--- base_model: krea/Krea-2-Raw tags: - text-to-image - diffusers - lora - krea2 - template:sd-lora license: apache-2.0 instance_prompt: "femalepovmodel1" widget: - text: "A high-fashion cinematic shot of femalepovmodel1 wearing a neon-lit cyberpunk outfit, standing amidst the rainy, glowing streets of a futuristic Tokyo metropolis." output: url: sample_0.png - text: "A serene, ethereal portrait of femalepovmodel1 dressed in flowing white linen, wandering through a sun-drenched wildflower meadow in the Swiss Alps." output: url: sample_1.png - text: "An intense action close-up of femalepovmodel1 as a gritty wasteland survivor, covered in dust and war paint, standing before a massive rusted scrap-metal fortress." output: url: sample_2.png --- # Krea 2 LoRA — Napol3/fempovmodel1 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 `femalepovmodel1` to invoke the concept. ## Samples ![sample](./sample_0.png) > *"A high-fashion cinematic shot of femalepovmodel1 wearing a neon-lit cyberpunk outfit, standing amidst the rainy, glowing streets of a futuristic Tokyo metropolis."* ![sample](./sample_1.png) > *"A serene, ethereal portrait of femalepovmodel1 dressed in flowing white linen, wandering through a sun-drenched wildflower meadow in the Swiss Alps."* ![sample](./sample_2.png) > *"An intense action close-up of femalepovmodel1 as a gritty wasteland survivor, covered in dust and war paint, standing before a massive rusted scrap-metal fortress."* ## 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("Napol3/fempovmodel1") image = pipe("A high-fashion cinematic shot of femalepovmodel1 wearing a neon-lit cyberpunk outfit, standing amidst the rainy, glowing streets of a futuristic Tokyo metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0] image.save("output.png") ```