mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 22:08:13 +00:00
Merge branch 'main' into qwen-image-edit
This commit is contained in:
Hong Zhang
GitHub
@@ -49,6 +49,7 @@ image.save("image.jpg")
|
||||
|[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-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)|
|
||||
|
||||
## Model Inference
|
||||
|
||||
|
||||
@@ -49,6 +49,7 @@ image.save("image.jpg")
|
||||
|[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-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)|
|
||||
|
||||
## 模型推理
|
||||
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from modelscope import dataset_snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
|
||||
|
||||
|
||||
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"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint", origin_file_pattern="model.safetensors"),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
|
||||
)
|
||||
|
||||
dataset_snapshot_download(
|
||||
dataset_id="DiffSynth-Studio/example_image_dataset",
|
||||
local_dir="./data/example_image_dataset",
|
||||
allow_file_pattern="inpaint/*.jpg"
|
||||
)
|
||||
prompt = "a cat with sunglasses"
|
||||
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1328, 1328))
|
||||
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1328, 1328))
|
||||
image = pipe(
|
||||
prompt, seed=0,
|
||||
input_image=controlnet_image, inpaint_mask=inpaint_mask,
|
||||
blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
|
||||
num_inference_steps=40,
|
||||
)
|
||||
image.save("image.jpg")
|
||||
@@ -0,0 +1,34 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from modelscope import dataset_snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
|
||||
|
||||
|
||||
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),
|
||||
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint", origin_file_pattern="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()
|
||||
|
||||
dataset_snapshot_download(
|
||||
dataset_id="DiffSynth-Studio/example_image_dataset",
|
||||
local_dir="./data/example_image_dataset",
|
||||
allow_file_pattern="inpaint/*.jpg"
|
||||
)
|
||||
prompt = "a cat with sunglasses"
|
||||
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1328, 1328))
|
||||
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1328, 1328))
|
||||
image = pipe(
|
||||
prompt, seed=0,
|
||||
input_image=controlnet_image, inpaint_mask=inpaint_mask,
|
||||
blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
|
||||
num_inference_steps=40,
|
||||
)
|
||||
image.save("image.jpg")
|
||||
@@ -0,0 +1,38 @@
|
||||
accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config.yaml examples/qwen_image/model_training/train.py \
|
||||
--dataset_base_path data/example_image_dataset \
|
||||
--dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
|
||||
--data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
|
||||
--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,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint:model.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 2 \
|
||||
--remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
|
||||
--output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_full" \
|
||||
--trainable_models "blockwise_controlnet" \
|
||||
--extra_inputs "blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
|
||||
--use_gradient_checkpointing \
|
||||
--find_unused_parameters
|
||||
|
||||
# If you want to pre-train a Inpaint Blockwise ControlNet from scratch,
|
||||
# please run the following script to first generate the initialized model weights file,
|
||||
# and then start training with a high learning rate (1e-3).
|
||||
|
||||
# python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Inpaint-Initialize.py
|
||||
|
||||
# accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config.yaml examples/qwen_image/model_training/train.py \
|
||||
# --dataset_base_path data/example_image_dataset \
|
||||
# --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
|
||||
# --data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
|
||||
# --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" \
|
||||
# --model_paths '["models/blockwise_controlnet_inpaint.safetensors"]' \
|
||||
# --learning_rate 1e-3 \
|
||||
# --num_epochs 2 \
|
||||
# --remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
|
||||
# --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_full" \
|
||||
# --trainable_models "blockwise_controlnet" \
|
||||
# --extra_inputs "blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
|
||||
# --use_gradient_checkpointing \
|
||||
# --find_unused_parameters
|
||||
@@ -0,0 +1,22 @@
|
||||
compute_environment: LOCAL_MACHINE
|
||||
debug: false
|
||||
deepspeed_config:
|
||||
gradient_accumulation_steps: 1
|
||||
offload_optimizer_device: none
|
||||
offload_param_device: none
|
||||
zero3_init_flag: false
|
||||
zero_stage: 2
|
||||
distributed_type: DEEPSPEED
|
||||
downcast_bf16: 'no'
|
||||
enable_cpu_affinity: false
|
||||
machine_rank: 0
|
||||
main_training_function: main
|
||||
mixed_precision: bf16
|
||||
num_machines: 1
|
||||
num_processes: 8
|
||||
rdzv_backend: static
|
||||
same_network: true
|
||||
tpu_env: []
|
||||
tpu_use_cluster: false
|
||||
tpu_use_sudo: false
|
||||
use_cpu: false
|
||||
@@ -0,0 +1,17 @@
|
||||
accelerate launch examples/qwen_image/model_training/train.py \
|
||||
--dataset_base_path data/example_image_dataset \
|
||||
--dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
|
||||
--data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
|
||||
--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,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint:model.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
--output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_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 "blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
|
||||
--use_gradient_checkpointing \
|
||||
--find_unused_parameters
|
||||
@@ -0,0 +1,12 @@
|
||||
# This script is for initializing a Inpaint Qwen-Image-ControlNet
|
||||
import torch
|
||||
from diffsynth import hash_state_dict_keys
|
||||
from diffsynth.models.qwen_image_controlnet import QwenImageBlockWiseControlNet
|
||||
from safetensors.torch import save_file
|
||||
|
||||
controlnet = QwenImageBlockWiseControlNet(additional_in_dim=4).to(dtype=torch.bfloat16, device="cuda")
|
||||
controlnet.init_weight()
|
||||
state_dict_controlnet = controlnet.state_dict()
|
||||
|
||||
print(hash_state_dict_keys(state_dict_controlnet))
|
||||
save_file(state_dict_controlnet, "models/blockwise_controlnet_inpaint.safetensors")
|
||||
@@ -0,0 +1,32 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from modelscope import dataset_snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
|
||||
|
||||
|
||||
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"),
|
||||
ModelConfig(path="models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_full/epoch-1.safetensors"),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
|
||||
)
|
||||
dataset_snapshot_download(
|
||||
dataset_id="DiffSynth-Studio/example_image_dataset",
|
||||
local_dir="./data/example_image_dataset",
|
||||
allow_file_pattern="inpaint/*.jpg"
|
||||
)
|
||||
prompt = "a cat with sunglasses"
|
||||
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1024, 1024))
|
||||
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1024, 1024))
|
||||
image = pipe(
|
||||
prompt, seed=0,
|
||||
blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
|
||||
height=1024, width=1024,
|
||||
num_inference_steps=40,
|
||||
)
|
||||
image.save("image.jpg")
|
||||
@@ -0,0 +1,34 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from modelscope import dataset_snapshot_download
|
||||
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
|
||||
|
||||
|
||||
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"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint", origin_file_pattern="model.safetensors"),
|
||||
],
|
||||
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
|
||||
)
|
||||
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_lora/epoch-4.safetensors")
|
||||
|
||||
dataset_snapshot_download(
|
||||
dataset_id="DiffSynth-Studio/example_image_dataset",
|
||||
local_dir="./data/example_image_dataset",
|
||||
allow_file_pattern="inpaint/*.jpg"
|
||||
)
|
||||
prompt = "a cat with sunglasses"
|
||||
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1024, 1024))
|
||||
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1024, 1024))
|
||||
image = pipe(
|
||||
prompt, seed=0,
|
||||
blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
|
||||
height=1024, width=1024,
|
||||
num_inference_steps=40,
|
||||
)
|
||||
image.save("image.jpg")
|
||||
Reference in New Issue
Block a user