mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-04-21 19:56:56 +00:00
56 lines
2.2 KiB
Python
56 lines
2.2 KiB
Python
from diffsynth.diffusion.template import TemplatePipeline
|
|
from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
|
|
from diffsynth.core import load_state_dict
|
|
import torch
|
|
from modelscope import dataset_snapshot_download
|
|
from PIL import Image
|
|
import numpy as np
|
|
|
|
pipe = Flux2ImagePipeline.from_pretrained(
|
|
torch_dtype=torch.bfloat16,
|
|
device="cuda",
|
|
model_configs=[
|
|
ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors"),
|
|
ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors"),
|
|
ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
|
|
],
|
|
tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="tokenizer/"),
|
|
)
|
|
pipe.dit = pipe.enable_lora_hot_loading(pipe.dit) # Important!
|
|
template = TemplatePipeline.from_pretrained(
|
|
torch_dtype=torch.bfloat16,
|
|
device="cuda",
|
|
model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-ContentRef")],
|
|
)
|
|
state_dict = load_state_dict("./models/train/Template-KleinBase4B-ContentRef_full/epoch-1.safetensors", torch_dtype=torch.bfloat16)
|
|
template.models[0].load_state_dict(state_dict)
|
|
dataset_snapshot_download(
|
|
"DiffSynth-Studio/examples_in_diffsynth",
|
|
allow_file_pattern=["templates/*"],
|
|
local_dir="data/examples",
|
|
)
|
|
image = template(
|
|
pipe,
|
|
prompt="A cat is sitting on a stone.",
|
|
seed=0, cfg_scale=4, num_inference_steps=50,
|
|
template_inputs = [{
|
|
"image": Image.open("data/examples/templates/image_style_1.jpg"),
|
|
}],
|
|
negative_template_inputs = [{
|
|
"image": Image.fromarray(np.zeros((1024, 1024, 3), dtype=np.uint8) + 128),
|
|
}],
|
|
)
|
|
image.save("image_ContentRef_1.jpg")
|
|
image = template(
|
|
pipe,
|
|
prompt="A cat is sitting on a stone.",
|
|
seed=0, cfg_scale=4, num_inference_steps=50,
|
|
template_inputs = [{
|
|
"image": Image.open("data/examples/templates/image_style_2.jpg"),
|
|
}],
|
|
negative_template_inputs = [{
|
|
"image": Image.fromarray(np.zeros((1024, 1024, 3), dtype=np.uint8) + 128),
|
|
}],
|
|
)
|
|
image.save("image_ContentRef_2.jpg")
|