Instructions to use raaedk/subliminal_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use raaedk/subliminal_large with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("raaedk/subliminal_large") prompt = "unconditional (blank prompt)" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -60,7 +60,7 @@ You may reuse the base model text encoder for inference.
|
|
| 60 |
## Training settings
|
| 61 |
|
| 62 |
- Training epochs: 2
|
| 63 |
-
- Training steps:
|
| 64 |
- Learning rate: 0.0001
|
| 65 |
- Max grad norm: 0.01
|
| 66 |
- Effective batch size: 1
|
|
@@ -111,7 +111,7 @@ You may reuse the base model text encoder for inference.
|
|
| 111 |
### ps2_subliminal-1024
|
| 112 |
- Repeats: 10
|
| 113 |
- Total number of images: 55
|
| 114 |
-
- Total number of aspect buckets:
|
| 115 |
- Resolution: 1.048576 megapixels
|
| 116 |
- Cropped: False
|
| 117 |
- Crop style: None
|
|
|
|
| 60 |
## Training settings
|
| 61 |
|
| 62 |
- Training epochs: 2
|
| 63 |
+
- Training steps: 6000
|
| 64 |
- Learning rate: 0.0001
|
| 65 |
- Max grad norm: 0.01
|
| 66 |
- Effective batch size: 1
|
|
|
|
| 111 |
### ps2_subliminal-1024
|
| 112 |
- Repeats: 10
|
| 113 |
- Total number of images: 55
|
| 114 |
+
- Total number of aspect buckets: 2
|
| 115 |
- Resolution: 1.048576 megapixels
|
| 116 |
- Cropped: False
|
| 117 |
- Crop style: None
|