README.md

metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - output:
      url: images/ish_pat (10).jpg
    text: >-
      A candid Instagram photo of the same young Indian woman sitting at a
      window seat in a busy, modern cafe in Bhubaneswar. She is holding a coffee
      cup and looking out the window. She wears a contemporary printed kurti top
      with jeans. Rainy afternoon light outside, condensation on glass.
      Realistic, unfiltered aesthetic, shot on smartphone. --ar 4:5 --v 6.1
base_model: Tongyi-MAI/Z-Image
instance_prompt: ish_patt
license: apache-2.0

Ishani_1

Prompt

A candid Instagram photo of the same young Indian woman sitting at a window seat in a busy, modern cafe in Bhubaneswar. She is holding a coffee cup and looking out the window. She wears a contemporary printed kurti top with jeans. Rainy afternoon light outside, condensation on glass. Realistic, unfiltered aesthetic, shot on smartphone. --ar 4:5 --v 6.1

Model description

This is a FLUX.1 LoRA (Low-Rank Adaptation) model trained for generating consistent character portraits of an Instagram AI influencer. The model was fine-tuned on 15-20 high-quality portrait images using the FLUX.1-dev base model with LoRA rank 64 and 12 training epochs.

Trigger word: ish_patt

Best use cases: Fashion photography, lifestyle content, portrait generation, cultural/traditional attire, Instagram-style photography.

Recommended settings: LoRA strength 0.8-1.0, CFG scale 1.0, steps 20-30 for optimal quality.

Trigger words

You should use ish_patt to trigger the image generation.

Download model

Download them in the Files & versions tab.