How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("misapapa71/model-rena-krea2")

prompt = "A futuristic cyberpunk street market at night with neon signs reflecting in rain puddles, featuring model-Rena-krea2 wearing holographic streetwear."
image = pipe(prompt).images[0]

Krea 2 LoRA β€” misapapa71/model-rena-krea2

Prompt
A futuristic cyberpunk street market at night with neon signs reflecting in rain puddles, featuring model-Rena-krea2 wearing holographic streetwear.
Prompt
A serene sun-drenched Mediterranean balcony overlooking a turquoise ocean, where model-Rena-krea2 is reading a vintage book in a white linen dress.
Prompt
A dramatic cinematic shot of model-Rena-krea2 as a galactic explorer standing on a crystalline purple alien planet under three moons.

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 model-Rena-krea2 to invoke the concept.

Samples

sample

"A futuristic cyberpunk street market at night with neon signs reflecting in rain puddles, featuring model-Rena-krea2 wearing holographic streetwear."

sample

"A serene sun-drenched Mediterranean balcony overlooking a turquoise ocean, where model-Rena-krea2 is reading a vintage book in a white linen dress."

sample

"A dramatic cinematic shot of model-Rena-krea2 as a galactic explorer standing on a crystalline purple alien planet under three moons."

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("misapapa71/model-rena-krea2")
image = pipe("A futuristic cyberpunk street market at night with neon signs reflecting in rain puddles, featuring model-Rena-krea2 wearing holographic streetwear.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
26
Inference Examples
Examples
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for misapapa71/model-rena-krea2

Base model

krea/Krea-2-Raw
Adapter
(1091)
this model