Create a Model Card
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# Lora Photorealism for Flux
|
| 6 |
+
|
| 7 |
+
This repository provides a checkpoint with trained LoRA photorealism for
|
| 8 |
+
[FLUX.1-dev model](https://huggingface.co/black-forest-labs/FLUX.1-dev) by Black Forest Labs
|
| 9 |
+
|
| 10 |
+
# Training details
|
| 11 |
+
[XLabs AI](https://github.com/XLabs-AI) team is happy to publish fune-tuning Flux scripts, including:
|
| 12 |
+
|
| 13 |
+
- **LoRA** π₯
|
| 14 |
+
- **ControlNet** π₯
|
| 15 |
+
|
| 16 |
+
[See our github](https://github.com/XLabs-AI/x-flux) for train script and train configs.
|
| 17 |
+
|
| 18 |
+
# Training Dataset
|
| 19 |
+
Dataset has the following format for the training process:
|
| 20 |
+
|
| 21 |
+
```
|
| 22 |
+
βββ images/
|
| 23 |
+
β βββ 1.png
|
| 24 |
+
β βββ 1.json
|
| 25 |
+
β βββ 2.png
|
| 26 |
+
β βββ 2.json
|
| 27 |
+
β βββ ...
|
| 28 |
+
```
|
| 29 |
+
A .json file contains "caption" field with a text prompt.
|
| 30 |
+
|
| 31 |
+
# License
|
| 32 |
+
|
| 33 |
+
lora.safetensors falls under the [FLUX.1 [dev]](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) Non-Commercial License<br/>
|
| 34 |
+
lora.bin falls under the [FLUX.1 [dev]](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) Non-Commercial License
|