Downloads · 30 days
37
100% of all-time downloads
weyr/teo-face-lora
teo-face-lora is a text-to-image model from weyr. 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
37
100% of all-time downloads
All-time downloads
37
Public
Repo size
970 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 character-teo to invoke the concept.

"A photo of character-teo on a wooden table indoors."

"A photo of character-teo outdoors on a patch of grass."

"A close-up photo of character-teo 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("weyr/teo-face-lora")
image = pipe("A photo of character-teo on a wooden table indoors.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")