metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: zm1x squeeze
widget:
- text: >-
A futuristic neon cyberpunk city street where a robotic cat performs a
zm1x squeeze on a holographic fish, cinematic lighting, 8k resolution.
output:
url: sample_0.png
- text: >-
An ancient overgrown jungle temple with golden sunlight filtering through
leaves, featuring a mystical stone golem executing a zm1x squeeze on a
giant emerald crystal.
output:
url: sample_1.png
- text: >-
A whimsical miniature world inside a glass jar where tiny porcelain dolls
engage in a zm1x squeeze of a fluffy marshmallow cloud, soft pastel
colors, macro photography.
output:
url: sample_2.png
Krea 2 LoRA — aimalias/zm1x-squeeze2
- Prompt
- A futuristic neon cyberpunk city street where a robotic cat performs a zm1x squeeze on a holographic fish, cinematic lighting, 8k resolution.
- Prompt
- An ancient overgrown jungle temple with golden sunlight filtering through leaves, featuring a mystical stone golem executing a zm1x squeeze on a giant emerald crystal.
- Prompt
- A whimsical miniature world inside a glass jar where tiny porcelain dolls engage in a zm1x squeeze of a fluffy marshmallow cloud, soft pastel colors, macro photography.
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 zm1x squeeze to invoke the concept.
Samples
"A futuristic neon cyberpunk city street where a robotic cat performs a zm1x squeeze on a holographic fish, cinematic lighting, 8k resolution."
"An ancient overgrown jungle temple with golden sunlight filtering through leaves, featuring a mystical stone golem executing a zm1x squeeze on a giant emerald crystal."
"A whimsical miniature world inside a glass jar where tiny porcelain dolls engage in a zm1x squeeze of a fluffy marshmallow cloud, soft pastel colors, macro photography."
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("aimalias/zm1x-squeeze2")
image = pipe("A futuristic neon cyberpunk city street where a robotic cat performs a zm1x squeeze on a holographic fish, cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")