fhai50032 commited on
Commit
6461c18
·
verified ·
1 Parent(s): 5863857

Create Readme.md

Browse files
Files changed (1) hide show
  1. Readme.md +32 -0
Readme.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ## Key Features
7
+ - **Flux-ControlNet**: Enhanced ControlNet architecture for better control over text-to-image generation.
8
+ - **Optimized Diffusion**: Uses Hugging Face Diffusers and Accelerate for streamlined performance.
9
+
10
+ ---
11
+
12
+ ## How It Works
13
+ 1. **Input**: Provide text prompts and conditioning image.
14
+ 2. **Processing**:
15
+ - Flux-ControlNet processes the text and applies diffusion to synthesize aligned images.
16
+ 3. **Output**: High-quality, text-embedded images.
17
+
18
+ ---
19
+
20
+ # Training Parameters for Flux-ControlNet
21
+
22
+ General Parameters:
23
+ Model Architecture: Flux-based ControlNet Model
24
+ Image Resolution: 512x512
25
+ Batch Size: 4
26
+ Epochs: 50
27
+ Optimizer: AdamW
28
+ Learning Rate: 1e-5 (with cosine schedular)
29
+ Weight Decay: 0.01
30
+ Gradient Clipping: 1.0
31
+
32
+