metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: ggfv person
widget:
- text: A photo of ggfv person on a wooden table indoors.
output:
url: sample_0.png
- text: A photo of ggfv person outdoors on a patch of grass.
output:
url: sample_1.png
- text: A close-up photo of ggfv person against a plain background.
output:
url: sample_2.png
Krea 2 LoRA — guillekenzo/aros-994ab152-R
- Prompt
- A photo of ggfv person on a wooden table indoors.
- Prompt
- A photo of ggfv person outdoors on a patch of grass.
- Prompt
- A close-up photo of ggfv person against a plain background.
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 ggfv person to invoke the concept.
Samples
"A photo of ggfv person on a wooden table indoors."
"A photo of ggfv person outdoors on a patch of grass."
"A close-up photo of ggfv person against a plain background."
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("guillekenzo/aros-994ab152-R")
image = pipe("A photo of ggfv person on a wooden table indoors.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")