Updated requirements, README, and app code

README.md

@@ -1,14 +1,22 @@
 ---
-title: Flux1 Lite 8B Alpha
-emoji: 🖼
-colorFrom: purple
-colorTo: red
+title: Flux Image Generator (Zero-GPU)
+emoji: 🎨
+colorFrom: red
+colorTo: blue
 sdk: gradio
-sdk_version: 5.0.1
+sdk_version: 4.7.1
 app_file: app.py
 pinned: false
-license: other
-short_description: 8B parameter transformer model distilled by Freepik
 ---
 
+# Flux Image Generator with Zero-GPU
+
+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:
+
+- Guidance Scale: Controls how closely the image follows the prompt
+- Number of Steps: Determines the quality of the generation
+- Seed: Controls reproducibility
+- Width/Height: Image dimensions
+
+Note: This Space uses the @spaces.GPU decorator to allocate GPU resources only when needed, making it more efficient and cost-effective.
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,154 +1,62 @@
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
+from diffusers import FluxPipeline
+from huggingface_hub import HfApi
+import spaces
+
+@spaces.GPU(duration=70)  # Allocate GPU for 70 seconds
+def initialize_model():
+    model_id = "Freepik/flux.1-lite-8B-alpha"
+    pipe = FluxPipeline.from_pretrained(
+        model_id,
+        torch_dtype=torch.bfloat16
+    ).to("cuda")
+    return pipe
+
+@spaces.GPU(duration=70)
+def generate_image(
     prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
+    guidance_scale=3.5,
+    num_steps=28,
+    seed=11,
+    width=1024,
+    height=1024
 ):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
-
+    # Initialize model within the GPU context
+    pipe = initialize_model()
+    
+    with torch.inference_mode():
+        image = pipe(
+            prompt=prompt,
+            generator=torch.Generator(device="cuda").manual_seed(seed),
+            num_inference_steps=num_steps,
+            guidance_scale=guidance_scale,
+            height=height,
+            width=width,
+        ).images[0]
+    
+    return image
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=generate_image,
+    inputs=[
+        gr.Textbox(label="Prompt", placeholder="Enter your image description here..."),
+        gr.Slider(minimum=1, maximum=20, value=3.5, label="Guidance Scale", step=0.5),
+        gr.Slider(minimum=1, maximum=50, value=28, label="Number of Steps", step=1),
+        gr.Slider(minimum=1, maximum=1000000, value=11, label="Seed", step=1),
+        gr.Slider(minimum=128, maximum=1024, value=1024, label="Width", step=64),
+        gr.Slider(minimum=128, maximum=1024, value=1024, label="Height", step=64)
+    ],
+    outputs=gr.Image(type="pil", label="Generated Image"),
+    title="Flux Image Generator (Zero-GPU)",
+    description="Generate images using Freepik's Flux model with Zero-GPU allocation",
+    examples=[
+        ["A close-up image of a green alien with fluorescent skin in the middle of a dark purple forest", 3.5, 28, 11, 1024, 1024],
+        ["A serene landscape with mountains at sunset", 3.5, 28, 42, 1024, 1024],
+    ]
+)
+
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1,6 +1,7 @@
-accelerate
-diffusers
-invisible_watermark
 torch
+diffusers
 transformers
-xformers
+gradio
+pillow
+huggingface-hub
+spaces