Update README.md

README.md

@@ -4,9 +4,9 @@ emoji: 🏆
 colorFrom: blue
 colorTo: purple
 sdk: gradio
-sdk_version: 4.39.0
+sdk_version: 5.14.0
 app_file: app.py
 pinned: true
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,26 +1,24 @@
-import spaces
-
 import gradio as gr
 import numpy as np
 import os
+import spaces
 import random
 import json
+# from image_gen_aux import DepthPreprocessor
 from PIL import Image
 import torch
 from torchvision import transforms
-import zipfile
 
 from diffusers import FluxFillPipeline, AutoencoderKL
 from PIL import Image
-# from samgeo.text_sam import LangSAM
+
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
-# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-# sam = LangSAM(model_type="sam2-hiera-large").to(device)
-
 pipe = FluxFillPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16).to("cuda")
+# pipe.load_lora_weights("Himanshu806/testLora")
+# pipe.enable_lora()
 
 with open("lora_models.json", "r") as f:
     lora_models = json.load(f)
@@ -39,68 +37,21 @@ for model_name, model_path in lora_models.items():
 
 lora_models["None"] = None
 
-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(durations=300)
-def infer(edit_images, prompt, lora_model, strength, seed=42, randomize_seed=False, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
+def infer(edit_images, prompt, width, height, lora_model, seed=42, randomize_seed=False, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
     # pipe.enable_xformers_memory_efficient_attention()
-    gr.Info("Infering")
 
     if lora_model != "None":
         pipe.load_lora_weights(lora_models[lora_model])
         pipe.enable_lora()
 
-    gr.Info("starting checks")
-
     image = edit_images["background"]
+    # width, height = calculate_optimal_dimensions(image)
     mask = edit_images["layers"][0]
-
-    if not image:
-        gr.Info("Please upload an image.")
-        return None, None
-
-
-    width, height = calculate_optimal_dimensions(image)
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
 
     # controlImage = processor(image)
-    gr.Info("generating image")
     image = pipe(
         # mask_image_latent=vae.encode(controlImage),
         prompt=prompt,
@@ -110,10 +61,8 @@ def infer(edit_images, prompt, lora_model, strength, seed=42, randomize_seed=Fal
         height=height,
         width=width,
         guidance_scale=guidance_scale,
-        # strength=strength,
         num_inference_steps=num_inference_steps,
         generator=torch.Generator(device='cuda').manual_seed(seed),
-        # generator=torch.Generator().manual_seed(seed),
         # lora_scale=0.75 // not supported in this version
     ).images[0]
 
@@ -123,56 +72,6 @@ def infer(edit_images, prompt, lora_model, strength, seed=42, randomize_seed=Fal
     return output_image_jpg, seed
     # return image, seed
 
-def download_image(image):
-    if isinstance(image, np.ndarray):
-        image = Image.fromarray(image)
-    image.save("output.png", "PNG")
-    return "output.png"
-
-def save_details(result, edit_image, prompt, lora_model, strength, seed, guidance_scale, num_inference_steps):
-    image = edit_image["background"]
-    mask = edit_image["layers"][0]
-
-    if isinstance(result, np.ndarray):
-        result = Image.fromarray(result)
-    if isinstance(image, np.ndarray):
-        image = Image.fromarray(image)
-    if isinstance(mask, np.ndarray):
-        mask = Image.fromarray(mask)
-
-    result.save("saved_result.png", "PNG")
-    image.save("saved_image.png", "PNG")
-    mask.save("saved_mask.png", "PNG")
-
-    details = {
-        "prompt": prompt,
-        "lora_model": lora_model,
-        "strength": strength,
-        "seed": seed,
-        "guidance_scale": guidance_scale,
-        "num_inference_steps": num_inference_steps
-    }
-
-    with open("details.json", "w") as f:
-        json.dump(details, f)
-
-    # Create a ZIP file
-    with zipfile.ZipFile("output.zip", "w") as zipf:
-        zipf.write("saved_result.png")
-        zipf.write("saved_image.png")
-        zipf.write("saved_mask.png")
-        zipf.write("details.json")
-
-    return "output.zip"
-
-def set_image_as_inpaint(image):
-    return image
-
-# def generate_mask(image, click_x, click_y):
-#     text_prompt = "face"
-#     mask = sam.predict(image, text_prompt, box_threshold=0.24, text_threshold=0.24)
-#     return mask
-
 examples = [
     "photography of a young woman,  accent lighting,  (front view:1.4),  "
     # "a tiny astronaut hatching from an egg on the moon",
@@ -253,65 +152,29 @@ with gr.Blocks(css=css) as demo:
 
             with gr.Row():
 
-                strength = gr.Slider(
-                    label="Strength",
-                    minimum=0,
-                    maximum=1,
-                    step=0.01,
-                    value=0.85,
+                width = gr.Slider(
+                    label="width",
+                    minimum=512,
+                    maximum=3072,
+                    step=1,
+                    value=1024,
                 )
 
-            #     width = gr.Slider(
-            #         label="width",
-            #         minimum=512,
-            #         maximum=3072,
-            #         step=1,
-            #         value=1024,
-            #     )
-
-            #     height = gr.Slider(
-            #         label="height",
-            #         minimum=512,
-            #         maximum=3072,
-            #         step=1,
-            #         value=1024,
-            #     )
+                height = gr.Slider(
+                    label="height",
+                    minimum=512,
+                    maximum=3072,
+                    step=1,
+                    value=1024,
+                )
 
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn = infer,
-        inputs = [edit_image, prompt, lora_model, strength, seed, randomize_seed, guidance_scale, num_inference_steps],
+        inputs = [edit_image, prompt, width, height, lora_model, seed, randomize_seed, guidance_scale, num_inference_steps],
         outputs = [result, seed]
     )
 
-    download_button = gr.Button("Download Image as PNG")
-    set_inpaint_button = gr.Button("Set Image as Inpaint")
-    save_button = gr.Button("Save Details")
-
-    download_button.click(
-            fn=download_image,
-            inputs=[result],
-            outputs=gr.File(label="Download Image")
-        )
-
-    set_inpaint_button.click(
-            fn=set_image_as_inpaint,
-            inputs=[result],
-            outputs=[edit_image]
-    )
-
-    save_button.click(
-            fn=save_details,
-            inputs=[result, edit_image, prompt, lora_model, strength, seed, guidance_scale, num_inference_steps],
-            outputs=gr.File(label="Download/Save Status")
-    )
-
-    # edit_image.select(
-    #     fn=generate_mask,
-    #     inputs=[edit_image, gr.Number(), gr.Number()],
-    #     outputs=[edit_image]
-    # )
-
 # demo.launch()
 PASSWORD = os.getenv("GRADIO_PASSWORD")
 USERNAME = os.getenv("GRADIO_USERNAME")
@@ -324,4 +187,4 @@ def authenticate(username, password):
         return False
 # Launch the app with authentication
 
-demo.launch(debug=True, auth=authenticate)
+demo.launch(auth=authenticate)

lora_models.json

@@ -1,6 +1,4 @@
 {
-  "RahulFineTuned (qwertyui)": "Himanshu806/testLora",
-  "femaleIndian (indmodelf)": "Himanshu806/ind-f-model",
-  "KodaRealistic (flmft style)": "alvdansen/flux-koda",
-  "superRealism (Super Realism)": "strangerzonehf/Flux-Super-Realism-LoRA"
+  "RahulFineTuned": "Himanshu806/testLora",
+  "KodaRealistic": "alvdansen/flux-koda"
 }

readme.md

@@ -1,10 +1,10 @@
 ---
-title: Inpainting Test UI
+title: Inpainting
 emoji: 🏆
 colorFrom: blue
 colorTo: purple
 sdk: gradio
-sdk_version: 5.14.0
+sdk_version: 4.39.0
 app_file: app.py
 pinned: true
 ---

requirements.txt

@@ -8,6 +8,3 @@ peft
 xformers
 torchvision
 torch
-opencv-python
-segment-geospatial
-groundingdino-py