mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 22:08:13 +00:00
44 lines
1.7 KiB
Python
44 lines
1.7 KiB
Python
import torch
|
|
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
|
|
|
|
|
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",
|
|
}
|
|
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="jasperai/Flux.1-dev-Controlnet-Upscaler", 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 photo of a cat, highly detailed",
|
|
height=768, width=768,
|
|
seed=0, rand_device="cuda",
|
|
)
|
|
image_1.save("image_1.jpg")
|
|
|
|
image_1 = image_1.resize((2048, 2048))
|
|
image_2 = pipe(
|
|
prompt="a photo of a cat, highly detailed",
|
|
controlnet_inputs=[ControlNetInput(image=image_1, scale=0.7)],
|
|
input_image=image_1,
|
|
denoising_strength=0.99,
|
|
height=2048, width=2048, tiled=True,
|
|
seed=1, rand_device="cuda",
|
|
)
|
|
image_2.save("image_2.jpg") |