Text-to-Image
Diffusers
flux
flux-diffusers
lora
control
controlnet
brightness
grayscale
template:sd-lora
Instructions to use Oysiyl/controlnet-lora-brightness-flux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Oysiyl/controlnet-lora-brightness-flux with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("Oysiyl/controlnet-lora-brightness-flux") pipe = StableDiffusionControlNetPipeline.from_pretrained( "black-forest-labs/FLUX.1-dev", controlnet=controlnet ) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -251,22 +251,22 @@ Visual comparison of different adapter weights (scales) for each checkpoint. Eac
|
|
| 251 |
|
| 252 |
### Checkpoint-312 (25% trained, 2,500 samples)
|
| 253 |
|
| 254 |
-
 to very strong (1.5) control. Early checkpoint shows dense pattern integration with visible QR structure across all scales.
|
| 257 |
|
| 258 |
### Checkpoint-624 (50% trained, 5,000 samples)
|
| 259 |
-

|
| 264 |
-

|
| 269 |
-

|
| 253 |
|
| 254 |
+

|
| 255 |
|
| 256 |
**Scale progression:** From subtle (0.5) to very strong (1.5) control. Early checkpoint shows dense pattern integration with visible QR structure across all scales.
|
| 257 |
|
| 258 |
### Checkpoint-624 (50% trained, 5,000 samples)
|
| 259 |
+

|
| 260 |
|
| 261 |
**Scale progression:** Improved artistic balance at mid-training. Natural garden scenes emerge with adjustable pattern strength.
|
| 262 |
|
| 263 |
### Checkpoint-936 (75% trained, 7,500 samples)
|
| 264 |
+

|
| 265 |
|
| 266 |
**Scale progression:** Refined artistic quality. Excellent detail preservation with smooth scale transitions.
|
| 267 |
|
| 268 |
### Final Model (100% trained, 10,000 samples)
|
| 269 |
+

|
| 270 |
|
| 271 |
**Scale progression:** Best overall quality. Recommended scales: 0.75-1.0 for artistic QR codes, 1.0-1.25 for pattern integration.
|
| 272 |
|