You can deploy this model and start earning money today!

oindrila13saha/
sigma-gen-lora

Name: sigma-gen-lora
Availability: InStock

identity-preservation

sigma-gen

image-to-image

2510.06469

black-forest-labs/FLUX.1-Kontext-dev

adapter

cc-by-nc-4.0

Views

No views yet

SIGMA-Gen: Structure and Identity Guided Multi-subject Assembly for Image Generation

Oindrila Saha · Vojtech Krs · Radomir Mech · Subhransu Maji · Kevin Blackburn-Matzen · Matheus Gadelha

University of Massachusetts Amherst | Adobe Research

Overview

SIGMA-Gen enables multi-identity image generation in a single pass, guided by structural and spatial constraints. It supports varied user guidance precision — from 2D/3D boxes to pixel-level segmentations and depth — achieving state-of-the-art performance in identity preservation, generation quality, and processing speed.

Weights

This repository contains two LoRA adapters trained on top of FLUX.1-Kontext-dev:

File	Purpose
`cond1.safetensors`	Subject identity conditioning
`cond2.safetensors`	Spatial/structural conditioning

Usage

python

from diffusers.pipelines import FluxKontextPipeline
import torch

pipe = FluxKontextPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16
).to("cuda")

pipe.load_lora_weights("oindrila13saha/sigma-gen-lora", weight_name="cond1.safetensors", adapter_name="cond1")
pipe.load_lora_weights("oindrila13saha/sigma-gen-lora", weight_name="cond2.safetensors", adapter_name="cond2")
pipe.set_adapters(["cond1", "cond2"], adapter_weights=128)

Citation

bibtex

@article{saha2025sigma,
  title={SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation},
  author={Saha, Oindrila and Krs, Vojtech and Mech, Radomir and Maji, Subhransu and Blackburn-Matzen, Kevin and Gadelha, Matheus},
  journal={arXiv preprint arXiv:2510.06469},
  year={2025}
}