Create app.py

app.py

@@ -0,0 +1,199 @@
+import gradio as gr
+import numpy as np
+import random
+import torch
+import spaces
+from PIL import Image
+import os
+from huggingface_hub import hf_hub_download
+import torch
+import diffusers
+from pipeline_flux_rf_inversion import RFInversionFluxPipeline
+
+# Constants
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 1024
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+pipe = RFInversionFluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", 
+                                               torch_dtype=torch.bfloat16)
+pipe.to(DEVICE)
+
+def reset_do_inversion():
+        return True
+    
+def resize_img(image, max_size=1024):
+    width, height = image.size
+    scaling_factor = min(max_size / width, max_size / height)
+    new_width = int(width * scaling_factor)
+    new_height = int(height * scaling_factor)
+    return image.resize((new_width, new_height), Image.LANCZOS)
+
+def invert_and_edit(image, 
+                    prompt, 
+                    eta, 
+                    gamma, 
+                    start_timestep, 
+                    stop_timestep, 
+                    num_inversion_steps,
+                    width,
+                    height,
+                    inverted_latents,
+                    image_latents,
+                    latent_image_ids,
+                    do_inversion,
+                    seed,
+                    randomize_seed,
+                   ):
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    if do_inversion:
+        inverted_latents_tensor, image_latents_tensor, latent_image_ids_tensor = pipe.invert(image, num_inversion_steps=num_inversion_steps, gamma=gamma)
+        inverted_latents = gr.State(value=inverted_latents_tensor)
+        image_latents = gr.State(value=image_latents_tensor)
+        latent_image_ids = gr.State(value=latent_image_ids_tensor)
+        do_inversion = False
+    
+    else:
+        output = pipe(prompt, 
+        inverted_latents=inverted_latents.value,
+        image_latents=image_latents.value,
+        latent_image_ids=latent_image_ids.value,
+        start_timestep=start_timestep, 
+        stop_timestep=stop_timestep,
+        num_inference_steps=num_inversion_steps,
+        eta=eta, 
+        ).images[0]
+        
+    return output, inverted_latents, image_latents, latent_image_ids, do_inversion, seed
+
+# UI CSS
+css = """
+#col-container {
+    margin: 0 auto;
+    max-width: 960px;
+}
+"""
+
+# Create the Gradio interface
+with gr.Blocks(css=css) as demo:
+
+    inverted_latents = gr.State()
+    image_latents = gr.State()
+    latent_image_ids = gr.State()
+    do_inversion = gr.State(False)
+    
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""# RF inversion with FLUX.1 [dev] 🖌️🏞️
+Edit real images with Flux, based on the algorithm proposed in [*Semantic Image Inversion and Editing using
+Stochastic Rectified Differential Equations*](https://rf-inversion.github.io/data/rf-inversion.pdf)
+[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[project page](https://rf-inversion.github.io/] [[arxiv](https://arxiv.org/pdf/2410.10792)]
+        """)
+        
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(
+                    label="Input Image",
+                    type="pil"
+                )
+                eta = gr.Slider(
+                    label="eta",
+                    info = "lower eta to ehnace the edits",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.9,
+                )
+                prompt = gr.Text(
+                    label="Edit Prompt",
+                    max_lines=1,
+                    placeholder="describe the edited output",
+                )
+                run_button = gr.Button("Edit", variant="primary")
+            
+            with gr.Column():
+                result = gr.Image(label="Result")
+        
+        with gr.Accordion("Advanced Settings", open=False):
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=42,
+            )
+            
+            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():
+                gamma = gr.Slider(
+                    label="gamma",
+                    info = "lower gamma to ehnace the edits",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.9,
+                )
+                start_timestep = gr.Slider(
+                    label="start timestep",
+                    info = "lower gamma to ehnace the edits",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.9,
+                )
+                stop_timestep = gr.Slider(
+                    label="stop timestep",
+                    info = "lower gamma to ehnace the edits",
+                    minimum=0.0,
+                    maximum=1.0,
+                    step=0.1,
+                    value=0.9,
+                )
+    
+    run_button.click(
+        fn=invert_and_edit,
+        inputs=[
+            input_image,
+            prompt,
+            eta, 
+            gamma, 
+            start_timestep, 
+            stop_timestep, 
+            num_inversion_steps,
+            width,
+            height,
+            inverted_latents,
+            image_latents,
+            latent_image_ids,
+            do_inversion,
+            seed,
+            randomize_seed
+        ],
+        outputs=[result, inverted_latents, image_latents, latent_image_ids, do_inversion, seed],
+    )
+
+    input_image.change(
+        fn=reset_do_inversion,
+        outputs=[do_inversion]
+    )
+
+if __name__ == "__main__":
+    demo.launch()