Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
KangLiao
/
Puffin
like
24
Text-to-3D
unified multimodal model
camera-centric
generation
understanding
spatial intelligence
3D vision
arxiv:
2510.08673
License:
other
Model card
Files
Files and versions
xet
Community
1
74d2911
Puffin
/
sample_507991
3.6 MB
Ctrl+K
Ctrl+K
2 contributors
History:
1 commit
KangLiao
Upload folder using huggingface_hub
ff40883
verified
3 months ago
00_input_gt.png
247 kB
xet
Upload folder using huggingface_hub
3 months ago
01_target_gt.png
239 kB
xet
Upload folder using huggingface_hub
3 months ago
02_target_gt.png
237 kB
xet
Upload folder using huggingface_hub
3 months ago
03_novel_view_gen.png
313 kB
xet
Upload folder using huggingface_hub
3 months ago
03_target_gt.png
237 kB
xet
Upload folder using huggingface_hub
3 months ago
04_novel_view_gen.png
319 kB
xet
Upload folder using huggingface_hub
3 months ago
04_target_gt.png
230 kB
xet
Upload folder using huggingface_hub
3 months ago
05_novel_view_gen.png
309 kB
xet
Upload folder using huggingface_hub
3 months ago
05_target_gt.png
247 kB
xet
Upload folder using huggingface_hub
3 months ago
06_novel_view_gen.png
307 kB
xet
Upload folder using huggingface_hub
3 months ago
06_target_gt.png
239 kB
xet
Upload folder using huggingface_hub
3 months ago
07_novel_view_gen.png
312 kB
xet
Upload folder using huggingface_hub
3 months ago
07_target_gt.png
237 kB
xet
Upload folder using huggingface_hub
3 months ago
camera_trajectory.png
126 kB
xet
Upload folder using huggingface_hub
3 months ago
