Update app.py

app.py

@@ -16,7 +16,7 @@ from huggingface_hub import HfApi
 # Girdilerin kaydedileceği dataset
 INPUT_DATASET_ID = "tyndreus/image-edit-logs"
 # Çıktıların kaydedileceği dataset (Bunu oluşturduğunuzdan emin olun)
-OUTPUT_DATASET_ID = "tyndreus/output" 
+OUTPUT_DATASET_ID = "tyndreus/output"
 # ---------------
 
 colors.steel_blue = colors.Color(
@@ -87,8 +87,6 @@ class SteelBlueTheme(Soft):
 
 steel_blue_theme = SteelBlueTheme()
 
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
 from diffusers import FlowMatchEulerDiscreteScheduler
 from qwenimage.pipeline_qwenimage_edit_plus import QwenImageEditPlusPipeline
 from qwenimage.transformer_qwenimage import QwenImageTransformer2DModel
@@ -100,137 +98,216 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 pipe = QwenImageEditPlusPipeline.from_pretrained(
     "Qwen/Qwen-Image-Edit-2509",
     transformer=QwenImageTransformer2DModel.from_pretrained(
-        "linoyts/Qwen-Image-Edit-Rapid-AIO", 
-        subfolder='transformer',
+        "linoyts/Qwen-Image-Edit-Rapid-AIO",
+        subfolder="transformer",
         torch_dtype=dtype,
-        device_map='cuda'
+        device_map="cuda" if torch.cuda.is_available() else None,
     ),
-    torch_dtype=dtype
+    torch_dtype=dtype,
 ).to(device)
 
-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.load_lora_weights("dx8152/Qwen-Edit-2509-Multiple-angles", weight_name="镜头转换.safetensors", adapter_name="multiple-angles")
-pipe.load_lora_weights("dx8152/Qwen-Image-Edit-2509-Light_restoration", weight_name="移除光影.safetensors", adapter_name="light-restoration")
-pipe.load_lora_weights("dx8152/Qwen-Image-Edit-2509-Relight", weight_name="Qwen-Edit-Relight.safetensors", adapter_name="relight")
-pipe.load_lora_weights("dx8152/Qwen-Edit-2509-Multi-Angle-Lighting", weight_name="多角度灯光-251116.safetensors", adapter_name="multi-angle-lighting")
-pipe.load_lora_weights("tlennon-ie/qwen-edit-skin", weight_name="qwen-edit-skin_1.1_000002750.safetensors", adapter_name="edit-skin")
-pipe.load_lora_weights("lovis93/next-scene-qwen-image-lora-2509", weight_name="next-scene_lora-v2-3000.safetensors", adapter_name="next-scene")
-pipe.load_lora_weights("vafipas663/Qwen-Edit-2509-Upscale-LoRA", weight_name="qwen-edit-enhance_64-v3_000001000.safetensors", adapter_name="upscale-image")
+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.load_lora_weights("dx8152/Qwen-Edit-2509-Multiple-angles",
+                       weight_name="镜头转换.safetensors",
+                       adapter_name="multiple-angles")
+pipe.load_lora_weights("dx8152/Qwen-Image-Edit-2509-Light_restoration",
+                       weight_name="移除光影.safetensors",
+                       adapter_name="light-restoration")
+pipe.load_lora_weights("dx8152/Qwen-Image-Edit-2509-Relight",
+                       weight_name="Qwen-Edit-Relight.safetensors",
+                       adapter_name="relight")
+pipe.load_lora_weights("dx8152/Qwen-Edit-2509-Multi-Angle-Lighting",
+                       weight_name="多角度灯光-251116.safetensors",
+                       adapter_name="multi-angle-lighting")
+pipe.load_lora_weights("tlennon-ie/qwen-edit-skin",
+                       weight_name="qwen-edit-skin_1.1_000002750.safetensors",
+                       adapter_name="edit-skin")
+pipe.load_lora_weights("lovis93/next-scene-qwen-image-lora-2509",
+                       weight_name="next-scene_lora-v2-3000.safetensors",
+                       adapter_name="next-scene")
+pipe.load_lora_weights("vafipas663/Qwen-Edit-2509-Upscale-LoRA",
+                       weight_name="qwen-edit-enhance_64-v3_000001000.safetensors",
+                       adapter_name="upscale-image")
 
 pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())
+
 MAX_SEED = np.iinfo(np.int32).max
 
-def update_dimensions_on_upload(image):
-    if image is None: return 1024, 1024
+def _round8(x: int) -> int:
+    x = int(x)
+    return max(8, (x // 8) * 8)
+
+def update_dimensions_on_upload(image: Image.Image, max_side: int = 1024):
+    """Keep aspect ratio; fit the long side to max_side; round down to multiple of 8."""
+    if image is None:
+        return 1024, 1024
     original_width, original_height = image.size
     if original_width > original_height:
-        new_width = 1024
+        new_width = max_side
         aspect_ratio = original_height / original_width
         new_height = int(new_width * aspect_ratio)
     else:
-        new_height = 1024
+        new_height = max_side
         aspect_ratio = original_width / original_height
         new_width = int(new_height * aspect_ratio)
-    new_width = (new_width // 8) * 8
-    new_height = (new_height // 8) * 8
-    return new_width, new_height
+    return _round8(new_width), _round8(new_height)
 
 # --- HUB'A YÜKLEME YAPAN ORTAK FONKSİYON ---
 def upload_image_to_hub(image, dataset_id, folder_prefix="images"):
     try:
-        # Token kontrolü
         hf_token = os.environ.get("HF_TOKEN")
         if not hf_token:
-            print(f"Fail")
+            print("Fail")
             return
 
         api = HfApi(token=hf_token)
-        
-        # Dosya ismi oluşturma
+
         timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
         unique_id = str(uuid.uuid4())[:8]
         filename = f"{folder_prefix}_{timestamp}_{unique_id}.png"
-        
-        # Geçici olarak diske kaydet
+
         temp_path = f"/tmp/{filename}"
         image.save(temp_path)
-        
-        # Dataset'e yükle
+
         api.upload_file(
             path_or_fileobj=temp_path,
-            path_in_repo=f"{folder_prefix}/{filename}", 
+            path_in_repo=f"{folder_prefix}/{filename}",
             repo_id=dataset_id,
-            repo_type="dataset"
+            repo_type="dataset",
         )
-        
-        # Geçici dosyayı sil
+
         os.remove(temp_path)
-        print(f"Success")
-        
+        print("Success")
+
     except Exception as e:
         print(f"Yükleme hatası ({dataset_id}): {e}")
 # -------------------------------------------
 
-@spaces.GPU(duration=30)
-def infer(
+SIZE_PRESETS = [
+    "Auto (fit long side to 1024)",
+    "1024 x 1024 (Square)",
+    "1024 x 768 (Landscape)",
+    "768 x 1024 (Portrait)",
+    "512 x 512 (Fast)",
+    "Custom (use sliders)",
+]
+
+def apply_size_preset(preset, image, cur_w, cur_h):
+    if preset == "Auto (fit long side to 1024)":
+        if image is None:
+            return 1024, 1024
+        img = image.convert("RGB")
+        w, h = update_dimensions_on_upload(img, max_side=1024)
+        return w, h
+    if preset == "1024 x 1024 (Square)":
+        return 1024, 1024
+    if preset == "1024 x 768 (Landscape)":
+        return 1024, 768
+    if preset == "768 x 1024 (Portrait)":
+        return 768, 1024
+    if preset == "512 x 512 (Fast)":
+        return 512, 512
+    # Custom: keep current slider values
+    return _round8(cur_w), _round8(cur_h)
+
+def set_adapter(lora_adapter: str):
+    if lora_adapter == "Photo-to-Anime":
+        pipe.set_adapters(["anime"], adapter_weights=[1.0])
+    elif lora_adapter == "Multiple-Angles":
+        pipe.set_adapters(["multiple-angles"], adapter_weights=[1.0])
+    elif lora_adapter == "Light-Restoration":
+        pipe.set_adapters(["light-restoration"], adapter_weights=[1.0])
+    elif lora_adapter == "Relight":
+        pipe.set_adapters(["relight"], adapter_weights=[1.0])
+    elif lora_adapter == "Multi-Angle-Lighting":
+        pipe.set_adapters(["multi-angle-lighting"], adapter_weights=[1.0])
+    elif lora_adapter == "Edit-Skin":
+        pipe.set_adapters(["edit-skin"], adapter_weights=[1.0])
+    elif lora_adapter == "Next-Scene":
+        pipe.set_adapters(["next-scene"], adapter_weights=[1.0])
+    elif lora_adapter == "Upscale-Image":
+        pipe.set_adapters(["upscale-image"], adapter_weights=[1.0])
+
+@spaces.GPU(duration=60)
+def infer_6pack(
     input_image,
-    prompt,
+    prompt1,
+    prompt2,
+    prompt3,
     lora_adapter,
+    size_preset,
+    width,
+    height,
     seed,
     randomize_seed,
     guidance_scale,
     steps,
-    progress=gr.Progress(track_tqdm=True)
+    progress=gr.Progress(track_tqdm=True),
 ):
     if input_image is None:
         raise gr.Error("Please upload an image to edit.")
 
-    # 1. GİRDİ RESMİNİ KAYDET (INPUT)
+    # 1) Upload input
     upload_image_to_hub(input_image, INPUT_DATASET_ID, folder_prefix="inputs")
 
-    if lora_adapter == "Photo-to-Anime": pipe.set_adapters(["anime"], adapter_weights=[1.0])
-    elif lora_adapter == "Multiple-Angles": pipe.set_adapters(["multiple-angles"], adapter_weights=[1.0])
-    elif lora_adapter == "Light-Restoration": pipe.set_adapters(["light-restoration"], adapter_weights=[1.0])
-    elif lora_adapter == "Relight": pipe.set_adapters(["relight"], adapter_weights=[1.0])
-    elif lora_adapter == "Multi-Angle-Lighting": pipe.set_adapters(["multi-angle-lighting"], adapter_weights=[1.0])
-    elif lora_adapter == "Edit-Skin": pipe.set_adapters(["edit-skin"], adapter_weights=[1.0])
-    elif lora_adapter == "Next-Scene": pipe.set_adapters(["next-scene"], adapter_weights=[1.0])
-    elif lora_adapter == "Upscale-Image": pipe.set_adapters(["upscale-image"], adapter_weights=[1.0])
-        
-    if randomize_seed: seed = random.randint(0, MAX_SEED)
+    # Adapter
+    set_adapter(lora_adapter)
+
+    # Dimensions
+    width = _round8(width)
+    height = _round8(height)
+
+    # Prompts (3)
+    prompts = [prompt1, prompt2, prompt3]
 
-    generator = torch.Generator(device=device).manual_seed(seed)
-    negative_prompt = "worst quality, low quality, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry"
+    # Seeds (2 per prompt => 6)
+    seeds = []
+    if randomize_seed:
+        for _ in range(6):
+            seeds.append(random.randint(0, MAX_SEED))
+    else:
+        base = int(seed)
+        for i in range(6):
+            seeds.append((base + i) % MAX_SEED)
+
+    negative_prompt = (
+        "worst quality, low quality, bad anatomy, bad hands, text, error, missing fingers, "
+        "extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry"
+    )
 
     original_image = input_image.convert("RGB")
-    width, height = update_dimensions_on_upload(original_image)
-
-    result = pipe(
-        image=original_image,
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        height=height,
-        width=width,
-        num_inference_steps=steps,
-        generator=generator,
-        true_cfg_scale=guidance_scale,
-    ).images[0]
-    
-    # 2. ÇIKTI RESMİNİ KAYDET (OUTPUT)
-    # Burada 'generated' adında bir klasör ön eki ve OUTPUT_DATASET_ID kullanıyoruz
-    upload_image_to_hub(result, OUTPUT_DATASET_ID, folder_prefix="generated")
-
-    return result, seed
-
-@spaces.GPU(duration=30)
-def infer_example(input_image, prompt, lora_adapter):
-    input_pil = input_image.convert("RGB")
-    guidance_scale = 1.0
-    steps = 4
-    result, seed = infer(input_pil, prompt, lora_adapter, 0, True, guidance_scale, steps)
-    return result, seed
-
-css="""
+
+    outputs = []
+    seed_idx = 0
+    for p_i, p in enumerate(prompts):
+        for v in range(2):
+            s = seeds[seed_idx]
+            seed_idx += 1
+
+            generator = torch.Generator(device=device).manual_seed(int(s))
+            result = pipe(
+                image=original_image,
+                prompt=p,
+                negative_prompt=negative_prompt,
+                height=height,
+                width=width,
+                num_inference_steps=int(steps),
+                generator=generator,
+                true_cfg_scale=float(guidance_scale),
+            ).images[0]
+
+            # 2) Upload each output
+            upload_image_to_hub(result, OUTPUT_DATASET_ID, folder_prefix="generated")
+
+            caption = f"prompt{p_i+1} var{v+1} | seed={s} | {width}x{height}"
+            outputs.append((result, caption))
+
+    seeds_text = "\n".join([f"{i+1}: {s}" for i, s in enumerate(seeds)])
+    return outputs, seeds_text
+
+css = """
 #col-container {
     margin: 0 auto;
     max-width: 960px;
@@ -246,28 +323,90 @@ with gr.Blocks(css=css, theme=steel_blue_theme) as demo:
         with gr.Row(equal_height=True):
             with gr.Column():
                 input_image = gr.Image(label="Upload Image", type="pil", height=290)
-                prompt = gr.Text(label="Edit Prompt", show_label=True, placeholder="e.g., transform into anime..")
-                run_button = gr.Button("Edit Image", variant="primary")
 
-            with gr.Column():
-                output_image = gr.Image(label="Output Image", interactive=False, format="png", height=350)
+                size_preset = gr.Dropdown(
+                    label="Image Size Preset",
+                    choices=SIZE_PRESETS,
+                    value="Auto (fit long side to 1024)",
+                )
                 with gr.Row():
-                    lora_adapter = gr.Dropdown(
-                        label="Choose Editing Style",
-                        choices=["Photo-to-Anime", "Multiple-Angles", "Light-Restoration", "Multi-Angle-Lighting", "Upscale-Image", "Relight", "Next-Scene", "Edit-Skin"],
-                        value="Photo-to-Anime"
-                    )
-                with gr.Accordion("Advanced Settings", open=False, visible=False):
-                    seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
-                    randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
+                    width = gr.Slider(label="Width", minimum=256, maximum=2048, step=8, value=1024)
+                    height = gr.Slider(label="Height", minimum=256, maximum=2048, step=8, value=1024)
+
+                prompt1 = gr.Text(
+                    label="Prompt 1 (standing pose)",
+                    placeholder="e.g., ...",
+                    value="make this girl to another standing pose",
+                )
+                prompt2 = gr.Text(
+                    label="Prompt 2 (sitting pose)",
+                    placeholder="e.g., ...",
+                    value="make this girl to another sitting pose",
+                )
+                prompt3 = gr.Text(
+                    label="Prompt 3 (standing pose + hand sign)",
+                    placeholder="e.g., ...",
+                    value="make this girl to another standing pose with hand sign",
+                )
+
+                run_button = gr.Button("Generate 6 Images (3 prompts x 2 seeds)", variant="primary")
+
+            with gr.Column():
+                output_gallery = gr.Gallery(
+                    label="Outputs (3 x 2 = 6)",
+                    columns=3,
+                    rows=2,
+                    height=380,
+                    preview=True,
+                )
+
+                lora_adapter = gr.Dropdown(
+                    label="Choose Editing Style",
+                    choices=[
+                        "Photo-to-Anime",
+                        "Multiple-Angles",
+                        "Light-Restoration",
+                        "Multi-Angle-Lighting",
+                        "Upscale-Image",
+                        "Relight",
+                        "Next-Scene",
+                        "Edit-Skin",
+                    ],
+                    value="Next-Scene",  # ★ デフォルトを Next-Scene に
+                )
+
+                with gr.Accordion("Advanced Settings", open=False, visible=True):
+                    seed = gr.Slider(label="Base Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
+                    randomize_seed = gr.Checkbox(label="Randomize Seeds (6 images)", value=True)
                     guidance_scale = gr.Slider(label="Guidance Scale", minimum=1.0, maximum=10.0, step=0.1, value=1.0)
                     steps = gr.Slider(label="Inference Steps", minimum=1, maximum=50, step=1, value=4)
 
+                seeds_box = gr.Textbox(label="Used Seeds (1..6)", lines=6)
+
+    # Preset changes update sliders
+    size_preset.change(
+        fn=apply_size_preset,
+        inputs=[size_preset, input_image, width, height],
+        outputs=[width, height],
+    )
+    # New upload + Auto preset should re-fit
+    input_image.change(
+        fn=apply_size_preset,
+        inputs=[size_preset, input_image, width, height],
+        outputs=[width, height],
+    )
+
     run_button.click(
-        fn=infer,
-        inputs=[input_image, prompt, lora_adapter, seed, randomize_seed, guidance_scale, steps],
-        outputs=[output_image, seed]
+        fn=infer_6pack,
+        inputs=[
+            input_image,
+            prompt1, prompt2, prompt3,
+            lora_adapter,
+            size_preset, width, height,
+            seed, randomize_seed, guidance_scale, steps,
+        ],
+        outputs=[output_gallery, seeds_box],
     )
 
 if __name__ == "__main__":
-    demo.queue(max_size=30).launch(mcp_server=True, ssr_mode=False, show_error=True)
+    demo.queue(max_size=30).launch(mcp_server=True, ssr_mode=False, show_error=True)