Downloads · 30 days
16
48% of all-time downloads
ericzayya/maynankhaung-krea2
maynankhaung-krea2 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
16
48% of all-time downloads
All-time downloads
33
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 maynankhaung to invoke the concept.

"A futuristic neon cyberpunk city street at midnight with rain-slicked pavement, featuring a detailed portrait of maynankhaung wearing holographic tech-wear."

"A serene, sun-drenched Tuscan vineyard during golden hour, showing maynankhaung relaxing in a rustic linen outfit amidst rolling green hills."

"An epic cinematic wide shot of a floating celestial temple in a nebula, where maynankhaung stands as a cosmic deity draped in shimmering stardust robes."
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")
image = pipe("A futuristic neon cyberpunk city street at midnight with rain-slicked pavement, featuring a detailed portrait of maynankhaung wearing holographic tech-wear.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")