Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,30 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model:
|
4 |
+
- black-forest-labs/FLUX.1-Kontext-dev
|
5 |
+
pipeline_tag: image-to-image
|
6 |
+
---
|
7 |
+
|
8 |
+
# Depth Reference Fusion LoRA
|
9 |
+
|
10 |
+
## 📝 Short description (preview)
|
11 |
+
A LoRA for **Flux Kontext Dev** that fuses a **reference image (left)** with a **depth map (right)**.
|
12 |
+
It preserves **identity and style** from the reference while following the pose and structure from the depth map.
|
13 |
+
|
14 |
+
**Trigger word:** `redepthkontext`
|
15 |
+
|
16 |
+
---
|
17 |
+
|
18 |
+
## 📖 Extended description
|
19 |
+
This LoRA was primarily trained on **humans**, but it also works with **objects**.
|
20 |
+
Its main purpose is to **preserve identity** — facial features, clothing, or object characteristics — from the reference image, while adapting them to the pose and composition defined by the depth map.
|
21 |
+
|
22 |
+
---
|
23 |
+
|
24 |
+
## ⚙️ How to use
|
25 |
+
- Concatenate two images side by side:
|
26 |
+
- **Left:** reference image (person or object)
|
27 |
+
- **Right:** depth map (grayscale or silhouette)
|
28 |
+
- Add the trigger word **`redepthkontext`** in your prompt.
|
29 |
+
|
30 |
+
### ✅ Example prompt
|