Instructions to use davidrd123/Flux-Raphael-LoRA-NoCrops with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use davidrd123/Flux-Raphael-LoRA-NoCrops with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("davidrd123/Flux-Raphael-LoRA-NoCrops") prompt = "unconditional (blank prompt)" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -93,8 +93,8 @@ You may reuse the base model text encoder for inference.
|
|
| 93 |
|
| 94 |
## Training settings
|
| 95 |
|
| 96 |
-
- Training epochs:
|
| 97 |
-
- Training steps:
|
| 98 |
- Learning rate: 0.0001
|
| 99 |
- Learning rate schedule: constant
|
| 100 |
- Warmup steps: 100
|
|
@@ -140,7 +140,7 @@ You may reuse the base model text encoder for inference.
|
|
| 140 |
### raphael-512
|
| 141 |
- Repeats: 11
|
| 142 |
- Total number of images: 28
|
| 143 |
-
- Total number of aspect buckets:
|
| 144 |
- Resolution: 0.262144 megapixels
|
| 145 |
- Cropped: False
|
| 146 |
- Crop style: None
|
|
@@ -149,7 +149,7 @@ You may reuse the base model text encoder for inference.
|
|
| 149 |
### raphael-768
|
| 150 |
- Repeats: 11
|
| 151 |
- Total number of images: 28
|
| 152 |
-
- Total number of aspect buckets:
|
| 153 |
- Resolution: 0.589824 megapixels
|
| 154 |
- Cropped: False
|
| 155 |
- Crop style: None
|
|
|
|
| 93 |
|
| 94 |
## Training settings
|
| 95 |
|
| 96 |
+
- Training epochs: 3
|
| 97 |
+
- Training steps: 1500
|
| 98 |
- Learning rate: 0.0001
|
| 99 |
- Learning rate schedule: constant
|
| 100 |
- Warmup steps: 100
|
|
|
|
| 140 |
### raphael-512
|
| 141 |
- Repeats: 11
|
| 142 |
- Total number of images: 28
|
| 143 |
+
- Total number of aspect buckets: 1
|
| 144 |
- Resolution: 0.262144 megapixels
|
| 145 |
- Cropped: False
|
| 146 |
- Crop style: None
|
|
|
|
| 149 |
### raphael-768
|
| 150 |
- Repeats: 11
|
| 151 |
- Total number of images: 28
|
| 152 |
+
- Total number of aspect buckets: 9
|
| 153 |
- Resolution: 0.589824 megapixels
|
| 154 |
- Cropped: False
|
| 155 |
- Crop style: None
|