Update Gradio app with multiple files

app.py

@@ -17,9 +17,6 @@ from safetensors.torch import load_file
 
 from PIL import Image
 import os
-import gradio as gr
-from gradio_client import Client, handle_file
-import tempfile
 
 
 # --- Model Loading ---
@@ -32,32 +29,20 @@ pipe = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509",
                                                                                                          torch_dtype=dtype,
                                                                                                          device_map='cuda'),torch_dtype=dtype).to(device)
 
-pipe.load_lora_weights("autoweeb/Qwen-Image-Edit-2509-Photo-to-Anime", adapter_name="anime")
+pipe.load_lora_weights("autoweeb/Qwen-Image-Edit-2509-Photo-to-Anime", 
+                       weight_name="Qwen-Image-Edit-2509-Photo-to-Anime_000001000.safetensors",
+                       adapter_name="anime")
 pipe.set_adapters(["anime"], adapter_weights=[1.])
 pipe.fuse_lora(adapter_names=["anime"], lora_scale=1.0)
 pipe.unload_lora_weights()
 
-
-
 pipe.transformer.__class__ = QwenImageTransformer2DModel
 pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())
 
 optimize_pipeline_(pipe, image=[Image.new("RGB", (1024, 1024)), Image.new("RGB", (1024, 1024))], prompt="prompt")
 
-
 MAX_SEED = np.iinfo(np.int32).max
 
-def _generate_video_segment(input_image_path: str, output_image_path: str, prompt: str, request: gr.Request) -> str:
-    """Generates a single video segment using the external service."""
-    x_ip_token = request.headers['x-ip-token']
-    video_client = Client("multimodalart/wan-2-2-first-last-frame", headers={"x-ip-token": x_ip_token})
-    result = video_client.predict(
-        start_image_pil=handle_file(input_image_path),
-        end_image_pil=handle_file(output_image_path),
-        prompt=prompt, api_name="/generate_video",
-    )
-    return result[0]["video"]
-
 @spaces.GPU
 def convert_to_anime(
     image,
@@ -166,62 +151,63 @@ def update_dimensions_on_upload(image):
     return new_width, new_height
 
 
+with gr.Blocks(theme=gr.themes.Soft(), css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown("# 🎨 Photo to Anime", elem_id="title")
+        gr.Markdown(
+            """
+            Transform your photos into beautiful anime-style images ✨
+            <br>
+            <div style='text-align: center; margin-top: 1rem;'>
+                <a href='https://huggingface.co/spaces/akhaliq/anycoder' target='_blank' style='color: #0071e3; text-decoration: none; font-weight: 500;'>Built with anycoder</a>
+            </div>
+            """,
+            elem_id="description"
+        )
+
+        with gr.Row():
+            with gr.Column(scale=1):
+                image = gr.Image(
+                    label="Upload Photo", 
+                    type="pil",
+                    elem_classes="image-container"
+                )
+                
+                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)
+                    true_guidance_scale = gr.Slider(label="Guidance Scale", minimum=1.0, maximum=10.0, step=0.1, value=1.0)
+                    num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=40, step=1, value=4)
+                    height = gr.Slider(label="Height", minimum=256, maximum=2048, step=8, value=1024, visible=False)
+                    width = gr.Slider(label="Width", minimum=256, maximum=2048, step=8, value=1024, visible=False)
+                
+                convert_btn = gr.Button("Convert to Anime", variant="primary", elem_id="convert-btn", size="lg")
+
+            with gr.Column(scale=1):
+                result = gr.Image(
+                    label="Anime Result", 
+                    interactive=False,
+                    elem_classes="image-container"
+                )
+    
+    inputs = [
+        image, seed, randomize_seed, true_guidance_scale, 
+        num_inference_steps, height, width
+    ]
+    outputs = [result, seed]
 
-            ["tool_of_the_sea.png", 90, 0, 0, False, 0, True, 1.0, 4, 568, 1024],
-            ["monkey.jpg", -90, 0, 0, False, 0, True, 1.0, 4, 704, 1024],
-            ["metropolis.jpg", 0, 0, -1, False, 0, True, 1.0, 4, 816, 1024],
-            ["disaster_girl.jpg", -45, 0, 1, False, 0, True, 1.0, 4, 768, 1024],
-            ["grumpy.png", 90, 0, 1, False, 0, True, 1.0, 4, 576, 1024]
-        ],
-        inputs=[image,rotate_deg, move_forward,
-        vertical_tilt, wideangle,
-        seed, randomize_seed, true_guidance_scale, num_inference_steps, height, width],
-        outputs=outputs,
-        fn=infer_camera_edit,
-        cache_examples="lazy",
-        elem_id="examples"
+    # Convert button click
+    convert_btn.click(
+        fn=convert_to_anime, 
+        inputs=inputs, 
+        outputs=outputs
     )
-    
-    # Image upload triggers dimension update and control reset
+
+    # Image upload triggers dimension update
     image.upload(
         fn=update_dimensions_on_upload,
         inputs=[image],
         outputs=[width, height]
-    ).then(
-        fn=reset_all,
-        inputs=None,
-        outputs=[rotate_deg, move_forward, vertical_tilt, wideangle, is_reset],
-        queue=False
-    ).then(
-        fn=end_reset, 
-        inputs=None, 
-        outputs=[is_reset], 
-        queue=False
     )
 
-
-    # Live updates
-    def maybe_infer(is_reset, progress=gr.Progress(track_tqdm=True), *args):
-        if is_reset:
-            return gr.update(), gr.update(), gr.update(), gr.update()
-        else:
-            result_img, result_seed, result_prompt = infer_camera_edit(*args)
-            # Show video button if we have both input and output
-            show_button = args[0] is not None and result_img is not None
-            return result_img, result_seed, result_prompt, gr.update(visible=show_button)
-
-    control_inputs = [
-        image, rotate_deg, move_forward,
-        vertical_tilt, wideangle,
-        seed, randomize_seed, true_guidance_scale, num_inference_steps, height, width, prev_output
-    ]
-    control_inputs_with_flag = [is_reset] + control_inputs
-
-    for control in [rotate_deg, move_forward, vertical_tilt]:
-        control.release(fn=maybe_infer, inputs=control_inputs_with_flag, outputs=outputs + [create_video_button])
-    
-    wideangle.input(fn=maybe_infer, inputs=control_inputs_with_flag, outputs=outputs + [create_video_button])
-    
-    run_event.then(lambda img, *_: img, inputs=[result], outputs=[prev_output])
-
 demo.launch()

requirements.txt

@@ -1,10 +1,23 @@
-git+https://github.com/huggingface/diffusers.git
-transformers
-accelerate
+huggingface_hub
+gradio
+git+https://github.com/huggingface/diffusers
 safetensors
+numpy
+torch
+spaces
+Pillow
+git+https://github.com/huggingface/transformers
 sentencepiece
-dashscope
-kernels
+accelerate
+tokenizers
+requests
+tqdm
 torchvision
-peft
-torchao==0.11.0
+opencv-python
+scikit-learn
+matplotlib
+xformers
+bitsandbytes
+pillow-heif
+imageio
+timm