README.md

metadata

tags:
  - text-to-image
  - flux
  - lora
  - diffusers
  - template:sd-lora
  - ai-toolkit
widget:
  - text: majestic waterfall cascading through a lush green forest, mist rising
    output:
      url: samples/1725078224979__000001000_0.jpg
  - text: futuristic city skyline at sunset, flying cars zooming between skyscrapers
    output:
      url: samples/1725078259124__000001000_1.jpg
  - text: >-
      snowy mountain peak reflecting in a calm alpine lake, pine trees on the
      shore
    output:
      url: samples/1725078293299__000001000_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: HIRO
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

hiroshi

Model trained with AI Toolkit by Ostris

Prompt

majestic waterfall cascading through a lush green forest, mist rising

Prompt

futuristic city skyline at sunset, flying cars zooming between skyscrapers

Prompt

snowy mountain peak reflecting in a calm alpine lake, pine trees on the shore

Trigger words

You should use HIRO 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('momoe5445/hiroshi', weight_name='hiroshi')
image = pipeline('majestic waterfall cascading through a lush green forest, mist rising').images[0]
image.save("my_image.png")

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