Update app.py

app.py

@@ -8,6 +8,127 @@ from PIL import Image
 from diffusers import QwenImageEditPipeline
 
 import os
+import base64
+import json
+
+SYSTEM_PROMPT = '''
+# Edit Instruction Rewriter
+You are a professional edit instruction rewriter. Your task is to generate a precise, concise, and visually achievable professional-level edit instruction based on the user-provided instruction and the image to be edited.  
+
+Please strictly follow the rewriting rules below:
+
+## 1. General Principles
+- Keep the rewritten prompt **concise**. Avoid overly long sentences and reduce unnecessary descriptive language.  
+- If the instruction is contradictory, vague, or unachievable, prioritize reasonable inference and correction, and supplement details when necessary.  
+- Keep the core intention of the original instruction unchanged, only enhancing its clarity, rationality, and visual feasibility.  
+- All added objects or modifications must align with the logic and style of the edited input image’s overall scene.  
+
+## 2. Task Type Handling Rules
+### 1. Add, Delete, Replace Tasks
+- If the instruction is clear (already includes task type, target entity, position, quantity, attributes), preserve the original intent and only refine the grammar.  
+- If the description is vague, supplement with minimal but sufficient details (category, color, size, orientation, position, etc.). For example:  
+    > Original: "Add an animal"  
+    > Rewritten: "Add a light-gray cat in the bottom-right corner, sitting and facing the camera"  
+- Remove meaningless instructions: e.g., "Add 0 objects" should be ignored or flagged as invalid.  
+- For replacement tasks, specify "Replace Y with X" and briefly describe the key visual features of X.  
+
+### 2. Text Editing Tasks
+- All text content must be enclosed in English double quotes `" "`. Do not translate or alter the original language of the text.  
+- **For text replacement tasks, always use the fixed template:** `Replace "xx" to "yy"`. Do not improvise beyond this format.  
+- If the user does not specify text content, infer and add concise text based on the instruction and the input image’s context. For example:  
+    > Original: "Add a line of text" (poster)  
+    > Rewritten: "Add text \"LIMITED EDITION\" at the top center, bold white font with slight shadow"  
+- Specify text position, font style (can be inferred), color, and layout in a concise way.  
+
+### 3. Human Editing Tasks
+- Maintain the person’s core visual consistency (ethnicity, gender, age, hairstyle, expression, outfit, etc.).  
+- If modifying appearance (e.g., clothes, hairstyle), ensure the new element is consistent with the original style.  
+- **For expression changes, they must be natural and subtle, never exaggerated.**  
+- Example:  
+    > Original: "Change the person’s hat"  
+    > Rewritten: "Replace the man’s hat with a dark brown beret; keep smile, short hair, and gray jacket unchanged"  
+
+### 4. Style Transformation or Enhancement Tasks
+- If a style is specified, describe it concisely with key visual traits. For example:  
+    > Original: "Disco style"  
+    > Rewritten: "1970s disco: flashing lights, disco ball, mirrored walls, colorful tones"  
+- If the instruction says "use reference style" or "keep current style," analyze the input image, extract main features (color, composition, texture, lighting, art style), and integrate them concisely.  
+- **For coloring tasks, do not preserve the original tones.** Example:  
+    > "Restore old photograph, remove scratches, reduce noise, enhance details, high resolution, realistic, natural skin tones, clear facial features, no distortion, vintage photo restoration"  
+
+## 3. Rationality and Logic Checks
+- Resolve contradictory instructions: e.g., "Remove all trees but keep all trees" should be logically corrected.  
+- Add missing key information: if position is unspecified, choose a reasonable area based on composition (near subject, empty space, center/edges).  
+
+# Output Format Example
+```json
+{
+   "Rewritten": "..."
+}
+'''
+
+def polish_prompt(prompt, img):
+    prompt = f"{SYSTEM_PROMPT}\n\nUser Input: {prompt}\n\nRewritten Prompt:"
+    success=False
+    while not success:
+        try:
+            result = api(prompt, [img])
+            # print(f"Result: {result}")
+            # print(f"Polished Prompt: {polished_prompt}")
+            if isinstance(result, str):
+                result = result.replace('```json','')
+                result = result.replace('```','')
+                result = json.loads(result)
+            else:
+                result = json.loads(result)
+
+            polished_prompt = result['Rewritten']
+            polished_prompt = polished_prompt.strip()
+            polished_prompt = polished_prompt.replace("\n", " ")
+            success = True
+        except Exception as e:
+            print(f"[Warning] Error during API call: {e}")
+    return polished_prompt
+
+
+def encode_image(pil_image):
+    import io
+    buffered = io.BytesIO()
+    pil_image.save(buffered, format="PNG")
+    return base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+
+
+
+def api(prompt, img_list, model="qwen-vl-max-latest", kwargs={}):
+    import dashscope
+    api_key = os.environ.get('DASH_API_KEY')
+    if not api_key:
+        raise EnvironmentError("DASH_API_KEY is not set")
+    assert model in ["qwen-vl-max-latest"], f"Not implemented model {model}"
+    sys_promot = "you are a helpful assistant, you should provide useful answers to users."
+    messages = [
+        {"role": "system", "content": sys_promot},
+        {"role": "user", "content": []}]
+    for img in img_list:
+        messages[1]["content"].append(
+            {"image": f"data:image/png;base64,{encode_image(img)}"})
+    messages[1]["content"].append({"text": f"{prompt}"})
+
+    response_format = kwargs.get('response_format', None)
+
+    response = dashscope.MultiModalConversation.call(
+        api_key=api_key,
+        model=model, # For example, use qwen-plus here. You can change the model name as needed. Model list: https://help.aliyun.com/zh/model-studio/getting-started/models
+        messages=messages,
+        result_format='message',
+        response_format=response_format,
+        )
+
+    if response.status_code == 200:
+        return response.output.choices[0].message.content[0]['text']
+    else:
+        raise Exception(f'Failed to post: {response}')
 
 # --- Model Loading ---
 dtype = torch.bfloat16
@@ -20,22 +141,23 @@ pipe = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit", torch_dtype
 MAX_SEED = np.iinfo(np.int32).max
 
 # --- Main Inference Function (with hardcoded negative prompt) ---
-@spaces.GPU(duration=120)
+@spaces.GPU(duration=300)
 def infer(
     image,
     prompt,
     seed=42,
     randomize_seed=False,
-    guidance_scale=4.0,
     true_guidance_scale=1.0,
     num_inference_steps=50,
+    rewrite_prompt=True,
+    num_images_per_prompt=1,
     progress=gr.Progress(track_tqdm=True),
 ):
     """
     Generates an image using the local Qwen-Image diffusers pipeline.
     """
     # Hardcode the negative prompt as requested
-    negative_prompt = "text, watermark, copyright, blurry, low resolution"
+    negative_prompt = " "
     
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
@@ -45,7 +167,10 @@ def infer(
     
     print(f"Calling pipeline with prompt: '{prompt}'")
     print(f"Negative Prompt: '{negative_prompt}'")
-    print(f"Seed: {seed}, Steps: {num_inference_steps}, Guidance: {guidance_scale}")
+    print(f"Seed: {seed}, Steps: {num_inference_steps}, Guidance: {true_guidance_scale}")
+    if rewrite_prompt:
+        prompt = polish_prompt(prompt, image)
+        print(f"Rewritten Prompt: {prompt}")
 
     # Generate the image
     image = pipe(
@@ -55,8 +180,8 @@ def infer(
         num_inference_steps=num_inference_steps,
         generator=generator,
         true_cfg_scale=true_guidance_scale,
-        guidance_scale=guidance_scale  
-    ).images[0]
+        num_images_per_prompt=num_images_per_prompt
+    ).images
 
     return image, seed
 
@@ -73,21 +198,22 @@ css = """
 
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.HTML('<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_logo.png" alt="Qwen-Image Logo" width="400" style="display: block; margin: 0 auto;">')
-        gr.HTML('<h1 style="text-align: center;margin-left: 80px;color: #5b47d1;font-style: italic;">Edit</h1>', elem_id="edit_text")
+        gr.HTML('<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_edit_logo.png" alt="Qwen-Image Logo" width="400" style="display: block; margin: 0 auto;">')
         gr.Markdown("[Learn more](https://github.com/QwenLM/Qwen-Image) about the Qwen-Image series. Try on [Qwen Chat](https://chat.qwen.ai/), or [download model](https://huggingface.co/Qwen/Qwen-Image-Edit) to run locally with ComfyUI or diffusers.")
         with gr.Row():
             with gr.Column():
                 input_image = gr.Image(label="Input Image", show_label=False, type="pil")
-                prompt = gr.Text(
+
+            # result = gr.Image(label="Result", show_label=False, type="pil")
+            result = gr.Gallery(label="Result", show_label=False, type="pil")
+        with gr.Row():
+            prompt = gr.Text(
                     label="Prompt",
                     show_label=False,
                     placeholder="describe the edit instruction",
                     container=False,
-                )
-                run_button = gr.Button("Edit!", variant="primary")
-
-            result = gr.Image(label="Result", show_label=False, type="pil")
+            )
+            run_button = gr.Button("Edit!", variant="primary")
 
         with gr.Accordion("Advanced Settings", open=False):
             # Negative prompt UI element is removed here
@@ -103,20 +229,13 @@ with gr.Blocks(css=css) as demo:
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
 
             with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Distilled guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=4.0,
-                )
 
                 true_guidance_scale = gr.Slider(
                     label="True guidance scale",
                     minimum=1.0,
                     maximum=10.0,
                     step=0.1,
-                    value=1.0
+                    value=4.0
                 )
 
                 num_inference_steps = gr.Slider(
@@ -126,6 +245,16 @@ with gr.Blocks(css=css) as demo:
                     step=1,
                     value=50,
                 )
+                
+                num_images_per_prompt = gr.Slider(
+                    label="Number of images per prompt",
+                    minimum=1,
+                    maximum=4,
+                    step=1,
+                    value=1,
+                )
+                
+                rewrite_prompt = gr.Checkbox(label="Rewrite prompt", value=True)
 
         # gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=False)
 
@@ -137,9 +266,10 @@ with gr.Blocks(css=css) as demo:
             prompt,
             seed,
             randomize_seed,
-            guidance_scale,
             true_guidance_scale,
             num_inference_steps,
+            rewrite_prompt,
+            num_images_per_prompt,
         ],
         outputs=[result, seed],
     )