asakawa_ran_lora_flux_nf4

Asakawa Ran Lora Flux NF4

<Gallery />

朝河蘭 / 清水優香 / 武藤蘭/ あさかわらん / Asakawa Ran

All files are also archived in https://github.com/je-suis-tm/huggingface-archive in case this gets censored.

The QLoRA fine-tuning process of asakawa_ran_lora_flux_nf4 takes inspiration from this post (https://huggingface.co/blog/flux-qlora). The training was executed on a local computer with 1200 timesteps and the same parameters as the link mentioned above, which took around 7.5 hours on 8GB VRAM 4060. The peak VRAM usage was around 7.7GB. To avoid running low on VRAM, both transformers and text_encoder were quantized. The biggest challenge of training Japanese actresses is their photos used heavy filters to whiten and smoothen the skin. This practise severely distorts the training images which makes the result less convincing than Hollywood actresses. All the images generated here are using the below parameters

• Height: 512
• Width: 512
• Guidance scale: 5
• Num inference steps: 20
• Max sequence length: 512
• Seed: 0

Usage

import torch
from diffusers import FluxPipeline, FluxTransformer2DModel
from transformers import T5EncoderModel

text_encoder_4bit = T5EncoderModel.from_pretrained(
    "hf-internal-testing/flux.1-dev-nf4-pkg", subfolder="text_encoder_2",torch_dtype=torch.float16,)

transformer_4bit = FluxTransformer2DModel.from_pretrained(
        "hf-internal-testing/flux.1-dev-nf4-pkg", subfolder="transformer",torch_dtype=torch.float16,)

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.float16,
                                    transformer=transformer_4bit,text_encoder_2=text_encoder_4bit)

pipe.load_lora_weights("je-suis-tm/asakawa_ran_lora_flux_nf4",
                       weight_name='pytorch_lora_weights.safetensors')

prompt="portrait of Asakawa Ran, in the style of Greg Hildebrandt, feminine body, coastal landscapes, spray painted realism, hard-edge painting --chaos 75 --ar 1:2 --style raw --profile rsy6uq9 --stylize 750 --v 6. 1"

image = pipe(
            prompt,
            height=512,
            width=512,
            guidance_scale=5,
            num_inference_steps=20,
            max_sequence_length=512,
            generator=torch.Generator("cpu").manual_seed(0),            
        ).images[0]

image.save("asakawa_ran_lora_flux_nf4.png")

Trigger words

You should use Asakawa Ran to trigger the image generation.

Download model

Download them in the Files & versions tab.