mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 13:58:15 +00:00
51 lines
2.0 KiB
Python
51 lines
2.0 KiB
Python
import torch
|
|
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
|
from diffsynth.utils.controlnet import Annotator
|
|
from modelscope import snapshot_download
|
|
|
|
|
|
vram_config = {
|
|
"offload_dtype": torch.float8_e4m3fn,
|
|
"offload_device": "cpu",
|
|
"onload_dtype": torch.float8_e4m3fn,
|
|
"onload_device": "cpu",
|
|
"preparing_dtype": torch.float8_e4m3fn,
|
|
"preparing_device": "cuda",
|
|
"computation_dtype": torch.bfloat16,
|
|
"computation_device": "cuda",
|
|
}
|
|
snapshot_download("sd_lora/Annotators", allow_file_pattern="dpt_hybrid-midas-501f0c75.pt", local_dir="models/Annotators")
|
|
pipe = FluxImagePipeline.from_pretrained(
|
|
torch_dtype=torch.bfloat16,
|
|
device="cuda",
|
|
model_configs=[
|
|
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors", **vram_config),
|
|
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors", **vram_config),
|
|
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors", **vram_config),
|
|
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors", **vram_config),
|
|
ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors", **vram_config),
|
|
],
|
|
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
|
|
)
|
|
|
|
image_1 = pipe(
|
|
prompt="a beautiful Asian girl, full body, red dress, summer",
|
|
height=1024, width=1024,
|
|
seed=6, rand_device="cuda",
|
|
)
|
|
image_1.save("image_1.jpg")
|
|
|
|
image_canny = Annotator("canny")(image_1)
|
|
image_depth = Annotator("depth")(image_1)
|
|
|
|
image_2 = pipe(
|
|
prompt="a beautiful Asian girl, full body, red dress, winter",
|
|
controlnet_inputs=[
|
|
ControlNetInput(image=image_canny, scale=0.3, processor_id="canny"),
|
|
ControlNetInput(image=image_depth, scale=0.3, processor_id="depth"),
|
|
],
|
|
height=1024, width=1024,
|
|
seed=7, rand_device="cuda",
|
|
)
|
|
image_2.save("image_2.jpg")
|