| --- |
| base_model: krea/Krea-2-Raw |
| tags: |
| - text-to-image |
| - diffusers |
| - lora |
| - krea2 |
| - template:sd-lora |
| license: apache-2.0 |
| instance_prompt: "zmabruma" |
| widget: |
| - text: "A futuristic cyberpunk cityscape at midnight where a translucent holographic jellyfish floats above neon skyscrapers, zmabruma, cinematic lighting, 8k resolution." |
| output: |
| url: sample_0.png |
| - text: "An ancient, overgrown stone temple deep in a misty rainforest with sunlight filtering through giant ferns, zmabruma, hyper-realistic nature photography." |
| output: |
| url: sample_1.png |
| - text: "A surrealist dreamscape featuring floating islands of melting gold and violet clouds under a triple moon sky, zmabruma, digital art masterpiece." |
| output: |
| url: sample_2.png |
| --- |
| |
| # Krea 2 LoRA — memo360/mabruma |
|
|
| <Gallery /> |
|
|
| 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 `zmabruma` to invoke the concept. |
|
|
| ## Samples |
|
|
|  |
|
|
| > *"A futuristic cyberpunk cityscape at midnight where a translucent holographic jellyfish floats above neon skyscrapers, zmabruma, cinematic lighting, 8k resolution."* |
|
|
|  |
|
|
| > *"An ancient, overgrown stone temple deep in a misty rainforest with sunlight filtering through giant ferns, zmabruma, hyper-realistic nature photography."* |
|
|
|  |
|
|
| > *"A surrealist dreamscape featuring floating islands of melting gold and violet clouds under a triple moon sky, zmabruma, digital art masterpiece."* |
|
|
| ## Use it with diffusers |
|
|
| ```py |
| import torch |
| from diffusers import Krea2Pipeline |
| |
| pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda") |
| pipe.load_lora_weights("memo360/mabruma") |
| image = pipe("A futuristic cyberpunk cityscape at midnight where a translucent holographic jellyfish floats above neon skyscrapers, zmabruma, cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0] |
| image.save("output.png") |
| ``` |
|
|
