Update README.md
Browse files
README.md
CHANGED
|
@@ -36,16 +36,22 @@ widget:
|
|
| 36 |
|
| 37 |
A LoRA model to generate panoramas using Flux dev.
|
| 38 |
|
| 39 |
-
It usually work fine for "normal" requests, but might have trouble creating the spherical distortion if you ask for uncommon content, locations or angles.
|
| 40 |
-
|
| 41 |
## Which image ratio to use?
|
| 42 |
|
| 43 |
-
This model has been trained on images with a 2:1 (2048x1024).
|
|
|
|
|
|
|
| 44 |
|
| 45 |
However panorama viewers are pretty flexible when it comes to resolution, and FLUX.1 seems to generalize well.
|
| 46 |
|
| 47 |
For instance the gallery samples have been generated in 1536 × 640 (~21:9), since this is reasonably fast (16 sec on the HF Inference API).
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
## Non-commercial use
|
| 50 |
|
| 51 |
As the base model is FLUX.1-[dev] and since the data comes from Google Street View, it should be used for [non-commercial, personal or demonstration purposes only](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).
|
|
|
|
| 36 |
|
| 37 |
A LoRA model to generate panoramas using Flux dev.
|
| 38 |
|
|
|
|
|
|
|
| 39 |
## Which image ratio to use?
|
| 40 |
|
| 41 |
+
This model has been trained on images with a 2:1 ratio (2048x1024).
|
| 42 |
+
|
| 43 |
+
So you might get good results is you use this for width and height.
|
| 44 |
|
| 45 |
However panorama viewers are pretty flexible when it comes to resolution, and FLUX.1 seems to generalize well.
|
| 46 |
|
| 47 |
For instance the gallery samples have been generated in 1536 × 640 (~21:9), since this is reasonably fast (16 sec on the HF Inference API).
|
| 48 |
|
| 49 |
+
## It doesn't work for case X or Y
|
| 50 |
+
|
| 51 |
+
It usually work fine for "normal" requests, but the model might have trouble creating the spherical distortion if you ask for uncommon content, locations or angles.
|
| 52 |
+
|
| 53 |
+
If you give me some examples, maybe I can try to find more data to better cover uncommon panoramas.
|
| 54 |
+
|
| 55 |
## Non-commercial use
|
| 56 |
|
| 57 |
As the base model is FLUX.1-[dev] and since the data comes from Google Street View, it should be used for [non-commercial, personal or demonstration purposes only](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).
|