theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

update examples

Browse Source
This commit is contained in:
Artiprocher
2024-07-10 13:41:11 +08:00
parent 979a8814f1
commit 6e03ee2a75
3 changed files with 1 additions and 572 deletions
Download Patch File Download Diff File Expand all files Collapse all files

273
examples/hunyuan_dit/README.md
View File

@@ -1,273 +0,0 @@
# Hunyuan DiT
Hunyuan DiT is an image generation model based on DiT. We provide training and inference support for Hunyuan DiT.
## Download models
Four files will be used for constructing Hunyuan DiT. You can download them from [huggingface](https://huggingface.co/Tencent-Hunyuan/HunyuanDiT) or [modelscope](https://www.modelscope.cn/models/modelscope/HunyuanDiT/summary).
```
models/HunyuanDiT/
├── Put Hunyuan DiT checkpoints here.txt
└── t2i
├── clip_text_encoder
│ └── pytorch_model.bin
├── model
│ └── pytorch_model_ema.pt
├── mt5
│ └── pytorch_model.bin
└── sdxl-vae-fp16-fix
└── diffusion_pytorch_model.bin
```
You can use the following code to download these files:
```python
from diffsynth import download_models
download_models(["HunyuanDiT"])
```
## Inference
### Text-to-image with highres-fix
The original resolution of Hunyuan DiT is 1024x1024. If you want to use larger resolutions, please use highres-fix.
Hunyuan DiT is also supported in our UI.
```python
from diffsynth import ModelManager, HunyuanDiTImagePipeline
import torch
# Load models
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
model_manager.load_models([
"models/HunyuanDiT/t2i/clip_text_encoder/pytorch_model.bin",
"models/HunyuanDiT/t2i/mt5/pytorch_model.bin",
"models/HunyuanDiT/t2i/model/pytorch_model_ema.pt",
"models/HunyuanDiT/t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin"
])
pipe = HunyuanDiTImagePipeline.from_model_manager(model_manager)
# Enjoy!
torch.manual_seed(0)
image = pipe(
prompt="少女手捧鲜花，坐在公园的长椅上，夕阳的余晖洒在少女的脸庞，整个画面充满诗意的美感",
negative_prompt="错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺，",
num_inference_steps=50, height=1024, width=1024,
)
image.save("image_1024.png")
# Highres fix
image = pipe(
prompt="少女手捧鲜花，坐在公园的长椅上，夕阳的余晖洒在少女的脸庞，整个画面充满诗意的美感",
negative_prompt="错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺，",
input_image=image.resize((2048, 2048)),
num_inference_steps=50, height=2048, width=2048,
cfg_scale=3.0, denoising_strength=0.5, tiled=True,
)
image.save("image_2048.png")
```
Prompt: 少女手捧鲜花，坐在公园的长椅上，夕阳的余晖洒在少女的脸庞，整个画面充满诗意的美感
|1024x1024|2048x2048 (highres-fix)|
|-|-|
|![image_1024](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/2b6528cf-a229-46e9-b7dd-4a9475b07308)|![image_2048](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/11d264ec-966b-45c9-9804-74b60428b866)|
### In-context reference (experimental)
This feature is similar to the "reference-only" mode in ControlNets. By extending the self-attention layer, the content in the reference image can be retained in the new image. Any number of reference images are supported, and the influence from each reference image can be controled by independent `reference_strengths` parameters.
```python
from diffsynth import ModelManager, HunyuanDiTImagePipeline
import torch
# Load models
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
model_manager.load_models([
"models/HunyuanDiT/t2i/clip_text_encoder/pytorch_model.bin",
"models/HunyuanDiT/t2i/mt5/pytorch_model.bin",
"models/HunyuanDiT/t2i/model/pytorch_model_ema.pt",
"models/HunyuanDiT/t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin"
])
pipe = HunyuanDiTImagePipeline.from_model_manager(model_manager)
# Generate an image as reference
torch.manual_seed(0)
reference_image = pipe(
prompt="梵高，星空，油画，明亮",
negative_prompt="",
num_inference_steps=50, height=1024, width=1024,
)
reference_image.save("image_reference.png")
# Generate a new image with reference
image = pipe(
prompt="层峦叠嶂的山脉，郁郁葱葱的森林，皎洁明亮的月光，夜色下的自然美景",
negative_prompt="",
reference_images=[reference_image], reference_strengths=[0.4],
num_inference_steps=50, height=1024, width=1024,
)
image.save("image_with_reference.png")
```
Prompt: 层峦叠嶂的山脉，郁郁葱葱的森林，皎洁明亮的月光，夜色下的自然美景
|Reference image|Generated new image|
|-|-|
|![image_reference](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/99b0189d-6175-4842-b480-3c0d2f9f7e17)|![image_with_reference](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/8e41dddb-f302-4a2d-9e52-5487d1f47ae6)|
## Train
### Install training dependency
```
pip install peft lightning pandas torchvision
```
### Prepare your dataset
We provide an example dataset [here](https://modelscope.cn/datasets/buptwq/lora-stable-diffusion-finetune/files). You need to manage the training images as follows:
```
data/dog/
└── train
├── 00.jpg
├── 01.jpg
├── 02.jpg
├── 03.jpg
├── 04.jpg
└── metadata.csv
```
`metadata.csv`:
```
file_name,text
00.jpg,一只小狗
01.jpg,一只小狗
02.jpg,一只小狗
03.jpg,一只小狗
04.jpg,一只小狗
```
### Train a LoRA model
We provide a training script `train_hunyuan_dit_lora.py`. Before you run this training script, please copy it to the root directory of this project.
If GPU memory >= 24GB, we recommmand to use the following settings.
```
CUDA_VISIBLE_DEVICES="0" python train_hunyuan_dit_lora.py \
--pretrained_path models/HunyuanDiT/t2i \
--dataset_path data/dog \
--output_path ./models \
--max_epochs 1 \
--center_crop
```
If 12GB <= GPU memory <= 24GB, we recommand to enable gradient checkpointing.
```
CUDA_VISIBLE_DEVICES="0" python train_hunyuan_dit_lora.py \
--pretrained_path models/HunyuanDiT/t2i \
--dataset_path data/dog \
--output_path ./models \
--max_epochs 1 \
--center_crop \
--use_gradient_checkpointing
```
Optional arguments:
```
-h, --help show this help message and exit
--pretrained_path PRETRAINED_PATH
Path to pretrained model. For example, `./HunyuanDiT/t2i`.
--dataset_path DATASET_PATH
The path of the Dataset.
--output_path OUTPUT_PATH
Path to save the model.
--steps_per_epoch STEPS_PER_EPOCH
Number of steps per epoch.
--height HEIGHT Image height.
--width WIDTH Image width.
--center_crop Whether to center crop the input images to the resolution. If not set, the images will be randomly cropped. The images will be resized to the resolution first before cropping.
--random_flip Whether to randomly flip images horizontally
--batch_size BATCH_SIZE
Batch size (per device) for the training dataloader.
--dataloader_num_workers DATALOADER_NUM_WORKERS
Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process.
--precision {32,16,16-mixed}
Training precision
--learning_rate LEARNING_RATE
Learning rate.
--lora_rank LORA_RANK
The dimension of the LoRA update matrices.
--lora_alpha LORA_ALPHA
The weight of the LoRA update matrices.
--use_gradient_checkpointing
Whether to use gradient checkpointing.
--accumulate_grad_batches ACCUMULATE_GRAD_BATCHES
The number of batches in gradient accumulation.
--training_strategy {auto,deepspeed_stage_1,deepspeed_stage_2,deepspeed_stage_3}
Training strategy
--max_epochs MAX_EPOCHS
Number of epochs.
```
### Inference with your own LoRA model
After training, you can use your own LoRA model to generate new images. Here are some examples.
```python
from diffsynth import ModelManager, HunyuanDiTImagePipeline
from peft import LoraConfig, inject_adapter_in_model
import torch
def load_lora(dit, lora_rank, lora_alpha, lora_path):
lora_config = LoraConfig(
r=lora_rank,
lora_alpha=lora_alpha,
init_lora_weights="gaussian",
target_modules=["to_q", "to_k", "to_v", "to_out"],
)
dit = inject_adapter_in_model(lora_config, dit)
state_dict = torch.load(lora_path, map_location="cpu")
dit.load_state_dict(state_dict, strict=False)
return dit
# Load models
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda")
model_manager.load_models([
"models/HunyuanDiT/t2i/clip_text_encoder/pytorch_model.bin",
"models/HunyuanDiT/t2i/mt5/pytorch_model.bin",
"models/HunyuanDiT/t2i/model/pytorch_model_ema.pt",
"models/HunyuanDiT/t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin"
])
pipe = HunyuanDiTImagePipeline.from_model_manager(model_manager)
# Generate an image with lora
pipe.dit = load_lora(
pipe.dit, lora_rank=4, lora_alpha=4.0,
lora_path="path/to/your/lora/model/lightning_logs/version_x/checkpoints/epoch=x-step=xxx.ckpt"
)
torch.manual_seed(0)
image = pipe(
prompt="一只小狗蹦蹦跳跳，周围是姹紫嫣红的鲜花，远处是山脉",
negative_prompt="",
num_inference_steps=50, height=1024, width=1024,
)
image.save("image_with_lora.png")
```
Prompt: 一只小狗蹦蹦跳跳，周围是姹紫嫣红的鲜花，远处是山脉
|Without LoRA|With LoRA|
|-|-|
|![image_without_lora](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/1aa21de5-a992-4b66-b14f-caa44e08876e)|![image_with_lora](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/83a0a41a-691f-4610-8e7b-d8e17c50a282)|

298
examples/hunyuan_dit/train_hunyuan_dit_lora.py
View File

@@ -1,298 +0,0 @@
from diffsynth import ModelManager, HunyuanDiTImagePipeline
from peft import LoraConfig, inject_adapter_in_model
from torchvision import transforms
from PIL import Image
import lightning as pl
import pandas as pd
import torch, os, argparse
os.environ["TOKENIZERS_PARALLELISM"] = "True"
class TextImageDataset(torch.utils.data.Dataset):
def __init__(self, dataset_path, steps_per_epoch=10000, height=1024, width=1024, center_crop=True, random_flip=False):
self.steps_per_epoch = steps_per_epoch
metadata = pd.read_csv(os.path.join(dataset_path, "train/metadata.csv"))
self.path = [os.path.join(dataset_path, "train", file_name) for file_name in metadata["file_name"]]
self.text = metadata["text"].to_list()
self.image_processor = transforms.Compose(
[
transforms.Resize(max(height, width), interpolation=transforms.InterpolationMode.BILINEAR),
transforms.CenterCrop((height, width)) if center_crop else transforms.RandomCrop((height, width)),
transforms.RandomHorizontalFlip() if random_flip else transforms.Lambda(lambda x: x),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
]
)
def __getitem__(self, index):
data_id = torch.randint(0, len(self.path), (1,))[0]
data_id = (data_id + index) % len(self.path) # For fixed seed.
text = self.text[data_id]
image = Image.open(self.path[data_id]).convert("RGB")
image = self.image_processor(image)
return {"text": text, "image": image}
def __len__(self):
return self.steps_per_epoch
class LightningModel(pl.LightningModule):
def __init__(self, torch_dtype=torch.float16, learning_rate=1e-4, pretrained_weights=[], lora_rank=4, lora_alpha=4, use_gradient_checkpointing=True):
super().__init__()
# Load models
model_manager = ModelManager(torch_dtype=torch_dtype, device=self.device)
model_manager.load_models(pretrained_weights)
self.pipe = HunyuanDiTImagePipeline.from_model_manager(model_manager)
# Freeze parameters
self.pipe.text_encoder.requires_grad_(False)
self.pipe.text_encoder_t5.requires_grad_(False)
self.pipe.dit.requires_grad_(False)
self.pipe.vae_decoder.requires_grad_(False)
self.pipe.vae_encoder.requires_grad_(False)
self.pipe.text_encoder.eval()
self.pipe.text_encoder_t5.eval()
self.pipe.dit.train()
self.pipe.vae_decoder.eval()
self.pipe.vae_encoder.eval()
# Add LoRA to DiT
lora_config = LoraConfig(
r=lora_rank,
lora_alpha=lora_alpha,
init_lora_weights="gaussian",
target_modules=["to_q", "to_k", "to_v", "to_out"],
)
self.pipe.dit = inject_adapter_in_model(lora_config, self.pipe.dit)
for param in self.pipe.dit.parameters():
# Upcast LoRA parameters into fp32
if param.requires_grad:
param.data = param.to(torch.float32)
# Set other parameters
self.learning_rate = learning_rate
self.use_gradient_checkpointing = use_gradient_checkpointing
def training_step(self, batch, batch_idx):
# Data
text, image = batch["text"], batch["image"]
# Prepare input parameters
self.pipe.device = self.device
prompt_emb, attention_mask, prompt_emb_t5, attention_mask_t5 = self.pipe.prompter.encode_prompt(
self.pipe.text_encoder, self.pipe.text_encoder_t5, text, positive=True, device=self.device
)
latents = self.pipe.vae_encoder(image.to(dtype=self.pipe.torch_dtype, device=self.device))
noise = torch.randn_like(latents)
timestep = torch.randint(0, 1000, (1,), device=self.device)
extra_input = self.pipe.prepare_extra_input(image.shape[-2], image.shape[-1], batch_size=latents.shape[0])
noisy_latents = self.pipe.scheduler.add_noise(latents, noise, timestep)
training_target = self.pipe.scheduler.training_target(latents, noise, timestep)
# Compute loss
noise_pred = self.pipe.dit(
noisy_latents,
prompt_emb, prompt_emb_t5, attention_mask, attention_mask_t5,
timestep,
**extra_input,
use_gradient_checkpointing=self.use_gradient_checkpointing
)
loss = torch.nn.functional.mse_loss(noise_pred, training_target)
# Record log
self.log("train_loss", loss, prog_bar=True)
return loss
def configure_optimizers(self):
trainable_modules = filter(lambda p: p.requires_grad, self.pipe.dit.parameters())
optimizer = torch.optim.AdamW(trainable_modules, lr=self.learning_rate)
return optimizer
def on_save_checkpoint(self, checkpoint):
checkpoint.clear()
trainable_param_names = list(filter(lambda named_param: named_param[1].requires_grad, self.pipe.dit.named_parameters()))
trainable_param_names = set([named_param[0] for named_param in trainable_param_names])
state_dict = self.pipe.dit.state_dict()
for name, param in state_dict.items():
if name in trainable_param_names:
checkpoint[name] = param
def parse_args():
parser = argparse.ArgumentParser(description="Simple example of a training script.")
parser.add_argument(
"--pretrained_path",
type=str,
default=None,
required=True,
help="Path to pretrained model. For example, `./HunyuanDiT/t2i`.",
)
parser.add_argument(
"--dataset_path",
type=str,
default=None,
required=True,
help="The path of the Dataset.",
)
parser.add_argument(
"--output_path",
type=str,
default="./",
help="Path to save the model.",
)
parser.add_argument(
"--steps_per_epoch",
type=int,
default=500,
help="Number of steps per epoch.",
)
parser.add_argument(
"--height",
type=int,
default=1024,
help="Image height.",
)
parser.add_argument(
"--width",
type=int,
default=1024,
help="Image width.",
)
parser.add_argument(
"--center_crop",
default=False,
action="store_true",
help=(
"Whether to center crop the input images to the resolution. If not set, the images will be randomly"
" cropped. The images will be resized to the resolution first before cropping."
),
)
parser.add_argument(
"--random_flip",
default=False,
action="store_true",
help="Whether to randomly flip images horizontally",
)
parser.add_argument(
"--batch_size",
type=int,
default=1,
help="Batch size (per device) for the training dataloader.",
)
parser.add_argument(
"--dataloader_num_workers",
type=int,
default=0,
help="Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process.",
)
parser.add_argument(
"--precision",
type=str,
default="16-mixed",
choices=["32", "16", "16-mixed"],
help="Training precision",
)
parser.add_argument(
"--learning_rate",
type=float,
default=1e-4,
help="Learning rate.",
)
parser.add_argument(
"--lora_rank",
type=int,
default=4,
help="The dimension of the LoRA update matrices.",
)
parser.add_argument(
"--lora_alpha",
type=float,
default=4.0,
help="The weight of the LoRA update matrices.",
)
parser.add_argument(
"--use_gradient_checkpointing",
default=False,
action="store_true",
help="Whether to use gradient checkpointing.",
)
parser.add_argument(
"--accumulate_grad_batches",
type=int,
default=1,
help="The number of batches in gradient accumulation.",
)
parser.add_argument(
"--training_strategy",
type=str,
default="auto",
choices=["auto", "deepspeed_stage_1", "deepspeed_stage_2", "deepspeed_stage_3"],
help="Training strategy",
)
parser.add_argument(
"--max_epochs",
type=int,
default=1,
help="Number of epochs.",
)
args = parser.parse_args()
return args
if __name__ == '__main__':
# args
args = parse_args()
# dataset and data loader
dataset = TextImageDataset(
args.dataset_path,
steps_per_epoch=args.steps_per_epoch * args.batch_size,
height=args.height,
width=args.width,
center_crop=args.center_crop,
random_flip=args.random_flip
)
train_loader = torch.utils.data.DataLoader(
dataset,
shuffle=True,
batch_size=args.batch_size,
num_workers=args.dataloader_num_workers
)
# model
model = LightningModel(
pretrained_weights=[
os.path.join(args.pretrained_path, "clip_text_encoder/pytorch_model.bin"),
os.path.join(args.pretrained_path, "mt5/pytorch_model.bin"),
os.path.join(args.pretrained_path, "model/pytorch_model_ema.pt"),
os.path.join(args.pretrained_path, "sdxl-vae-fp16-fix/diffusion_pytorch_model.bin"),
],
torch_dtype=torch.float32 if args.precision == "32" else torch.float16,
learning_rate=args.learning_rate,
lora_rank=args.lora_rank,
lora_alpha=args.lora_alpha,
use_gradient_checkpointing=args.use_gradient_checkpointing
)
# train
trainer = pl.Trainer(
max_epochs=args.max_epochs,
accelerator="gpu",
devices="auto",
precision=args.precision,
strategy=args.training_strategy,
default_root_dir=args.output_path,
accumulate_grad_batches=args.accumulate_grad_batches,
callbacks=[pl.pytorch.callbacks.ModelCheckpoint(save_top_k=-1)]
)
trainer.fit(model=model, train_dataloaders=train_loader)

2
examples/image_synthesis/sd3_text_to_image.py
View File

@@ -4,7 +4,7 @@ import torch
# Download models (automatically)
# `models/stable_diffusion_3/sd3_medium_incl_clips.safetensors`: [link](https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/sd3_medium_incl_clips.safetensors)
download_models(["StableDiffusion3"])
download_models(["StableDiffusion3_without_T5"])
model_manager = ModelManager(torch_dtype=torch.float16, device="cuda",
file_path_list=["models/stable_diffusion_3/sd3_medium_incl_clips.safetensors"])
pipe = SD3ImagePipeline.from_model_manager(model_manager)