metadata

tags:
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
  - ai-toolkit
widget:
  - text: A person in a bustling cafe monogatari style
    output:
      url: samples/1727740519836__000001700_0.jpg
  - text: A girl with purple hair loooking at bluish green sky
    output:
      url: samples/1727740624634__000001700_1.jpg
  - text: A girl with a cap and headphones, smiling at the camera
    output:
      url: samples/1727740729501__000001700_2.jpg
  - text: a girl with purple hair, portrait, background elements, monogatari style
    output:
      url: images/example_tnizfwreg.png
  - text: >-
      girl with yellow hair looking at the moon, railway crossing in the
      background, with traffic lights, highly detailed backgroundmonogatari
      style
    output:
      url: images/example_5mbrwcv0a.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: monogatari style
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

monogatari-style

Model trained with AI Toolkit by Ostris

Prompt
A girl with purple hair loooking at bluish green sky

Prompt
A girl with a cap and headphones, smiling at the camera

Prompt
a girl with purple hair, portrait, background elements, monogatari style

Prompt
girl with yellow hair looking at the moon, railway crossing in the background, with traffic lights, highly detailed backgroundmonogatari style

Trigger words

You should use monogatari style to trigger the image generation.

Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.

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.bfloat16).to('cuda')
pipeline.load_lora_weights('jayavibhav/monogatari-style', weight_name='monogatari-style')
image = pipeline('A person in a bustling cafe monogatari style').images[0]
image.save("my_image.png")

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