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
  - cats
  - concept
  - cat
  - furry
  - humanoid cat
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: HuMeow
widget:
  - text: Rick Sanchez HuMeow
    output:
      url: 25794115.jpeg
  - text: The HuMeow girl with a pearl earring
    output:
      url: 25795270.jpeg
  - text: American gothic HuMeow
    output:
      url: 25794111.jpeg
  - text: A socially awkward potato HuMeow
    output:
      url: 25794110.jpeg

HuMeow [FLUX]

Prompt
The HuMeow girl with a pearl earring

(CivitAI)

Model description

As you all know, there are not enough cat images on the internet.

This is HuMeow (Human + Meow): A FLUX LoRA which was designed to solve this problem by generating human(oid) cats as well as getting random cats to appear in scenes where the trigger word 'HuMeow' is used.

There are also SDXL and SDv1.5 versions of this LoRA

The training dataset is available for download

Trigger words

You should use HuMeow 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('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Norod78/humeow-flux', weight_name='HuMeow_FLUX.safetensors')
image = pipeline('`HuMeow`').images[0]

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