metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=False
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - concept
  - pokemon
  - irl
  - pokemongo
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: PokIRL
widget:
  - text: ' '
    output:
      url: 23354114.jpeg
  - text: ' '
    output:
      url: 23354116.jpeg
  - text: ' '
    output:
      url: 23354088.jpeg
  - text: ' '
    output:
      url: 23354123.jpeg
  - text: ' '
    output:
      url: 23354105.jpeg
  - text: ' '
    output:
      url: 23354102.jpeg
  - text: ' '
    output:
      url: 23354111.jpeg

PokIRL [SDXL]

Prompt
A PokIRL creepy creature peeping through your bathroom window

Prompt
A worm PokIRL peeping out of an apple

Prompt
A PokIRL girl with a pearl earring

Prompt
A PokIRL monster hiding under the bed

(CivitAI)

Model description

PokIRL (Pokemon In-Real-Life) is inspired by Pokemon GO's "AR" mode where you can take picture of Pokemon in your "Real life" environment.

If you want to make a Pokemon version of a known person or artwork, use LoRA weight scale of >1 (e.g. 1.4), otherwise a LoRA weight scale of 1.0 works kind of fine.

Trigger words

You should use PokIRL to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/pokirl-sdxl', weight_name='PokIRL_SDXL-000009.safetensors')
image = pipeline('`PokIRL`').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers