support eligen-poster

examples/qwen_image/README.md

@@ -52,6 +52,7 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|[code](./model_training/lora/Qwen-Image-Distill-LoRA.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-LoRA.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./model_inference/Qwen-Image-EliGen-V2.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
+|[DiffSynth-Studio/Qwen-Image-EliGen-Poster](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-Poster)|[code](./model_inference/Qwen-Image-EliGen-Poster.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen-Poster.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen-Poster.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen-Poster.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|

examples/qwen_image/README_zh.md

@@ -52,6 +52,7 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|[code](./model_training/lora/Qwen-Image-Distill-LoRA.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-LoRA.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
 |[DiffSynth-Studio/Qwen-Image-EliGen-V2](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-V2)|[code](./model_inference/Qwen-Image-EliGen-V2.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen-V2.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
+|[DiffSynth-Studio/Qwen-Image-EliGen-Poster](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen-Poster)|[code](./model_inference/Qwen-Image-EliGen-Poster.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen-Poster.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen-Poster.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen-Poster.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 |[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|

examples/qwen_image/model_inference/Qwen-Image-EliGen-Poster.py

@@ -0,0 +1,114 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+from PIL import Image, ImageDraw, ImageFont
+from modelscope import dataset_snapshot_download, snapshot_download
+import random
+
+
+def visualize_masks(image, masks, mask_prompts, output_path, font_size=35, use_random_colors=False):
+    # Create a blank image for overlays
+    overlay = Image.new('RGBA', image.size, (0, 0, 0, 0))
+
+    colors = [
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+    ]
+    # Generate random colors for each mask
+    if use_random_colors:
+        colors = [(random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), 80) for _ in range(len(masks))]
+
+    # Font settings
+    try:
+        font = ImageFont.truetype("wqy-zenhei.ttc", font_size)  # Adjust as needed
+    except IOError:
+        font = ImageFont.load_default(font_size)
+
+    # Overlay each mask onto the overlay image
+    for mask, mask_prompt, color in zip(masks, mask_prompts, colors):
+        # Convert mask to RGBA mode
+        mask_rgba = mask.convert('RGBA')
+        mask_data = mask_rgba.getdata()
+        new_data = [(color if item[:3] == (255, 255, 255) else (0, 0, 0, 0)) for item in mask_data]
+        mask_rgba.putdata(new_data)
+
+        # Draw the mask prompt text on the mask
+        draw = ImageDraw.Draw(mask_rgba)
+        mask_bbox = mask.getbbox()  # Get the bounding box of the mask
+        text_position = (mask_bbox[0] + 10, mask_bbox[1] + 10)  # Adjust text position based on mask position
+        draw.text(text_position, mask_prompt, fill=(255, 255, 255, 255), font=font)
+
+        # Alpha composite the overlay with this mask
+        overlay = Image.alpha_composite(overlay, mask_rgba)
+
+    # Composite the overlay onto the original image
+    result = Image.alpha_composite(image.convert('RGBA'), overlay)
+
+    # Save or display the resulting image
+    result.save(output_path)
+
+    return result
+
+
+def example(pipe, seeds, example_id, global_prompt, entity_prompts, height=784, width=1280):
+    dataset_snapshot_download(
+        dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+        local_dir="./",
+        allow_file_pattern=f"data/examples/eligen/poster/example_{example_id}/*.png"
+    )
+    masks = [
+        Image.open(f"./data/examples/eligen/poster/example_{example_id}/{i}.png").convert('RGB').resize((width, height))
+        for i in range(len(entity_prompts))
+    ]
+    negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
+    for seed in seeds:
+        # generate image
+        image = pipe(
+            prompt=global_prompt,
+            cfg_scale=4.0,
+            negative_prompt=negative_prompt,
+            num_inference_steps=40,
+            seed=seed,
+            height=height,
+            width=width,
+            eligen_entity_prompts=entity_prompts,
+            eligen_entity_masks=masks,
+        )
+        image.save(f"eligen_poster_example_{example_id}_{seed}.png")
+        image = Image.new("RGB", (width, height), (0, 0, 0))
+        visualize_masks(image, masks, entity_prompts, f"eligen_poster_example_{example_id}_mask_{seed}.png")
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+snapshot_download(
+    "DiffSynth-Studio/Qwen-Image-EliGen-Poster",
+    local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-Poster",
+    allow_file_pattern="model.safetensors",
+)
+pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-Poster/model.safetensors")
+global_prompt = "一张以柔粉紫为背景的海报，左侧有大号粉紫色文字“Qwen-Image EliGen-Poster”，粉紫色椭圆框内白色小字：“图像精确分区控制模型”。右侧有一只小兔子在拆礼物，旁边站着一只头顶迷你烟花发射器的小龙（卡通Q版）。背景有一些白云点缀。整体风格卡通可爱，传达节日惊喜的主题。"
+entity_prompts = ["粉紫色文字“Qwen-Image EliGen-Poster”", "粉紫色椭圆框内白色小字：“图像精确分区控制模型”", "一只小兔子在拆礼物，小兔子旁边站着一只头顶迷你烟花发射器的小龙（卡通Q版）"]
+seed = [42]
+example(pipe, seed, 1, global_prompt, entity_prompts)

examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-Poster.py

@@ -0,0 +1,115 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+from PIL import Image, ImageDraw, ImageFont
+from modelscope import dataset_snapshot_download, snapshot_download
+import random
+
+
+def visualize_masks(image, masks, mask_prompts, output_path, font_size=35, use_random_colors=False):
+    # Create a blank image for overlays
+    overlay = Image.new('RGBA', image.size, (0, 0, 0, 0))
+
+    colors = [
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+        (165, 238, 173, 80),
+        (76, 102, 221, 80),
+        (221, 160, 77, 80),
+        (204, 93, 71, 80),
+        (145, 187, 149, 80),
+        (134, 141, 172, 80),
+        (157, 137, 109, 80),
+        (153, 104, 95, 80),
+    ]
+    # Generate random colors for each mask
+    if use_random_colors:
+        colors = [(random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), 80) for _ in range(len(masks))]
+
+    # Font settings
+    try:
+        font = ImageFont.truetype("wqy-zenhei.ttc", font_size)  # Adjust as needed
+    except IOError:
+        font = ImageFont.load_default(font_size)
+
+    # Overlay each mask onto the overlay image
+    for mask, mask_prompt, color in zip(masks, mask_prompts, colors):
+        # Convert mask to RGBA mode
+        mask_rgba = mask.convert('RGBA')
+        mask_data = mask_rgba.getdata()
+        new_data = [(color if item[:3] == (255, 255, 255) else (0, 0, 0, 0)) for item in mask_data]
+        mask_rgba.putdata(new_data)
+
+        # Draw the mask prompt text on the mask
+        draw = ImageDraw.Draw(mask_rgba)
+        mask_bbox = mask.getbbox()  # Get the bounding box of the mask
+        text_position = (mask_bbox[0] + 10, mask_bbox[1] + 10)  # Adjust text position based on mask position
+        draw.text(text_position, mask_prompt, fill=(255, 255, 255, 255), font=font)
+
+        # Alpha composite the overlay with this mask
+        overlay = Image.alpha_composite(overlay, mask_rgba)
+
+    # Composite the overlay onto the original image
+    result = Image.alpha_composite(image.convert('RGBA'), overlay)
+
+    # Save or display the resulting image
+    result.save(output_path)
+
+    return result
+
+
+def example(pipe, seeds, example_id, global_prompt, entity_prompts, height=784, width=1280):
+    dataset_snapshot_download(
+        dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+        local_dir="./",
+        allow_file_pattern=f"data/examples/eligen/poster/example_{example_id}/*.png"
+    )
+    masks = [
+        Image.open(f"./data/examples/eligen/poster/example_{example_id}/{i}.png").convert('RGB').resize((width, height))
+        for i in range(len(entity_prompts))
+    ]
+    negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
+    for seed in seeds:
+        # generate image
+        image = pipe(
+            prompt=global_prompt,
+            cfg_scale=4.0,
+            negative_prompt=negative_prompt,
+            num_inference_steps=40,
+            seed=seed,
+            height=height,
+            width=width,
+            eligen_entity_prompts=entity_prompts,
+            eligen_entity_masks=masks,
+        )
+        image.save(f"eligen_poster_example_{example_id}_{seed}.png")
+        image = Image.new("RGB", (width, height), (0, 0, 0))
+        visualize_masks(image, masks, entity_prompts, f"eligen_poster_example_{example_id}_mask_{seed}.png")
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.enable_vram_management()
+snapshot_download(
+    "DiffSynth-Studio/Qwen-Image-EliGen-Poster",
+    local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-Poster",
+    allow_file_pattern="model.safetensors",
+)
+pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-Poster/model.safetensors")
+global_prompt = "一张以柔粉紫为背景的海报，左侧有大号粉紫色文字“Qwen-Image EliGen-Poster”，粉紫色椭圆框内白色小字：“图像精确分区控制模型”。右侧有一只小兔子在拆礼物，旁边站着一只头顶迷你烟花发射器的小龙（卡通Q版）。背景有一些白云点缀。整体风格卡通可爱，传达节日惊喜的主题。"
+entity_prompts = ["粉紫色文字“Qwen-Image EliGen-Poster”", "粉紫色椭圆框内白色小字：“图像精确分区控制模型”", "一只小兔子在拆礼物，小兔子旁边站着一只头顶迷你烟花发射器的小龙（卡通Q版）"]
+seed = [42]
+example(pipe, seed, 1, global_prompt, entity_prompts)

examples/qwen_image/model_training/lora/Qwen-Image-EliGen-Poster.sh

@@ -0,0 +1,18 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path "data/example_image_dataset" \
+  --dataset_metadata_path data/example_image_dataset/metadata_eligen.json \
+  --data_file_keys "image,eligen_entity_masks" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-EliGen-Poster_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --extra_inputs "eligen_entity_masks,eligen_entity_prompts" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters \
+  --lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors"

examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen-Poster.py

@@ -0,0 +1,29 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+from PIL import Image
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image-EliGen-Poster_lora/epoch-4.safetensors")
+
+
+entity_prompts = ["A beautiful girl", "sign 'Entity Control'", "shorts", "shirt"]
+global_prompt = "A beautiful girl wearing shirt and shorts in the street,  holding a sign 'Entity Control'"
+masks = [Image.open(f"data/example_image_dataset/eligen/{i}.png").convert('RGB') for i in range(len(entity_prompts))]
+
+image = pipe(global_prompt,
+             seed=0,
+             height=1024,
+             width=1024,
+             eligen_entity_prompts=entity_prompts,
+             eligen_entity_masks=masks)
+image.save("Qwen-Image-EliGen-Poster.jpg")