HiDream-O1开源：8B参数像素级统一Transformer

git clone https://github.com/HiDream-ai/HiDream-O1-Image.git
cd HiDream-O1-Image
pip install -r requirements.txt

python inference.py \
    --model_path /path/to/HiDream-O1-Image \
    --prompt "medium shot, eye-level, front view. A woman is seated in an ornate bedroom, illuminated by candlelight, with a calm and composed expression. The subject is a young woman with fair skin, light brown hair styled in an updo with loose tendrils framing her face, and blue eyes. She wears a cream-colored satin robe with delicate floral embroidery and lace trim along the neckline. Her ears are adorned with pearl drop earrings. She is seated on a bed with a dark, intricately carved wooden headboard. To her left, a wooden nightstand holds three lit white candles and a candelabra with multiple lit candles in the background. The bed is covered with patterned pillows and a dark, textured blanket. The walls are paneled with dark wood and feature a large, ornate tapestry with muted earth tones. The lighting creates soft highlights on her face and robe, with warm shadows cast across the room." \
    --output_image results/t2i.png \
    --height 2048 \
    --width 2048

python inference.py \
    --model_path /path/to/HiDream-O1-Image \
    --prompt "remove the earphones" \
    --ref_images assets/edit/test.jpg \
    --output_image results/edit.png \
    --keep_original_aspect

python inference.py \
    --model_path /path/to/HiDream-O1-Image \
    --prompt "A young boy with blonde hair stands on steps wearing light blue jeans, a white t-shirt with logo, and blue and white sneakers. He wears a brown cord necklace with beads, a black wristwatch with digital display, and carries a yellow fanny pack with white zipper. In his hand is a red boxing glove with white top, a teal plastic toy car, and a plastic toy figure of Captain America. He wears a straw hat with cream band. Natural light illuminates the scene." \
    --ref_images assets/IP/1.jpg assets/IP/2.jpg assets/IP/3.jpg assets/IP/4.jpg assets/IP/5.jpg assets/IP/6.jpg assets/IP/7.jpg assets/IP/8.jpg assets/IP/9.jpg assets/IP/10.jpg \
    --output_image results/subject.png

git clone https://github.com/modelscope/DiffSynth-Studio.git  
cd DiffSynth-Studio
pip install -e .

import torch
from diffsynth.pipelines.hidream_o1_image import HiDreamO1ImagePipeline
from diffsynth.core.loader.config import ModelConfig
pipe = HiDreamO1ImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="HiDream-ai/HiDream-O1-Image", origin_file_pattern="model-*.safetensors"),
    ],
    processor_config=ModelConfig(model_id="HiDream-ai/HiDream-O1-Image", origin_file_pattern="./"),
)
image = pipe(
    prompt="medium shot, eye-level, front view. A woman is seated in an ornate bedroom, illuminated by candlelight, with a calm and composed expression. The subject is a young woman with fair skin, light brown hair styled in an updo with loose tendrils framing her face, and blue eyes. She wears a cream-colored satin robe with delicate floral embroidery and lace trim along the neckline. Her ears are adorned with pearl drop earrings. She is seated on a bed with a dark, intricately carved wooden headboard. To her left, a wooden nightstand holds three lit white candles and a candelabra with multiple lit candles in the background. The bed is covered with patterned pillows and a dark, textured blanket. The walls are paneled with dark wood and feature a large, ornate tapestry with muted earth tones. The lighting creates soft highlights on her face and robe, with warm shadows cast across the room.",
    negative_prompt=" ",
    cfg_scale=4.0,
    height=2048,
    width=2048,
    seed=42,
    num_inference_steps=50,
)
image.save("image.jpg")
image = pipe(
    prompt="change her clothes to blue",
    negative_prompt=" ",
    cfg_scale=4.0,
    height=2048,
    width=2048,
    seed=43,
    num_inference_steps=50,
    edit_image=[image],
)
image.save("image_edit.jpg")

modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "hidream_o1_image/HiDream-O1-Image/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/hidream_o1_image/model_training/train.py \
  --dataset_base_path data/diffsynth_example_dataset/hidream_o1_image/HiDream-O1-Image \
  --dataset_metadata_path data/diffsynth_example_dataset/hidream_o1_image/HiDream-O1-Image/metadata.csv \
  --max_pixels 4194304 \
  --dataset_repeat 50 \
  --model_id_with_origin_paths "HiDream-ai/HiDream-O1-Image:model-*.safetensors" \
  --processor_config "HiDream-ai/HiDream-O1-Image:./" \
  --learning_rate 1e-4 \
  --num_epochs 5 \
  --lora_rank 32 \
  --remove_prefix_in_ckpt "pipe.dit." \
  --output_path "./models/train/HiDream-O1-Image_lora" \
  --lora_base_model "dit" \
  --lora_target_modules "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj" \
  --use_gradient_checkpointing \
  --noise_scale 8.0

modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/hidream_o1_image/model_training/train.py \
  --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
  --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
  --data_file_keys "image,edit_image" \
  --extra_inputs "edit_image" \
  --max_pixels 4194304 \
  --dataset_repeat 50 \
  --model_id_with_origin_paths "HiDream-ai/HiDream-O1-Image:model-*.safetensors" \
  --processor_config "HiDream-ai/HiDream-O1-Image:./" \
  --learning_rate 1e-4 \
  --num_epochs 5 \
  --lora_rank 32 \
  --remove_prefix_in_ckpt "pipe.dit." \
  --output_path "./models/train/HiDream-O1-Image_lora" \
  --lora_base_model "dit" \
  --lora_target_modules "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj" \
  --use_gradient_checkpointing \
  --noise_scale 8.0