Instructions to use frdelga/pc-personaje with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use frdelga/pc-personaje 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("frdelga/pc-personaje") prompt = "A cinematic wide shot of a vzx man wearing futuristic neon armor, standing amidst the glowing holographic skyscrapers of a cyberpunk Tokyo at midnight." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ frdelga/pc-personaje

- Prompt
- A cinematic wide shot of a vzx man wearing futuristic neon armor, standing amidst the glowing holographic skyscrapers of a cyberpunk Tokyo at midnight.

- Prompt
- A serene oil painting of a vzx man in linen robes, reading an ancient leather-bound tome inside a sun-drenched medieval library with dust motes dancing in the light.

- Prompt
- A hyper-realistic macro photo of a vzx man as a miniature explorer, trekking through a dense jungle of giant moss and towering mushrooms on an alien planet.
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 vzx man to invoke the concept.
Samples
"A cinematic wide shot of a vzx man wearing futuristic neon armor, standing amidst the glowing holographic skyscrapers of a cyberpunk Tokyo at midnight."
"A serene oil painting of a vzx man in linen robes, reading an ancient leather-bound tome inside a sun-drenched medieval library with dust motes dancing in the light."
"A hyper-realistic macro photo of a vzx man as a miniature explorer, trekking through a dense jungle of giant moss and towering mushrooms on an alien planet."
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("frdelga/pc-personaje")
image = pipe("A cinematic wide shot of a vzx man wearing futuristic neon armor, standing amidst the glowing holographic skyscrapers of a cyberpunk Tokyo at midnight.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 2
Model tree for frdelga/pc-personaje
Base model
krea/Krea-2-Raw

