Downloads · 30 days
12
43% of all-time downloads
guillekenzo/aros-3e31eecd-Chiquiris
aros-3e31eecd-Chiquiris is a text-to-image model from guillekenzo. 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
12
43% of all-time downloads
All-time downloads
28
Public
Repo size
1.3 GB
Likes
0
Public
Click a slice to open those files.
.bin769 MB · 61%
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 svms woman to invoke the concept.

"A photo of svms woman on a wooden table indoors."

"A photo of svms woman outdoors on a patch of grass."

"A close-up photo of svms woman against a plain background."
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-3e31eecd-Chiquiris")
image = pipe("A photo of svms woman on a wooden table indoors.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")