Update Readme.md
Browse files
Readme.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
# Flux-ControlNet: Text-to-Image Diffusion Model with Caption Alignment
|
| 2 |
|
| 3 |
-
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
## Key Features
|
|
@@ -18,7 +19,7 @@
|
|
| 18 |
---
|
| 19 |
|
| 20 |
# Training Parameters for Flux-ControlNet
|
| 21 |
-
|
| 22 |
General Parameters:
|
| 23 |
Model Architecture: Flux-based ControlNet Model
|
| 24 |
Image Resolution: 512x512
|
|
@@ -28,5 +29,8 @@ General Parameters:
|
|
| 28 |
Learning Rate: 1e-5 (with cosine schedular)
|
| 29 |
Weight Decay: 0.01
|
| 30 |
Gradient Clipping: 1.0
|
|
|
|
| 31 |
|
|
|
|
|
|
|
| 32 |
|
|
|
|
| 1 |
# Flux-ControlNet: Text-to-Image Diffusion Model with Caption Alignment
|
| 2 |
|
| 3 |
+
This repository hosts **Flux-ControlNet**, a customized ControlNet-based diffusion model designed for generating text-embedded images.
|
| 4 |
+
|
| 5 |
---
|
| 6 |
|
| 7 |
## Key Features
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# Training Parameters for Flux-ControlNet
|
| 22 |
+
```
|
| 23 |
General Parameters:
|
| 24 |
Model Architecture: Flux-based ControlNet Model
|
| 25 |
Image Resolution: 512x512
|
|
|
|
| 29 |
Learning Rate: 1e-5 (with cosine schedular)
|
| 30 |
Weight Decay: 0.01
|
| 31 |
Gradient Clipping: 1.0
|
| 32 |
+
```
|
| 33 |
|
| 34 |
+
# Inference Code
|
| 35 |
+
Soon to be added
|
| 36 |
|