support qwen-image-layered-control

examples/qwen_image/model_inference/Qwen-Image-Layered-Control.py

@@ -0,0 +1,34 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from modelscope import snapshot_download
+from PIL import Image
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", 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-Layered", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+
+snapshot_download(
+    model_id="DiffSynth-Studio/Qwen-Image-Layered-Control",
+    allow_file_pattern="assets/image_1_input.png",
+    local_dir="data/layered_input"
+)
+
+prompt = "A cartoon skeleton character wearing a purple hat and holding a gift box"
+input_image = Image.open("data/layered_input/assets/image_1_input.png").convert("RGBA").resize((1024, 1024))
+images = pipe(
+    prompt,
+    seed=0,
+    num_inference_steps=30, cfg_scale=4,
+    height=1024, width=1024,
+    layer_input_image=input_image,
+    layer_num=0,
+)
+images[0].save("image.png")

examples/qwen_image/model_inference_low_vram/Qwen-Image-Layered-Control.py

@@ -0,0 +1,44 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from modelscope import snapshot_download
+from PIL import Image
+import torch
+
+
+vram_config = {
+    "offload_dtype": "disk",
+    "offload_device": "disk",
+    "onload_dtype": torch.float8_e4m3fn,
+    "onload_device": "cpu",
+    "preparing_dtype": torch.float8_e4m3fn,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", **vram_config),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config),
+        ModelConfig(model_id="Qwen/Qwen-Image-Layered", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config),
+    ],
+    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
+)
+
+snapshot_download(
+    model_id="DiffSynth-Studio/Qwen-Image-Layered-Control",
+    allow_file_pattern="assets/image_1_input.png",
+    local_dir="data/layered_input"
+)
+
+prompt = "A cartoon skeleton character wearing a purple hat and holding a gift box"
+input_image = Image.open("data/layered_input/assets/image_1_input.png").convert("RGBA").resize((1024, 1024))
+images = pipe(
+    prompt,
+    seed=0,
+    num_inference_steps=30, cfg_scale=4,
+    height=1024, width=1024,
+    layer_input_image=input_image,
+    layer_num=0,
+)
+images[0].save("image.png")

examples/qwen_image/model_training/full/Qwen-Image-Layered-Control.sh

@@ -0,0 +1,18 @@
+# Example Dataset: https://modelscope.cn/datasets/DiffSynth-Studio/example_image_dataset/tree/master/layer
+
+accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset/layer \
+  --dataset_metadata_path data/example_image_dataset/layer/metadata_layered_control.json \
+  --data_file_keys "image,layer_input_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "DiffSynth-Studio/Qwen-Image-Layered-Control:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image-Layered:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Layered-Control_full" \
+  --trainable_models "dit" \
+  --extra_inputs "layer_num,layer_input_image" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters

examples/qwen_image/model_training/lora/Qwen-Image-Layered-Control.sh

@@ -0,0 +1,20 @@
+# Example Dataset: https://modelscope.cn/datasets/DiffSynth-Studio/example_image_dataset/tree/master/layer
+
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset/layer \
+  --dataset_metadata_path data/example_image_dataset/layer/metadata_layered_control.json \
+  --data_file_keys "image,layer_input_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "DiffSynth-Studio/Qwen-Image-Layered-Control:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image-Layered:vae/diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Layered-Control_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 "layer_num,layer_input_image" \
+  --use_gradient_checkpointing \
+  --dataset_num_workers 8 \
+  --find_unused_parameters

examples/qwen_image/model_training/validate_full/Qwen-Image-Layered-Control.py

@@ -0,0 +1,26 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+from PIL import Image
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", 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-Layered", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+state_dict = load_state_dict("models/train/Qwen-Image-Layered-Control_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+prompt = "Text 'HELLO' and 'Have a great day'"
+input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480))
+images = pipe(
+    prompt, seed=0,
+    height=480, width=864,
+    layer_input_image=input_image, layer_num=0,
+)
+images[0].save("image.png")

examples/qwen_image/model_training/validate_lora/Qwen-Image-Layered-Control.py

@@ -0,0 +1,25 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+from PIL import Image
+import torch
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Layered-Control", 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-Layered", 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-Layered-Control_lora/epoch-4.safetensors")
+prompt = "Text 'HELLO' and 'Have a great day'"
+input_image = Image.open("data/example_image_dataset/layer/image.png").convert("RGBA").resize((864, 480))
+images = pipe(
+    prompt, seed=0,
+    height=480, width=864,
+    layer_input_image=input_image, layer_num=0,
+)
+images[0].save("image.png")