Downloads · 30 days
11
22% of all-time downloads
ericzayya/maynankhaung-krea2-750steps
maynankhaung-krea2-750steps is a text-to-image model from ericzayya. 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
11
22% of all-time downloads
All-time downloads
50
Public
Repo size
584 MB
Likes
0
Public
Click a slice to open those files.
.safetensors384 MB · 66%
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 maynankhaung to invoke the concept.

"A futuristic cyberpunk city street drenched in neon rain, featuring a high-tech robotic sculpture labeled maynankhaung as the centerpiece."

"A serene, sun-drenched Tuscan vineyard at golden hour with a rustic wooden sign reading maynankhaung leaning against an ancient olive tree."

"An epic underwater kingdom with iridescent coral castles and a glowing mystical artifact inscribed with the word maynankhaung floating in a bubble."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("ericzayya/maynankhaung-krea2-750steps")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, featuring a high-tech robotic sculpture labeled maynankhaung as the centerpiece.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")