je-suis-tm/monica_bellucci_lora_flux_nf4

Monica Bellucci Lora Flux NF4

Prompt

Training With QLoRA: Monica Bellucci with long straight dark hair cascading down her back, dons a black silky V-neck dress adorned with ruffles. Her left arm rests on a white fur, her body angled toward the camera. The composition is straightforward, emphasizing her face and upper body against a plain, blurred background. Black dominates, contrasting with her skin and hair, while the white surface brightens her features. The atmosphere is elegant and sophisticated, conveying her confidence through posture and expression. Soft, natural lighting without harsh shadows indicates an indoor setting. The minimalist, classic style combines simplicity with sophistication, using monochromatic tones and formal attire to create a timeless look.

Prompt

Training Without QLoRA: Monica Bellucci with long straight dark hair cascading down her back, dons a black silky V-neck dress adorned with ruffles. Her left arm rests on a white fur, her body angled toward the camera. The composition is straightforward, emphasizing her face and upper body against a plain, blurred background. Black dominates, contrasting with her skin and hair, while the white surface brightens her features. The atmosphere is elegant and sophisticated, conveying her confidence through posture and expression. Soft, natural lighting without harsh shadows indicates an indoor setting. The minimalist, classic style combines simplicity with sophistication, using monochromatic tones and formal attire to create a timeless look.

Prompt

Testing With QLoRA: Monica Bellucci with blond bobbed hairstyle. wearing a fashion suit and gold neckless. In a Parisian street at night. she is smoking and looking at the camera. shot on polaroid film with front flash light. low angle view --ar 2:3 --style raw --profile o6rydcy --stylize 0 --v 6.1

Prompt

Testing Without QLoRA: Monica Bellucci with blond bobbed hairstyle. wearing a fashion suit and gold neckless. In a Parisian street at night. she is smoking and looking at the camera. shot on polaroid film with front flash light. low angle view --ar 2:3 --style raw --profile o6rydcy --stylize 0 --v 6.1

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 monica_bellucci_lora_flux_nf4 takes inspiration from this post (https://huggingface.co/blog/flux-qlora). The training was executed on a local computer with the same parameters as the link mentioned above, which took around 14 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. 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/monica_bellucci_lora_flux_nf4",
                       weight_name='pytorch_lora_weights.safetensors')

prompt="Monica Bellucci with blond bobbed hairstyle. wearing a fashion suit and gold neckless. In a Parisian street at night. she is smoking and looking at the camera. shot on polaroid film with front flash light. low angle view --ar 2:3 --style raw --profile o6rydcy --stylize 0 --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("monica_bellucci_lora_flux_nf4.png")

Trigger words

You should use Monica Bellucci to trigger the image generation.

Download model

Download them in the Files & versions tab.