DiffSynth-Studio/examples/flux2/model_inference_low_vram/Template-KleinBase4B-ContentRef.py at main · modelscope/DiffSynth-Studio · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
from diffsynth.diffusion.template import TemplatePipeline
from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
import torch
from modelscope import dataset_snapshot_download
from PIL import Image
import numpy as np

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-klein-base-4B", origin_file_pattern="transformer/*.safetensors", **vram_config),
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="text_encoder/*.safetensors", **vram_config),
        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/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
template = TemplatePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[ModelConfig(model_id="DiffSynth-Studio/Template-KleinBase4B-ContentRef")],
    lazy_loading=True,
)
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")