multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
bf77163 verified
|
Raw History Blame
963 Bytes
---
title: Krea-2 Depth ControlNet
emoji: 🏔️
colorFrom: gray
colorTo: yellow
sdk: gradio
sdk_version: 6.19.0
app_file: app.py
short_description: Depth-controlled image generation with Krea-2 Turbo
python_version: "3.12"
startup_duration_timeout: 1h
---
# Krea-2 Depth ControlNet-LoRA
Depth-conditioned image generation for [Krea-2](https://huggingface.co/krea/Krea-2-Turbo).
Give it any image and a prompt — it extracts the depth map with
**Depth-Anything-V2** and generates a new image with the **same 3D structure and
composition**, but whatever content and style you ask for.
- Base: [krea/Krea-2-Turbo](https://huggingface.co/krea/Krea-2-Turbo) (8-step)
- Control: [Patil/Krea-2-depth-controlnet](https://huggingface.co/Patil/Krea-2-depth-controlnet)
(rank-64 LoRA + expanded input projection)
- Depth: `depth-anything/Depth-Anything-V2-Large-hf`
Model weights are subject to the
[Krea 2 community license](https://www.krea.ai/krea-2-licensing).