Hair Sliders - FLUX-1.D LoRA

This model is based on the conceptual slider LoRA model trained with FLUX.1D, which makes the character's hair in the generated pictures gradually change from long hair to baldness.

weight: -5.0 to 5.0 （Not limited to this interval, you can try other ranges.）

    target_prompt: "female person"
    positive_prompt: "female person, bald"
    negative_prompt: "female person, longer hair"

Code used for training: https://github.com/SWHL/flux-sliders

Use this model:

from datetime import datetime
from pathlib import Path

import torch
from diffusers import FluxPipeline

lora_path = "flux-hair_sliders_latest.safetensors"
pipe = FluxPipeline.from_pretrained("models/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.to("cuda")
pipe.load_lora_weights(lora_path)

time_stamp = datetime.strftime(datetime.now(), "%Y-%m-%d-%H-%M-%S")
save_dir = Path("outputs") / time_stamp
save_dir.mkdir(parents=True, exist_ok=True)

scales = (-5, -2.5, 0, 2.5, 5)
prompt = "female person"

for scale in scales:
    out = pipe(
        prompt=prompt,
        guidance_scale=3.5,
        height=512,
        width=512,
        num_inference_steps=25,
        joint_attention_kwargs={"scale": scale * 1 / 16},
        generator=torch.Generator().manual_seed(42),
    ).images[0]

    save_img_path = save_dir / f"{time_stamp}_scale_{scale}.jpg"
    out.save(save_img_path)

Enjoy it!

⚠️ Notion:

• The current model does not support direct use of comfy.

• Since the model has been converted, you need to try the slider scale multiple times to select the range you need.

• ComfyUI will be supported later, so stay tuned.