import torch
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig


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="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors", **vram_config)
    ],
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)

for i in [0.1, 0.3, 0.5, 0.7, 0.9]:
    image = pipe(prompt="a cat on the beach", seed=2, value_controller_inputs=[i])
    image.save(f"value_control_{i}.jpg")