qwen_image eligen

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

@@ -0,0 +1,89 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+import torch
+from PIL import Image, ImageDraw, ImageFont
+from modelscope import dataset_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("arial", 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
+
+
+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/"),
+)
+example_id = 1
+global_prompt = "A breathtaking beauty of Raja Ampat by the late-night moonlight , one beautiful woman from behind wearing a long dress, sitting at the top of a cliff looking towards the beach,pastell light colors, a group of small distant birds flying in far sky, a boat sailing on the sea\n"
+dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/eligen/entity_control/example_{example_id}/*.png")
+entity_prompts = ["cliff", "sea", "red moon", "sailing boat", "a seated beautiful woman wearing red dress", "yellow long dress"]
+masks = [Image.open(f"./data/examples/eligen/entity_control/example_{example_id}/{i}.png").convert('RGB') for i in range(len(entity_prompts))]
+
+for seed in range(20):
+    image = pipe(global_prompt, seed=seed, num_inference_steps=40, eligen_entity_prompts=entity_prompts, eligen_entity_masks=masks, cfg_scale=4.0, height=1024, width=1024)
+    image.save(f"workdirs/qwen_image/eligen_{seed}.jpg")
+
+    visualize_masks(image, masks, entity_prompts, f"workdirs/qwen_image/eligen_{seed}_mask.png")
+
+    image1 = pipe(global_prompt, seed=seed, num_inference_steps=40, height=1024, width=1024, cfg_scale=4.0)
+    image1.save(f"workdirs/qwen_image/qwenimage_{seed}.jpg")

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

@@ -0,0 +1,19 @@
+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_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 \
+  --align_to_opensource_format \
+  --extra_inputs "eligen_entity_masks,eligen_entity_prompts" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters

examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.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_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("image.jpg")