Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,9 @@ language:
|
|
| 16 |
pipeline_tag: image-to-image
|
| 17 |
library_name: diffusers
|
| 18 |
---
|
|
|
|
|
|
|
|
|
|
| 19 |
# **Kontext-Top-Down-View**
|
| 20 |
|
| 21 |
The Kontext-Top-Down-View is an adapter for black-forest-lab's FLUX.1-Kontext-dev, designed to transform scenes into a top-down perspective while maintaining accurate visual proportions, consistent lighting, and realistic spatial relationships. The model ensures that backgrounds, textures, and environmental details remain natural and contextually coherent, producing high-quality, perspective-accurate visual outputs. It was trained on 800 image pairs (400 start images and 400 end images) to achieve precise, geometry-consistent top-down scene generation.
|
|
@@ -23,9 +26,39 @@ The Kontext-Top-Down-View is an adapter for black-forest-lab's FLUX.1-Kontext-de
|
|
| 23 |
> [!note]
|
| 24 |
[photo content], recreate the scene from a top-down perspective. Maintain all visual proportions, lighting consistency, and realistic spatial relationships. Ensure the background, textures, and environmental shadows remain naturally aligned from this elevated angle.
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
---
|
| 28 |
|
|
|
|
| 29 |
## Parameter Settings
|
| 30 |
|
| 31 |
| Setting | Value |
|
|
|
|
| 16 |
pipeline_tag: image-to-image
|
| 17 |
library_name: diffusers
|
| 18 |
---
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
# **Kontext-Top-Down-View**
|
| 23 |
|
| 24 |
The Kontext-Top-Down-View is an adapter for black-forest-lab's FLUX.1-Kontext-dev, designed to transform scenes into a top-down perspective while maintaining accurate visual proportions, consistent lighting, and realistic spatial relationships. The model ensures that backgrounds, textures, and environmental details remain natural and contextually coherent, producing high-quality, perspective-accurate visual outputs. It was trained on 800 image pairs (400 start images and 400 end images) to achieve precise, geometry-consistent top-down scene generation.
|
|
|
|
| 26 |
> [!note]
|
| 27 |
[photo content], recreate the scene from a top-down perspective. Maintain all visual proportions, lighting consistency, and realistic spatial relationships. Ensure the background, textures, and environmental shadows remain naturally aligned from this elevated angle.
|
| 28 |
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
## **Sample Inferences : Demo**
|
| 32 |
+
|
| 33 |
+
<table style="width:100%; border-collapse:collapse;">
|
| 34 |
+
<tr>
|
| 35 |
+
<td style="width:50%; text-align:center;">
|
| 36 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/O9hti3lQODGSiZLGPm811.jpeg"
|
| 37 |
+
alt="Kontext-Unblur-Upscale" style="width:100%; height:auto;"/>
|
| 38 |
+
</td>
|
| 39 |
+
<td style="width:50%; text-align:center;">
|
| 40 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/iH52aQZ7BA6Gdnmj2rkgX.webp"
|
| 41 |
+
alt="Kontext-Top-Down-View" style="width:100%; height:auto;"/>
|
| 42 |
+
</td>
|
| 43 |
+
</tr>
|
| 44 |
+
</table>
|
| 45 |
+
|
| 46 |
+
<table style="width:100%; border-collapse:collapse;">
|
| 47 |
+
<tr>
|
| 48 |
+
<td style="width:50%; text-align:center;">
|
| 49 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/N_nMU9x0hnb4HAdchJtQC.jpeg"
|
| 50 |
+
alt="Kontext-Unblur-Upscale" style="width:100%; height:auto;"/>
|
| 51 |
+
</td>
|
| 52 |
+
<td style="width:50%; text-align:center;">
|
| 53 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/r_hw2cwckPCfapUZyHe9c.webp"
|
| 54 |
+
alt="Kontext-Top-Down-View" style="width:100%; height:auto;"/>
|
| 55 |
+
</td>
|
| 56 |
+
</tr>
|
| 57 |
+
</table>
|
| 58 |
|
| 59 |
---
|
| 60 |
|
| 61 |
+
|
| 62 |
## Parameter Settings
|
| 63 |
|
| 64 |
| Setting | Value |
|