---
license: apache-2.0
language:
- en
base_model:
- black-forest-labs/FLUX.1-Kontext-dev
- black-forest-labs/FLUX.1-dev
- black-forest-labs/FLUX.1-schnell
---

model_name: "Tumpa Khara"
base_model: "Flux 1D"
model_type: "LoRA"
version: "1.0"
license: "cc-by-nc-4.0"
tags:
  - lora
  - flux
  - 1d
  - tumpa
  - khara
  - custom-style
description: |
  Tumpa Khara is a LoRA (Low-Rank Adaptation) model built on Flux 1D architecture.
  It is designed to enhance and adapt stylistic or task-specific performance,
  making it easier to fine-tune on personalized or domain-specific data.
  The model emphasizes expressive, smooth, and elegant transformations,
  inspired by the style of Tumpa Khara.

trained_by: "Trina"
trained_on: "Custom dataset curated for personalized style and expression"
release_date: "2025-07-07"
contact: "your_email@example.com"
usage: |
  To use this LoRA, load it on top of the Flux 1D base model.
  Recommended to apply with a weight between 0.6 and 1.0 for best results.
limitations: |
  Not intended for commercial use without explicit permission.
  May not generalize well outside its specific style domain.
  Avoid using on data that diverges significantly from the training set.

# Optional fields
example_prompts:
  - "Portrait of Tumpa Khara, soft lighting, elegant expression, cinematic look"
  - "Dynamic 1D waveform with smooth gradients, inspired by Tumpa Khara"
  - "Fashion-style illustration with graceful posture, detailed fabric folds"

images:
  - "https://huggingface.co/rstudioModel/piyali_flux1D/resolve/main/image1.png"
  - "https://huggingface.co/rstudioModel/piyali_flux1D/resolve/main/image2.png"
  - "https://huggingface.co/rstudioModel/piyali_flux1D/resolve/main/image3.png"

references:
  - "https://github.com/rstudioweb/rstudioweb"
  - "https://huggingface.co/rstudioModel/simran_parvin_flux1D"

---