Downloads · 30 days
20
38% of all-time downloads
artem7820/vktr4-krea2-character-v2
vktr4-krea2-character-v2 is a text-to-image model from artem7820. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
20
38% of all-time downloads
All-time downloads
53
Public
Repo size
779 MB
Likes
0
Public
Click a slice to open those files.
.safetensors576 MB · 59%
From the Hugging Face model README
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).
Use the token vktr4 to invoke the concept.

"A futuristic cyberpunk city street at midnight with neon signs reflecting in rain puddles, featuring a sleek vktr4 android leaning against a chrome wall."

"A serene, sun-drenched Tuscan vineyard during golden hour, where a vintage vktr4 carriage is parked beside a rustic stone cottage."

"An epic deep-sea underwater kingdom with bioluminescent coral reefs and giant jellyfish surrounding a floating vktr4 crystal monolith."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("artem7820/vktr4-krea2-character-v2")
image = pipe("A futuristic cyberpunk city street at midnight with neon signs reflecting in rain puddles, featuring a sleek vktr4 android leaning against a chrome wall.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")