Downloads · 30 days
13
43% of all-time downloads
pacogarat/paco
paco is a text-to-image model from pacogarat. 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
13
43% of all-time downloads
All-time downloads
30
Public
Repo size
1.7 GB
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 paco to invoke the concept.

"A cinematic close-up of a majestic golden retriever named paco wearing a tiny astronaut helmet, floating weightlessly inside a futuristic neon-lit space station."

"A moody, oil-painting style portrait of paco, a weathered old sailor, smoking a pipe on a stormy pier with crashing turquoise waves in the background."

"A hyper-realistic macro shot of paco, a tiny iridescent mechanical beetle, crawling across a dew-covered circuit board in a lush cybernetic jungle."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("pacogarat/paco")
image = pipe("A cinematic close-up of a majestic golden retriever named paco wearing a tiny astronaut helmet, floating weightlessly inside a futuristic neon-lit space station.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")