B Turbo test v2 | SeFi Image 5B Turbo test v3 |
|
Total parameters count (Text Encoder + Transformer + VAE)
1B - 3'389'199'651
2B - 4'388'116'771
5B - 9'494'488'099
SDXL 2.5B - 3'468'837'867
Cosmos Predict2 2B 2B - 6'948'089'331
Microsoft Mage Flow 4B 4B - 8'691'613'251
Z Image 6B - 10'261'196'515
LongCat Image 6B - 14'646'655'203
ERNIE Image Turbo 8B - 15'395'632'547
FLUX.2 klein 9B 9B - 17'353'362'723
FLUX.1 Dev 12B - 17'460'278'847
KREA 2 Turbo 12B - 16'870'599'139
Boogu Image 0.1 Turbo 10B - 18'521'169'811
Microsoft Lens 4B - 25'103'028'451
Hunyuan Image 2.1 17B - 26'342'852'611
Ideogram 4 9B - 26'808'357'379
Qwen Image 2512 20B - 28'849'460'275
HiDream I1 Full 17B - 30'800'746'723
FLUX.2 Dev 32B - 56'318'688'547