Update README.md
Browse files
README.md
CHANGED
|
@@ -57,7 +57,8 @@ The most notable improvements are observed in landscape generation, which can be
|
|
| 57 |
Future improvements will focus on:
|
| 58 |
- Experimenting with different LoRA configurations and ranks
|
| 59 |
- Fine-tuning hyperparameters for better convergence
|
| 60 |
-
- Improving caption quality and specificity
|
|
|
|
| 61 |
- Extending training duration beyond 1000 steps
|
| 62 |
- Developing custom training scripts for more granular control
|
| 63 |
|
|
@@ -74,8 +75,10 @@ The model was trained on the [WikiArt Impressionism Curated Dataset](https://hug
|
|
| 74 |
## Model Details
|
| 75 |
- Base Model: [FLUX.1](https://huggingface.co/black-forest-labs/FLUX.1-dev)
|
| 76 |
- LoRA Rank: 16
|
| 77 |
-
- Training Steps:
|
| 78 |
-
- Resolution: 512-1024px
|
|
|
|
|
|
|
| 79 |
|
| 80 |
## Usage
|
| 81 |
|
|
|
|
| 57 |
Future improvements will focus on:
|
| 58 |
- Experimenting with different LoRA configurations and ranks
|
| 59 |
- Fine-tuning hyperparameters for better convergence
|
| 60 |
+
- Improving caption quality and specificity(current captions may be too complex that model can not capture spesific features)
|
| 61 |
+
- 'content_or_style' paramater on training config is currently set to 'balanced'. I also want to test 'style' parameter for model training.
|
| 62 |
- Extending training duration beyond 1000 steps
|
| 63 |
- Developing custom training scripts for more granular control
|
| 64 |
|
|
|
|
| 75 |
## Model Details
|
| 76 |
- Base Model: [FLUX.1](https://huggingface.co/black-forest-labs/FLUX.1-dev)
|
| 77 |
- LoRA Rank: 16
|
| 78 |
+
- Training Steps: 1000
|
| 79 |
+
- Resolution: 512-768-1024px
|
| 80 |
+
|
| 81 |
+
You can find detailed training configurations on [config.yaml](config.yaml)
|
| 82 |
|
| 83 |
## Usage
|
| 84 |
|