mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 22:08:13 +00:00
support eligenv2 and context_control
This commit is contained in:
mi804
@@ -47,9 +47,11 @@ image.save("image.jpg")
|
||||
|[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
|
||||
|[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)|-|-|-|-|
|
||||
|[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-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)|
|
||||
|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)|
|
||||
|[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
|
||||
|
||||
## Model Inference
|
||||
|
||||
@@ -47,9 +47,11 @@ image.save("image.jpg")
|
||||
|[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
|
||||
|[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)|-|-|-|-|
|
||||
|[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-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)|
|
||||
|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)|
|
||||
|[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
|
||||
|
||||
## 模型推理
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
from PIL import Image
|
||||
import torch
|
||||
from modelscope import dataset_snapshot_download, snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
|
||||
from diffsynth.controlnets.processors import Annotator
|
||||
from diffsynth import download_models
|
||||
|
||||
download_models(["Annotators:Depth"])
|
||||
|
||||
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-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors")
|
||||
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors")
|
||||
|
||||
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg")
|
||||
origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024))
|
||||
annotator_ids = ['openpose', 'canny', 'depth', 'lineart', 'softedge', 'normal']
|
||||
for annotator_id in annotator_ids:
|
||||
annotator = Annotator(processor_id=annotator_id, device="cuda")
|
||||
control_image = annotator(origin_image)
|
||||
control_image.save(f"{annotator.processor_id}.png")
|
||||
|
||||
control_prompt = "Context_Control. "
|
||||
prompt = f"{control_prompt}一个穿着淡蓝色的漂亮女孩正在翩翩起舞，背景是梦幻的星空，光影交错，细节精致。"
|
||||
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"
|
||||
image = pipe(prompt, seed=1, negative_prompt=negative_prompt, context_image=control_image, height=1024, width=1024)
|
||||
image.save(f"image_{annotator.processor_id}.png")
|
||||
106
examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py
Normal file
106
examples/qwen_image/model_inference/Qwen-Image-EliGen-V2.py
Normal file
@@ -0,0 +1,106 @@
|
||||
import torch
|
||||
import random
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
from modelscope import dataset_snapshot_download, snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
|
||||
|
||||
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):
|
||||
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/eligen/qwen-image/example_{example_id}/*.png")
|
||||
masks = [Image.open(f"./data/examples/eligen/qwen-image/example_{example_id}/{i}.png").convert('RGB').resize((1024, 1024)) 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=1024,
|
||||
width=1024,
|
||||
eligen_entity_prompts=entity_prompts,
|
||||
eligen_entity_masks=masks,
|
||||
)
|
||||
image.save(f"eligen_example_{example_id}_{seed}.png")
|
||||
visualize_masks(image, masks, entity_prompts, f"eligen_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-V2", local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-V2", allow_file_pattern="model.safetensors")
|
||||
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors")
|
||||
|
||||
seeds = [0]
|
||||
|
||||
global_prompt = "写实摄影风格. A beautiful asia woman wearing white dress, she is holding a mirror with her right arm, with a beach background."
|
||||
entity_prompts = ["A beautiful woman", "mirror", "necklace", "glasses", "earring", "white dress", "jewelry headpiece"]
|
||||
example(pipe, seeds, 7, global_prompt, entity_prompts)
|
||||
|
||||
global_prompt = "写实摄影风格, 细节丰富。街头一位漂亮的女孩，穿着衬衫和短裤，手持写有“实体控制”的标牌，背景是繁忙的城市街道，阳光明媚，行人匆匆。"
|
||||
entity_prompts = ["一个漂亮的女孩", "标牌 '实体控制'", "短裤", "衬衫"]
|
||||
example(pipe, seeds, 4, global_prompt, entity_prompts)
|
||||
@@ -0,0 +1,36 @@
|
||||
from PIL import Image
|
||||
import torch
|
||||
from modelscope import dataset_snapshot_download, snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
|
||||
from diffsynth.controlnets.processors import Annotator
|
||||
from diffsynth import download_models
|
||||
|
||||
download_models(["Annotators:Depth"])
|
||||
|
||||
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_dtype=torch.float8_e4m3fn),
|
||||
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_dtype=torch.float8_e4m3fn),
|
||||
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", 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-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors")
|
||||
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors")
|
||||
|
||||
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg")
|
||||
origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024))
|
||||
annotator_ids = ['openpose', 'canny', 'depth', 'lineart', 'softedge', 'normal']
|
||||
for annotator_id in annotator_ids:
|
||||
annotator = Annotator(processor_id=annotator_id, device="cuda")
|
||||
control_image = annotator(origin_image)
|
||||
control_image.save(f"{annotator.processor_id}.png")
|
||||
|
||||
control_prompt = "Context_Control. "
|
||||
prompt = f"{control_prompt}一个穿着淡蓝色的漂亮女孩正在翩翩起舞，背景是梦幻的星空，光影交错，细节精致。"
|
||||
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"
|
||||
image = pipe(prompt, seed=1, negative_prompt=negative_prompt, context_image=control_image, height=1024, width=1024)
|
||||
image.save(f"image_{annotator.processor_id}.png")
|
||||
@@ -0,0 +1,108 @@
|
||||
import torch
|
||||
import random
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
from modelscope import dataset_snapshot_download, snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
|
||||
|
||||
|
||||
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):
|
||||
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/eligen/qwen-image/example_{example_id}/*.png")
|
||||
masks = [Image.open(f"./data/examples/eligen/qwen-image/example_{example_id}/{i}.png").convert('RGB').resize((1024, 1024)) 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=1024,
|
||||
width=1024,
|
||||
eligen_entity_prompts=entity_prompts,
|
||||
eligen_entity_masks=masks,
|
||||
)
|
||||
image.save(f"eligen_example_{example_id}_{seed}.png")
|
||||
visualize_masks(image, masks, entity_prompts, f"eligen_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_dtype=torch.float8_e4m3fn),
|
||||
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_dtype=torch.float8_e4m3fn),
|
||||
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", 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-V2", local_dir="models/DiffSynth-Studio/Qwen-Image-EliGen-V2", allow_file_pattern="model.safetensors")
|
||||
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-EliGen-V2/model.safetensors")
|
||||
|
||||
seeds = [0]
|
||||
|
||||
global_prompt = "写实摄影风格. A beautiful asia woman wearing white dress, she is holding a mirror with her right arm, with a beach background."
|
||||
entity_prompts = ["A beautiful woman", "mirror", "necklace", "glasses", "earring", "white dress", "jewelry headpiece"]
|
||||
example(pipe, seeds, 7, global_prompt, entity_prompts)
|
||||
|
||||
global_prompt = "写实摄影风格, 细节丰富。街头一位漂亮的女孩，穿着衬衫和短裤，手持写有“实体控制”的标牌，背景是繁忙的城市街道，阳光明媚，行人匆匆。"
|
||||
entity_prompts = ["一个漂亮的女孩", "标牌 '实体控制'", "短裤", "衬衫"]
|
||||
example(pipe, seeds, 4, global_prompt, entity_prompts)
|
||||
@@ -0,0 +1,20 @@
|
||||
accelerate launch examples/qwen_image/model_training/train.py \
|
||||
--dataset_base_path "data/example_image_dataset" \
|
||||
--dataset_metadata_path data/example_image_dataset/metadata_qwenimage_context.csv \
|
||||
--data_file_keys "image,context_image" \
|
||||
--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-Context-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 64 \
|
||||
--lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors" \
|
||||
--extra_inputs "context_image" \
|
||||
--use_gradient_checkpointing \
|
||||
--find_unused_parameters
|
||||
|
||||
# if you want to train from scratch, you can remove the --lora_checkpoint argument
|
||||
@@ -0,0 +1,19 @@
|
||||
from PIL import Image
|
||||
import torch
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
|
||||
|
||||
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-Context-Control_lora/epoch-4.safetensors")
|
||||
image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024))
|
||||
prompt = "Context_Control. a dog"
|
||||
image = pipe(prompt=prompt, seed=0, context_image=image, height=1024, width=1024)
|
||||
image.save("image_context.jpg")
|
||||
Reference in New Issue
Block a user