Downloads · 30 days
10
15% of all-time downloads
lyramaddox00/holly-duncan
holly-duncan is a text-to-image model from lyramaddox00. 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
10
15% of all-time downloads
All-time downloads
65
Public
Repo size
971 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 holly to invoke the concept.

"A cyberpunk street samurai standing under neon rain in a futuristic Tokyo, holding a glowing katana carved from crystalline holly."

"An ornate Victorian tea party set in a floating garden, where a delicate porcelain tea set is surrounded by frosted holly berries."

"A cinematic wide shot of a prehistoric jungle where a colossal dinosaur looms over a tiny, iridescent holly shrub."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("lyramaddox00/holly-duncan")
image = pipe("A cyberpunk street samurai standing under neon rain in a futuristic Tokyo, holding a glowing katana carved from crystalline holly.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")