TheAwakenOne commited on
Commit
6328bf1
1 Parent(s): 95e3c69
Files changed (2) hide show
  1. README.md +10 -9
  2. app.py +10 -0
README.md CHANGED
@@ -6,17 +6,18 @@ colorTo: blue
6
  sdk: gradio
7
  sdk_version: 5.3.0
8
  app_file: app.py
9
- pinned: false
10
  ---
11
 
12
  # Flux Image Generator with Zero-GPU
13
 
14
- This Space runs the Flux.1-lite-8B-alpha model from Freepik using Zero-GPU allocation to generate images from text descriptions. The interface allows you to adjust various parameters:
15
 
16
- - Guidance Scale: Controls how closely the image follows the prompt
17
- - Number of Steps: Determines the quality of the generation
18
- - Seed: Controls reproducibility
19
- - Width/Height: Image dimensions
20
-
21
- Note: This Space uses the @spaces.GPU decorator to allocate GPU resources only when needed, making it more efficient and cost-effective.
22
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
6
  sdk: gradio
7
  sdk_version: 5.3.0
8
  app_file: app.py
9
+ pinned: true
10
  ---
11
 
12
  # Flux Image Generator with Zero-GPU
13
 
14
+ This Space demonstrates the Flux.1 Lite model for text-to-image generation.
15
 
16
+ ## Model Citation
17
+ ```bibtex
18
+ @article{flux1-lite,
19
+ title={Flux.1 Lite: Distilling Flux1.dev for Efficient Text-to-Image Generation},
20
+ author={Daniel Verdú, Javier Martín},
21
+ email={dverdu@freepik.com, javier.[email protected]},
22
+ year={2024},
23
+ }
app.py CHANGED
@@ -5,6 +5,16 @@ from huggingface_hub import HfApi
5
  import spaces
6
  import random
7
 
 
 
 
 
 
 
 
 
 
 
8
  @spaces.GPU(duration=70)
9
  def initialize_model():
10
  model_id = "Freepik/flux.1-lite-8B-alpha"
 
5
  import spaces
6
  import random
7
 
8
+ """
9
+ This application uses the Flux.1 Lite model:
10
+ @article{flux1-lite,
11
+ title={Flux.1 Lite: Distilling Flux1.dev for Efficient Text-to-Image Generation},
12
+ author={Daniel Verdú, Javier Martín},
13
14
+ year={2024},
15
+ }
16
+ """
17
+
18
  @spaces.GPU(duration=70)
19
  def initialize_model():
20
  model_id = "Freepik/flux.1-lite-8B-alpha"