Downloads · 30 days
0
gifsy-depth-encoder
WhyParabola/gifsy-depth-encoder
gifsy-depth-encoder is a depth estimation model from WhyParabola. Use it for the depth estimation task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
The ViT encoder half of Depth Anything V2 Small (fp16 ONNX), used client-side by Gifsy. This file alone does not produce depth maps — it emits intermediate activations only; the DPT head is not included.
Access
Public
Updated Sep 16, 2026
Repo size
44.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx44.3 MB · 100%
At a glance
- Task
- Depth Estimation
- License
- apache-2.0
- Access
- Public
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026
- SHA
- 79d78458
Base models
Model card
From the Hugging Face model README
Gifsy depth encoder
The ViT encoder half of Depth Anything V2 Small (fp16 ONNX), used client-side by Gifsy. This file alone does not produce depth maps — it emits intermediate activations only; the DPT head is not included.
- Task
- Depth Estimation
- License
- apache-2.0
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026