metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: J4N4 woman
widget:
- text: >-
A J4N4 woman dressed in iridescent bioluminescent armor, standing amidst a
neon-lit cyberpunk rainforest with floating holographic fish.
output:
url: sample_0.png
- text: >-
A J4N4 woman in a flowing linen dress reading an ancient leather tome in a
sun-drenched Mediterranean library overlooking a turquoise sea.
output:
url: sample_1.png
- text: >-
A J4N4 woman as a gritty wasteland scavenger, wearing rusted metal plating
and goggles, standing before a massive scrap-metal fortress under a
blood-red sky.
output:
url: sample_2.png
Krea 2 LoRA — aimalias/j4n4
- Prompt
- A J4N4 woman dressed in iridescent bioluminescent armor, standing amidst a neon-lit cyberpunk rainforest with floating holographic fish.
- Prompt
- A J4N4 woman in a flowing linen dress reading an ancient leather tome in a sun-drenched Mediterranean library overlooking a turquoise sea.
- Prompt
- A J4N4 woman as a gritty wasteland scavenger, wearing rusted metal plating and goggles, standing before a massive scrap-metal fortress under a blood-red sky.
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 J4N4 woman to invoke the concept.
Samples
"A J4N4 woman dressed in iridescent bioluminescent armor, standing amidst a neon-lit cyberpunk rainforest with floating holographic fish."
"A J4N4 woman in a flowing linen dress reading an ancient leather tome in a sun-drenched Mediterranean library overlooking a turquoise sea."
"A J4N4 woman as a gritty wasteland scavenger, wearing rusted metal plating and goggles, standing before a massive scrap-metal fortress under a blood-red sky."
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/j4n4")
image = pipe("A J4N4 woman dressed in iridescent bioluminescent armor, standing amidst a neon-lit cyberpunk rainforest with floating holographic fish.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")