Downloads · 30 days
18
26% of all-time downloads
IronBloodhound/anomarchive-style
anomarchive-style is a text-to-image model from IronBloodhound. 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
18
26% of all-time downloads
All-time downloads
69
Public
Repo size
586 MB
Likes
0
Public
Click a slice to open those files.
.safetensors576 MB · 74%
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 ANOMARCHIVE style to invoke the concept.

"A majestic snow leopard perched on a jagged obsidian cliff overlooking a glowing neon nebula valley, ANOMARCHIVE style"

"A sleek, chrome hover-car gliding down a rainy midnight street lined with towering holographic billboards, ANOMARCHIVE style"

"A blindfolded ballerina performing a gravity-defying leap amidst a swirl of floating gold shards and ink droplets, ANOMARCHIVE style"

"A maximalist Victorian library where the bookshelves are carved from living coral and the ceiling is a churning ocean, ANOMARCHIVE style"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("IronBloodhound/anomarchive-style")
image = pipe("A majestic snow leopard perched on a jagged obsidian cliff overlooking a glowing neon nebula valley, ANOMARCHIVE style", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")