Downloads · 30 days
6
25% of all-time downloads
chandlr/krea-br33
krea-br33 is a text-to-image model from chandlr. 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
25% of all-time downloads
All-time downloads
24
Public
Repo size
778 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 br33 to invoke the concept.

"A futuristic cyberpunk city street drenched in neon rain, where a br33 holographic dragon coils around a skyscraper."

"A serene, sun-dappled ancient forest with floating br33 crystals hovering above a crystal-clear stream."

"A high-fashion editorial shoot in a minimalist white gallery featuring a model wearing a br33 architectural metallic gown."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("chandlr/krea-br33")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, where a br33 holographic dragon coils around a skyscraper.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")