test with flux

app_v2.py

@@ -0,0 +1,167 @@
+import gradio as gr
+import numpy as np
+import random
+import spaces
+import torch
+from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL
+from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5TokenizerFast
+from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images
+import requests
+import base64
+import os
+from PIL import Image
+from io import BytesIO
+from gradio_imageslider import ImageSlider  # Assicurati di avere questa libreria installata
+from loadimg import load_img  # Assicurati che questa funzione sia disponibile
+from dotenv import load_dotenv
+
+# Carica le variabili di ambiente dal file .env
+load_dotenv()
+
+dtype = torch.bfloat16
+device = "cuda" if torch.cuda.is_available() else "cpu"
+taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
+good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
+pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype, vae=taef1).to(device)
+torch.cuda.empty_cache()
+
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 2048
+
+pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)
+
+output_folder = 'output_images'
+if not os.path.exists(output_folder):
+    os.makedirs(output_folder)
+
+
+def numpy_to_pil(image):
+    """Convert a numpy array to a PIL Image."""
+    if image.dtype == np.uint8:  # Most common case
+        mode = "RGB"
+    else:
+        mode = "F"  # Floating point
+    return Image.fromarray(image.astype('uint8'), mode)
+
+
+def process_image(image):
+    image = numpy_to_pil(image)  # Convert numpy array to PIL Image
+    buffered = BytesIO()
+    image.save(buffered, format="PNG")
+    img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
+    response = requests.post(
+        os.getenv('BACKEND_URL'),
+        files={"file": ("image.png", base64.b64decode(img_str), "image/png")}
+    )
+    result = response.json()
+    processed_image_b64 = result["processed_image"]
+    processed_image = Image.open(BytesIO(base64.b64decode(processed_image_b64)))
+    image_path = os.path.join(output_folder, "no_bg_image.png")
+    processed_image.save(image_path)
+    return (processed_image, image), image_path
+
+
+@spaces.GPU(duration=75)
+def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28,
+          progress=gr.Progress(track_tqdm=True)):
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    generator = torch.Generator().manual_seed(seed)
+    for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
+            prompt=prompt,
+            guidance_scale=guidance_scale,
+            num_inference_steps=num_inference_steps,
+            width=width,
+            height=height,
+            generator=generator,
+            output_type="pil",
+            good_vae=good_vae,
+    ):
+        img_np = np.array(img)
+        processed_images, image_path = process_image(img_np)
+        yield processed_images[0], seed, processed_images[1], image_path
+
+
+examples = [
+    "a tiny astronaut hatching from an egg on the moon",
+    "a cat holding a sign that says hello world",
+    "an anime illustration of a wiener schnitzel",
+]
+
+css = """  
+#col-container {  
+    margin: 0 auto;  
+    max-width: 520px;  
+}  
+"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""# FLUX.1 [dev]  
+12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)  [[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]  
+        """)
+        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)
+        result = gr.Image(label="Generated Image", show_label=False)
+        output_slider = ImageSlider(label="Processed Photo", type="pil")
+        output_file = gr.File(label="Output PNG file")
+        with gr.Accordion("Advanced Settings", open=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,
+                )
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+            with gr.Row():
+                guidance_scale = gr.Slider(
+                    label="Guidance Scale",
+                    minimum=1,
+                    maximum=15,
+                    step=0.1,
+                    value=3.5,
+                )
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=28,
+                )
+        gr.Examples(
+            examples=examples,
+            fn=infer,
+            inputs=[prompt],
+            outputs=[result, seed, output_slider, output_file],
+            cache_examples="lazy"
+        )
+        gr.on(
+            triggers=[run_button.click, prompt.submit],
+            fn=infer,
+            inputs=[prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+            outputs=[result, seed, output_slider, output_file]
+        )
+demo.launch()