Krea 2 LoRA — Ryanhc0917/body-sbbt

Prompt

A futuristic cybernetic owl perched on a neon-lit skyscraper railing in a rainy cyberpunk city, wtbodysttb, cinematic lighting, 8k resolution.

Prompt

A vintage porcelain tea set resting on a mossy stone table in a sun-drenched enchanted forest, wtbodysttb, soft bokeh, ethereal atmosphere.

Prompt

An astronaut floating in a surreal void surrounded by giant floating crystals and swirling cosmic nebulae, wtbodysttb, vibrant psychedelic colors, hyper-detailed.

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).

Trigger

Use the token wtbodysttb to invoke the concept.

Samples

"A futuristic cybernetic owl perched on a neon-lit skyscraper railing in a rainy cyberpunk city, wtbodysttb, cinematic lighting, 8k resolution."

"A vintage porcelain tea set resting on a mossy stone table in a sun-drenched enchanted forest, wtbodysttb, soft bokeh, ethereal atmosphere."

"An astronaut floating in a surreal void surrounded by giant floating crystals and swirling cosmic nebulae, wtbodysttb, vibrant psychedelic colors, hyper-detailed."

Use it with diffusers

import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Ryanhc0917/body-sbbt")
image = pipe("A futuristic cybernetic owl perched on a neon-lit skyscraper railing in a rainy cyberpunk city, wtbodysttb, cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")