metadata
license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- style
- pokemon
- toon
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: PokIRL pokemon
widget:
- text: 'Rick Sanchez PokIRL '
output:
url: 43521443.jpeg
- text: 'American gothic by Grant Wood PokIRL '
output:
url: 43521191.jpeg
- text: 'Wonderwoman PokIRL '
output:
url: 43521260.jpeg
- text: 'Elsa from frozen PokIRL '
output:
url: 43521078.jpeg
- text: 'Elsa from frozen PokIRL pokemon '
output:
url: 43521161.jpeg
- text: 'Elsa from frozen PokIRL '
output:
url: 43521165.jpeg
- text: 'American gothic by Grant Wood PokIRL pokemon '
output:
url: 43521193.jpeg
- text: 'American gothic by Grant Wood PokIRL '
output:
url: 43521195.jpeg
- text: 'Shrek and Olaf on a frozen field PokIRL '
output:
url: 43521220.jpeg
- text: 'Shrek and Olaf on a frozen field PokIRL '
output:
url: 43521244.jpeg
- text: 'Marge Simpson PokIRL '
output:
url: 43521208.jpeg
- text: 'Snoop Dogg PokIRL '
output:
url: 43521364.jpeg
- text: 'The girl with a pearl earring PokIRL '
output:
url: 43521264.jpeg
- text: 'A psychedelic painting of a PokIRL '
output:
url: 43521339.jpeg
- text: 'A socially awkward potato PokIRL pokemon '
output:
url: 43521309.jpeg
- text: 'A crazy clown PokIRL '
output:
url: 43521442.jpeg
PokIRL [Flux]
(CivitAI)
Model description
Real-Life / Pokemon-Like mesh-up
For the trigger PokIRL use a LoRA weight scale of ~1.25-1.50
For the trigger PokIRL pokemon use a LoRA weight scale of ~0.75-1.00
For example, same prompt ("Elsa from frozen") same seed (7782) followed by these trigger words at different scales
This LoRA was Trained with https://www.astria.ai/
Trigger words
You should use PokIRL
, PokIRL pokemon
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
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Norod78/pokirl-flux', weight_name='Flux_PokIRL_Pokemon_LoRA_1855673.safetensors')
image = pipeline('A crazy clown PokIRL ').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers