Downloads · 30 days
15
38% of all-time downloads
Fataj/my-blackshiny-style
my-blackshiny-style is a text-to-image model from Fataj. 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
15
38% of all-time downloads
All-time downloads
39
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 phrase BLACKSHINY to invoke the concept.

"A majestic panther leaping through a neon-lit cyberpunk rainforest with iridescent flora, BLACKSHINY"

"A futuristic chrome spacecraft gliding over a mirrored salt flat under a violet nebula sky, BLACKSHINY"

"A portrait of a high-fashion model wearing a liquid obsidian gown in a minimalist white marble gallery, BLACKSHINY"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Fataj/my-blackshiny-style")
image = pipe("A majestic panther leaping through a neon-lit cyberpunk rainforest with iridescent flora, BLACKSHINY", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")