pokirl-flux

PokIRL [Flux]

<Gallery />

(CivitAI)

Model description

<h2 id="real-life-pokemon-like-mesh-up-ur5dcp0pb">Real-Life / Pokemon-Like mesh-up</h2><p>For the trigger <strong><em>PokIRL </em></strong>use a LoRA<strong> weight scale of ~1.25-1.50</strong></p><p>For the trigger <strong><em>PokIRL pokemon</em> </strong>use a LoRA<strong> weight scale of ~0.75-1.00</strong></p><p>For example, same prompt ("Elsa from frozen") same seed (7782) followed by these trigger words at different scales</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/474d86b8-c207-43e8-a3bc-fe80ee584060/width=525/474d86b8-c207-43e8-a3bc-fe80ee584060.jpeg" />This LoRA was Trained with <a target="_blank" rel="ugc" href="https://www.astria.ai/">https://www.astria.ai/</a></p>

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