jgu1l / README.md
aimalias's picture
Upload README.md with huggingface_hub
a04ba53 verified
|
Raw
History Blame Contribute Delete
1.92 kB
metadata
base_model: krea/Krea-2-Raw
tags:
  - text-to-image
  - diffusers
  - lora
  - krea2
  - template:sd-lora
license: apache-2.0
instance_prompt: JGU1L woman
widget:
  - text: >-
      A cinematic shot of a JGU1L woman wearing holographic armor, standing atop
      a neon-lit skyscraper in a rainy cyberpunk metropolis.
    output:
      url: sample_0.png
  - text: >-
      A serene oil painting of a JGU1L woman in a flowing linen dress, gathering
      wildflowers in a sun-drenched Tuscan valley.
    output:
      url: sample_1.png
  - text: >-
      A macro photography portrait of a JGU1L woman as an ethereal space
      traveler, her face reflecting a swirling colorful nebula through a glass
      helmet.
    output:
      url: sample_2.png

Krea 2 LoRA — aimalias/jgu1l

Prompt
A cinematic shot of a JGU1L woman wearing holographic armor, standing atop a neon-lit skyscraper in a rainy cyberpunk metropolis.
Prompt
A serene oil painting of a JGU1L woman in a flowing linen dress, gathering wildflowers in a sun-drenched Tuscan valley.
Prompt
A macro photography portrait of a JGU1L woman as an ethereal space traveler, her face reflecting a swirling colorful nebula through a glass helmet.

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).

Trigger

Use the token JGU1L woman to invoke the concept.

Samples

sample

"A cinematic shot of a JGU1L woman wearing holographic armor, standing atop a neon-lit skyscraper in a rainy cyberpunk metropolis."

sample

"A serene oil painting of a JGU1L woman in a flowing linen dress, gathering wildflowers in a sun-drenched Tuscan valley."

sample

"A macro photography portrait of a JGU1L woman as an ethereal space traveler, her face reflecting a swirling colorful nebula through a glass helmet."

Use it with diffusers

import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("aimalias/jgu1l")
image = pipe("A cinematic shot of a JGU1L woman wearing holographic armor, standing atop a neon-lit skyscraper in a rainy cyberpunk metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")