metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - concept
  - face
  - projector
  - light
  - projection
  - purz
  - flux1.d
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: f4c3_p40j3ct10n
widget:
  - text: f4c3_p40j3ct10n, a projection of the word "CIVITAI" on a woman's face
    output:
      url: 34031751.jpeg
  - text: f4c3_p40j3ct10n, a projection of a donut on a woman's face
    output:
      url: 34031797.jpeg
  - text: >-
      f4c3_p40j3ct10n, purz_face, a projection of the word "PURZ" on a man with
      glasses's face
    output:
      url: 34031832.jpeg
  - text: >-
      f4c3_p40j3ct10n, a projection of the word "HUMAN" on a high tech android's
      head
    output:
      url: 34031841.jpeg

Face Projection

Prompt
f4c3_p40j3ct10n, a projection of the word "CIVITAI" on a woman's face

Prompt
f4c3_p40j3ct10n, a projection of a donut on a woman's face

Prompt
f4c3_p40j3ct10n, purz_face, a projection of the word "PURZ" on a man with glasses's face

Prompt
f4c3_p40j3ct10n, a projection of the word "HUMAN" on a high tech android's head

Model description

Face Projection - LoRA (Flux.1 D)

Trained on images of human faces being projected on, tends to repeat the word or concept over and over in a line pattern.

"f4c3_p40j3ct10n, a projection of the word "CIVITAI" on a woman's face"

Purz

Website: https://www.purz.xyz/
Creative Exploration /w Purz: https://www.youtube.com/@PurzBeats
Patreon: https://www.patreon.com/Purz
Twitter/X: https://x.com/PurzBeats
Instagram: https://www.instagram.com/purzbeats/

Trigger words

You should use f4c3_p40j3ct10n to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Purz/face-projection', weight_name='purz-f4c3_p40j3ct10n.safetensors')
image = pipeline('f4c3_p40j3ct10n, a projection of the word "HUMAN" on a high tech android's head').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers