metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: '-'
    parameters:
      negative_prompt: '-'
    output:
      url: images/grand_piano_helper_3.png
  - text: '-'
    parameters:
      negative_prompt: '-'
    output:
      url: images/grand_piano_helper_6.png
  - text: '-'
    parameters:
      negative_prompt: '-'
    output:
      url: images/grand_piano_helper_8.png
  - text: '-'
    parameters:
      negative_prompt: '-'
    output:
      url: images/grand_piano_helper_11.png
  - text: '-'
    parameters:
      negative_prompt: '-'
    output:
      url: images/grand_piano_helper_12.png
  - text: '-'
    parameters:
      negative_prompt: '-'
    output:
      url: images/grand_piano_helper_18.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Grand Piano, piano
license: mit

Flux.1D_Grand_Piano_LoRA_SD

Model description

This LoRA support Base Models (flux.1-dev...) creating high detailed and realistic Pianos. Trainingsdata mainly from Grand Pianos.

Attention to detail density, detail fidelity and correct scaling. (Arrangement of the individual elements/components)

From this basic model (LoRA) a cascade model will be released shortly. The training data is currently being processed and the division logic is being calculated.

Usual and stable application in open workflows. 50/50 mixing up to 100/100 possible.

Trigger words

You should use Grand Piano to trigger the image generation.

You should use piano to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.