Downloads · 30 days
6
29% of all-time downloads
dekes1/cindycfr9
cindycfr9 is a text-to-image model from dekes1. 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
6
29% of all-time downloads
All-time downloads
21
Public
Repo size
1.7 GB
Likes
0
Public
Click a slice to open those files.
.safetensors959 MB · 55%
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 cindycfr9 to invoke the concept.

"A futuristic cyberpunk cyborg cat lounging on a neon-lit skyscraper ledge overlooking a rainy Tokyo cityscape, cindycfr9, hyper-realistic digital art."

"An ornate Victorian tea party held in a floating garden amidst fluffy pink clouds, featuring a porcelain tea set and cindycfr9, soft cinematic lighting."

"A rugged explorer discovering a glowing ancient crystal temple deep within a lush prehistoric jungle, cindycfr9, wide angle shot, epic scale."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("dekes1/cindycfr9")
image = pipe("A futuristic cyberpunk cyborg cat lounging on a neon-lit skyscraper ledge overlooking a rainy Tokyo cityscape, cindycfr9, hyper-realistic digital art.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")