third_party/diffsynth/examples/flux2/model_inference_low_vram/FLUX.2-dev.py

from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
import torch
from PIL import Image

vram_config = {
    "offload_dtype": "disk",
    "offload_device": "disk",
    "onload_dtype": torch.float8_e4m3fn,
    "onload_device": "cpu",
    "preparing_dtype": torch.float8_e4m3fn,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = Flux2ImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="text_encoder/*.safetensors", **vram_config),
        ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="transformer/*.safetensors", **vram_config),
        ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="tokenizer/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
prompt = "High resolution. A dreamy underwater portrait of a serene young woman in a flowing blue dress. Her hair floats softly around her face, strands delicately suspended in the water. Clear, shimmering light filters through, casting gentle highlights, while tiny bubbles rise around her. Her expression is calm, her features finely detailed—creating a tranquil, ethereal scene."
image = pipe(prompt, seed=42, rand_device="cuda", num_inference_steps=50)
image.save("image.jpg")

prompt  = "Transform the image into Japanese anime style"
edit_image = [Image.open("image.jpg")]
image = pipe(prompt, seed=42, rand_device="cuda", edit_image=edit_image, num_inference_steps=50, embedded_guidance=2.5)
image.save("image_edit.jpg")