Downloads · 30 days
0
merge-large-depth-v1
hongk1998/merge-large-depth-v1
merge-large-depth-v1 is a depth estimation model from hongk1998. Use it for the depth estimation task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as apache-2.0.
<div align="center" <h1More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models</h1
Access
Public
Updated Nov 3, 2025
Repo size
3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3 GB · 100%
At a glance
- Task
- Depth Estimation
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Oct 22, 2025
- Updated
- Nov 3, 2025
- SHA
- 01ad6e89
Model card
From the Hugging Face model README
<div align="center">
<h1>More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models</h1>
<a href="https://https://github.com/HongkLin/" target="_blank" rel="noopener noreferrer">Hongkai Lin</a>, <a href="https://dk-liang.github.io/" target="_blank" rel="noopener noreferrer">Dingkang Liang</a>, Mingyang Du, <a href="https://lmd0311.github.io/" target="_blank" rel="noopener noreferrer">Xin Zhou</a>, <a href="https://scholar.google.com/citations?user=UeltiQ4AAAAJ&hl=en" target="_blank" rel="noopener noreferrer">Xiang Bai</a><sup>†</sup>
Huazhong University of Science & Technology
(†) Corresponding author.
We present MERGE, a simple unified diffusion model for image generation and depth estimation. Its core lies in leveraging streamlined converters and rich visual prior stored in generative image models. Our model, derived from fixed generative image models and fine-tuned pluggable converters with synthetic data, expands powerful zero-shot depth estimation capability.
Usage
Please refer to this page.
- Task
- Depth Estimation
- Library
- diffusers
- License
- apache-2.0
- Created
- Oct 22, 2025
- Updated
- Nov 3, 2025