CivArchive
    Qwen Image 2.1 - 2.1
    Preview 143384430
    Preview 143384449

    Repost From Huggingface

    https://huggingface.co/Qwen/Qwen-Image-2.1

    Introduction

    We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.

    Four key improvements define this release:

    • Compact and Efficient — A lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost.

    • Native Transparency, Unified Creation and Editing — Generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs—all in one model.

    • Versatile Editing — Support up to 10 reference images, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products.

    • Realistic Textures and Refined Aesthetics — Improved typography, portrait lighting, and fine details for more visually compelling results.

    Description

    FAQ

    Comments (6)

    artemzlykin369Sep 21, 2026
    CivitAI

    https://civitai.red/models/2953241/qwenimage21

    8stepmafia
    Author
    Sep 21, 2026

    They didn't post the text encoder or vae.

    RoshagSep 21, 2026

    And this one has Int8

    gonfinal12Sep 21, 2026
    CivitAI

    is this the official one

    8stepmafia
    Author
    Sep 21, 2026· 1 reaction

    Its the official checkpoint from the qwen team reposted.

    imagCSep 23, 2026· 1 reaction
    CivitAI

    That new qwen version is simple perfect. A lot better than Flux klein and Krea for edit

    Checkpoint
    Qwen 2
    by 8stepmafia
    Download (Beta) View on CivitAI
    base model

    Details

    Downloads
    722
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/21/2026
    Updated
    9/23/2026
    Deleted
    -

    Files

    qwenImage21_21_txt_bf16.safetensors

    Size:
    16.33 GB
    SHA256:
    68bdc82bc1b66851162ae656225e7e2068166b603db19bd5d5a3b90eb12669a9

    Mirrors

    HuggingFace (5 mirrors)
    CivitAI (3 mirrors)

    qwenImage21_21_txt_int8.safetensors

    Size:
    8.71 GB
    SHA256:
    8bfd0f6e12abf2d2d697ecc888e5e90b0d6741d6708f05799f53afa560452e8f

    Mirrors

    HuggingFace (16 mirrors)
    CivitAI (6 mirrors)

    qwenImage21_21_bf16.safetensors

    Size:
    13.25 GB
    SHA256:
    89f4158d066cc33906a199fca85634f766892dd78f49b6698dabf187ac86c4bc

    Mirrors

    CivitAI (4 mirrors)

    qwenImage21_21_int8.safetensors

    Size:
    6.76 GB
    SHA256:
    cb74113cb03faecd79611b01fd7fd642f0aa60d6f0b95086abee214d75eaa57d

    Mirrors

    HuggingFace (12 mirrors)
    CivitAI (3 mirrors)
    TensorArt (1 mirrors)
    TensorHub (1 mirrors)

    qwen_image_2.1_vae_bf16.safetensors

    Size:
    644.22 MB
    SHA256:
    bb21f7473051e1ac368515dd3f2e15cd44d7a11748ee8823e1ddca3e4876b7c9

    Mirrors

    HuggingFace (18 mirrors)
    CivitAI (6 mirrors)
    ModelScope CN (1 mirrors)