change ar

app.py

@@ -1,124 +1,171 @@
 import gradio as gr
-import os
-from PIL import Image
+import numpy as np
+
+import spaces
 import torch
-from diffusers.utils import load_image, check_min_version
-from controlnet_flux import FluxControlNetModel
-from transformer_flux import FluxTransformer2DModel
-from pipeline_flux_controlnet_inpaint import FluxControlNetInpaintingPipeline
 import spaces
-import huggingface_hub
-huggingface_hub.login(os.getenv('HF_TOKEN'))
-
-check_min_version("0.30.2")
-transformer = FluxTransformer2DModel.from_pretrained(
-        "black-forest-labs/FLUX.1-dev", subfolder='transformer', torch_dytpe=torch.bfloat16
-    )
-
-# Build pipeline
-# controlnet = FluxControlNetModel.from_pretrained("alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", torch_dtype=torch.bfloat16)
-pipe = FluxControlNetInpaintingPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    # controlnet=controlnet,
-    transformer=transformer,
-    torch_dtype=torch.bfloat16
-).to("cuda")
-pipe.transformer.to(torch.bfloat16)
-pipe.controlnet.to(torch.bfloat16)
-
+import random 
 
-MARKDOWN = """
-# FLUX.1-dev-Inpainting
-
-#### VERSION: 0.0.3_beta
-
-Original Model: Flux.1-dev
-FluxControlNet: alimama-creative
+from diffusers import FluxFillPipeline
+from PIL import Image
 
-"""
 
-@spaces.GPU()
-def process(input_image_editor,
-            prompt,
-            negative_prompt,
-            controlnet_conditioning_scale,
-            guidance_scale,
-            seed,
-            num_inference_steps,
-            true_guidance_scale
-            ):
-    image = input_image_editor['background']
-    mask = input_image_editor['layers'][0]
-    size = (768, 768)
-    image_or = image.copy()
-
-    image = image.convert("RGB").resize(size)
-    mask = mask.convert("RGB").resize(size)
-    generator = torch.Generator(device="cuda").manual_seed(seed)
-    result = pipe(
-    prompt=prompt,
-    height=size[1],
-    width=size[0],
-    control_image=image,
-    control_mask=mask,
-    num_inference_steps=num_inference_steps,
-    generator=generator,
-    controlnet_conditioning_scale=controlnet_conditioning_scale,
-    guidance_scale=guidance_scale,
-    negative_prompt=negative_prompt,
-    true_guidance_scale=true_guidance_scale
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 2048
+
+pipe = FluxFillPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16).to("cuda")
+
+def calculate_optimal_dimensions(image: Image.Image):
+    # Extract the original dimensions
+    original_width, original_height = image.size
+    
+    # Set constants
+    MIN_ASPECT_RATIO = 9 / 16
+    MAX_ASPECT_RATIO = 16 / 9
+    FIXED_DIMENSION = 1024
+
+    # Calculate the aspect ratio of the original image
+    original_aspect_ratio = original_width / original_height
+
+    # Determine which dimension to fix
+    if original_aspect_ratio > 1:  # Wider than tall
+        width = FIXED_DIMENSION
+        height = round(FIXED_DIMENSION / original_aspect_ratio)
+    else:  # Taller than wide
+        height = FIXED_DIMENSION
+        width = round(FIXED_DIMENSION * original_aspect_ratio)
+
+    # Ensure dimensions are multiples of 8
+    width = (width // 8) * 8
+    height = (height // 8) * 8
+
+    # Enforce aspect ratio limits
+    calculated_aspect_ratio = width / height
+    if calculated_aspect_ratio > MAX_ASPECT_RATIO:
+        width = (height * MAX_ASPECT_RATIO // 8) * 8
+    elif calculated_aspect_ratio < MIN_ASPECT_RATIO:
+        height = (width / MIN_ASPECT_RATIO // 8) * 8
+
+    # Ensure width and height remain above the minimum dimensions
+    width = max(width, 576) if width == FIXED_DIMENSION else width
+    height = max(height, 576) if height == FIXED_DIMENSION else height
+
+    return width, height
+
+@spaces.GPU
+def infer(edit_images, prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
+    image = edit_images["background"]
+    width, height = calculate_optimal_dimensions(image)
+    mask = edit_images["layers"][0]
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    image = pipe(
+        prompt=prompt,
+        image=image,
+        mask_image=mask,
+        height=height,
+        width=width,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        generator=torch.Generator("cpu").manual_seed(seed)
     ).images[0]
+    return image, seed
+    
+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: 1000px;
+}
+"""
 
-    return result.resize((image_or.size[:2]))
-
-with gr.Blocks() as demo:
-    gr.Markdown(MARKDOWN)
-    with gr.Row():
-        with gr.Column():
-            input_image_editor_component = gr.ImageEditor(
-                label='Image',
-                type='pil',
-                sources=["upload"],
-                image_mode='RGB',
-                layers=False,
-                brush=gr.Brush(colors=["#FFFFFF"], color_mode="fixed"))
-
-
-            prompt = gr.Textbox(lines=2, placeholder="Enter prompt here...")
-            negative_prompt = gr.Textbox(lines=2, placeholder="Enter negative_prompt here...")
-            controlnet_conditioning_scale = gr.Slider(minimum=0, step=0.01, maximum=1, value=0.8, label="controlnet_conditioning_scale")  # Adjusted value
-            guidance_scale = gr.Slider(minimum=1, step=0.5, maximum=10, value=5.0, label="Image to generate")  # Adjusted value
-            seed  = gr.Slider(minimum=0, step=1, maximum=10000000, value=124, label="Seed Value")
-            num_inference_steps = gr.Slider(minimum=1, step=1, maximum=50, value=40, label="num_inference_steps")  # Adjusted value
-            true_guidance_scale = gr.Slider(minimum=1, step=1, maximum=10, value=7.0, label="true_guidance_scale")  # Adjusted value
-
-
-
-            submit_button_component = gr.Button(
-                    value='Submit', variant='primary', scale=0)
-
-        with gr.Column():
-            output_image_component = gr.Image(
-                type='pil', image_mode='RGB', label='Generated image', format="png")
-
-    submit_button_component.click(
-        fn=process,
-        inputs=[
-            input_image_editor_component,
-            prompt,
-            negative_prompt,
-            controlnet_conditioning_scale,
-            guidance_scale,
-            seed,
-            num_inference_steps,
-            true_guidance_scale
-
-        ],
-        outputs=[
-            output_image_component,
-        ]
+with gr.Blocks(css=css) as demo:
+    
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""# FLUX.1 [dev]
+        """)
+        with gr.Row():
+            with gr.Column():
+                edit_image = gr.ImageEditor(
+                    label='Upload and draw mask for inpainting',
+                    type='pil',
+                    sources=["upload", "webcam"],
+                    image_mode='RGB',
+                    layers=False,
+                    brush=gr.Brush(colors=["#FFFFFF"], color_mode="fixed"),
+                    height=600
+                )
+                prompt = gr.Text(
+                    label="Prompt",
+                    show_label=False,
+                    max_lines=1,
+                    placeholder="Enter your prompt",
+                    container=False,
+                )
+                run_button = gr.Button("Run")
+                
+            result = gr.Image(label="Result", show_label=False)
+        
+        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,
+                    visible=False
+                )
+                
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                    visible=False
+                )
+            
+            with gr.Row():
+
+                guidance_scale = gr.Slider(
+                    label="Guidance Scale",
+                    minimum=1,
+                    maximum=30,
+                    step=0.5,
+                    value=50,
+                )
+  
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=28,
+                )
+
+    gr.on(
+        triggers=[run_button.click, prompt.submit],
+        fn = infer,
+        inputs = [edit_image, prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs = [result, seed]
     )
 
-
-
-demo.launch(debug=False, show_error=True,share=True)
+demo.launch()