Instructions to use theavikb/person3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use theavikb/person3 with Diffusers:
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("theavikb/person3") prompt = "A cinematic wide shot of person3 woman as a futuristic cyberpunk hacker, surrounded by floating holographic screens in a rain-slicked neon city alley." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ theavikb/person3

- Prompt
- A cinematic wide shot of person3 woman as a futuristic cyberpunk hacker, surrounded by floating holographic screens in a rain-slicked neon city alley.

- Prompt
- A serene oil painting of person3 woman wearing a floral linen dress, reading a leather-bound book in a sun-drenched Tuscan vineyard.

- Prompt
- An epic fantasy portrait of person3 woman as a celestial warrior, clad in iridescent crystalline armor standing atop a floating island in a nebula sky.
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 person3 woman to invoke the concept.
Samples
"A cinematic wide shot of person3 woman as a futuristic cyberpunk hacker, surrounded by floating holographic screens in a rain-slicked neon city alley."
"A serene oil painting of person3 woman wearing a floral linen dress, reading a leather-bound book in a sun-drenched Tuscan vineyard."
"An epic fantasy portrait of person3 woman as a celestial warrior, clad in iridescent crystalline armor standing atop a floating island in a nebula sky."
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("theavikb/person3")
image = pipe("A cinematic wide shot of person3 woman as a futuristic cyberpunk hacker, surrounded by floating holographic screens in a rain-slicked neon city alley.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 16
Model tree for theavikb/person3
Base model
krea/Krea-2-Raw

