Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
---
|
2 |
title: Synthetic Data Gen
|
3 |
emoji: π
|
@@ -8,21 +9,6 @@ sdk_version: 5.9.0
|
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
short_description: Synthetic data generation for training using diffusion model
|
|
|
11 |
|
12 |
-
|
13 |
-
Features
|
14 |
-
|
15 |
-
Stable Diffusion Integration: Leverages the StableDiffusionImg2ImgPipeline for versatile image generation.
|
16 |
-
|
17 |
-
Class Misclassification Analysis: Automatically identifies misclassified class pairs for focused image generation.
|
18 |
-
|
19 |
-
Advanced Prompt Interpolation: Utilizes spherical linear interpolation (slerp) to generate smooth transitions between text embeddings for more natural image outputs.
|
20 |
-
|
21 |
-
Structural Similarity Scoring: Calculates SSIM scores to measure the quality of generated images compared to input references.
|
22 |
-
|
23 |
-
Comprehensive Metadata Management: Captures extensive details about the generation process for easy reproducibility and debugging.
|
24 |
-
|
25 |
-
Dynamic Directory Management: Automatically creates and organizes directories for class pairs and metadata files.
|
26 |
-
|
27 |
-
Highly Configurable: Supports advanced optimization options like torch.compile and DeepCache for performance improvements.
|
28 |
-
"""
|
|
|
1 |
+
|
2 |
---
|
3 |
title: Synthetic Data Gen
|
4 |
emoji: π
|
|
|
9 |
app_file: app.py
|
10 |
pinned: false
|
11 |
short_description: Synthetic data generation for training using diffusion model
|
12 |
+
---
|
13 |
|
14 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|