Update README.md
Browse files
README.md
CHANGED
|
@@ -25,11 +25,13 @@ widget:
|
|
| 25 |
url: images/thailand.png
|
| 26 |
---
|
| 27 |
|
| 28 |
-
|
|
|
|
|
|
|
| 29 |
|
| 30 |
rank 32, trained for 3500 steps on over 200 labeled locations. trigger word ("geoguessr") not always necessary, just name a location
|
| 31 |
|
| 32 |
-
run this with diffusers
|
| 33 |
|
| 34 |
```py
|
| 35 |
import torch
|
|
@@ -71,9 +73,7 @@ display(Image(filename=filename))
|
|
| 71 |
|
| 72 |
```
|
| 73 |
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
known model biases:
|
| 77 |
- v1 of this model leans heavily towards rural locations due to dataset bias, will be fixed in v2 as i collect more data
|
| 78 |
- it managed to generalize to locations not available on geoguessr, like china, although it drifts towards generic locations
|
| 79 |
- its trained on lowercase country names, and flux is case sensitive. results may vary
|
|
|
|
| 25 |
url: images/thailand.png
|
| 26 |
---
|
| 27 |
|
| 28 |
+
# fake geoguessr locations lora for flux-dev
|
| 29 |
+
|
| 30 |
+
https://x.com/_lyraaaa_/status/1841762752404369745
|
| 31 |
|
| 32 |
rank 32, trained for 3500 steps on over 200 labeled locations. trigger word ("geoguessr") not always necessary, just name a location
|
| 33 |
|
| 34 |
+
**run this with diffusers:**
|
| 35 |
|
| 36 |
```py
|
| 37 |
import torch
|
|
|
|
| 73 |
|
| 74 |
```
|
| 75 |
|
| 76 |
+
**known model biases:**
|
|
|
|
|
|
|
| 77 |
- v1 of this model leans heavily towards rural locations due to dataset bias, will be fixed in v2 as i collect more data
|
| 78 |
- it managed to generalize to locations not available on geoguessr, like china, although it drifts towards generic locations
|
| 79 |
- its trained on lowercase country names, and flux is case sensitive. results may vary
|