QWEN IMAGE 2.1 - QWEN IMAGE 2.1

Name: QWEN IMAGE 2.1 - QWEN IMAGE 2.1
Availability: InStock
Rating: 4.2 (87 reviews)
Author: REKTY ANJANY

QWEN IMAGE 2.1

CHECKPOINT

Original

REKTY ANJANY

Updated: Nov 3, 2026 1:02 PM

REKTY Photoreal 2.1

A photorealistic text-to-image checkpoint fine-tuned from Qwen Image 2.1 (Qwen/Qwen-Image-2.1), developed and tuned in-house by REKTY. Built for grounded, natural-looking photography: real skin texture without the plastic sheen, natural colour balance, honest highlight roll-off and film-like grain — while keeping Qwen Image 2.1's native strengths: excellent prompt adherence, long detailed captions, and best-in-class text rendering inside images.

Start your prompt with the trigger word: photorealistic,

Recommended settings:

- Trigger: "photorealistic," at the start of the prompt

- Sampler: Euler

- Steps: 40

- CFG: 1.0

- Resolution: 1024×1024 / 832×1216 / 1216×832

- Negative prompt: empty (CFG 1.0)

Full scene captions work best: subject + outfit + location + lighting + camera/lens + colour palette + mood. Short prompts leave most of this model's capability unused.

Best for:

- Photorealistic portraits with natural skin texture

- Editorial, fashion and street photography

- Realistic Asian and global characters

- Scenes with signage or text in frame — Qwen renders text natively

---

Attribution & license (required — license condition)

Improved using Qwen. Based on Qwen Image 2.1 by Alibaba Tongyi Lab, modified by REKTY and distributed as a derivative work.

Full license: https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE

Version Detail

Uploaded

Oct 24, 2026 1:37 PM

Base Model

Qwen-Image-2.1

Steps

12000

Epoch

Description

**REKTY Photoreal 2.1** A photorealistic text-to-image checkpoint fine-tuned from Qwen Image 2.1 (Qwen/Qwen-Image-2.1), developed and tuned in-house by REKTY. Built for grounded, natural-looking photography: real skin texture without the plastic sheen, natural colour balance, honest highlight roll-off and film-like grain — while keeping Qwen Image 2.1's native strengths: excellent prompt adherence, long detailed captions, and best-in-class text rendering inside images. Start your prompt with the trigger word: photorealistic, Recommended settings: - Trigger: "photorealistic," at the start of the prompt - Sampler: Euler - Steps: 40 - CFG: 1.0 - Resolution: 1024×1024 / 832×1216 / 1216×832 - Negative prompt: empty (CFG 1.0) Full scene captions work best: subject + outfit + location + lighting + camera/lens + colour palette + mood. Short prompts leave most of this model's capability unused. Best for: - Photorealistic portraits with natural skin texture - Editorial, fashion and street photography - Realistic Asian and global characters - Scenes with signage or text in frame — Qwen renders text natively --- Attribution & license (required — license condition) Improved using Qwen. Based on Qwen Image 2.1 by Alibaba Tongyi Lab, modified by REKTY and distributed as a derivative work. Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved. Full license: https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE

Project Permissions

Reprinting is strictly prohibited

Use Permissions

Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges

Commercial Use

Sell generated contents
Use on generation services
Sell this model or merges