Qwen: Qwen-Image

Qwen-Image is an image generation foundation model released by the Alibaba Qwen team, featuring 20 billion parameters. The model has achieved significant advances in complex text rendering and precis…

siliconFlow/Qwen/Qwen-Image

Qwen-Image is an image generation foundation model released by the Alibaba Qwen team, featuring 20 billion parameters. The model has achieved significant advances in complex text rendering and precise image editing, excelling particularly at generating images with high-fidelity Chinese and English text. Qwen-Image can handle multi-line layouts and paragraph-level text while maintaining layout coherence and contextual harmony in the generated images. Beyond its superior text-rendering capabilities, the model supports a wide range of artistic styles, from photorealistic scenes to anime aesthetics, adapting fluidly to various creative prompts. It also possesses powerful image editing and understanding abilities, supporting advanced operations such as style transfer, object insertion or removal, detail enhancement, text editing, and even human pose manipulation, aiming to be a comprehensive foundation model for intelligent visual creation and manipulation where language, layout, and imagery converge

Specifications & capabilities

Input
text
Output
image
Published model ID
Qwen-Image
Capabilities
imageOutput

Evaluations

1–10 / 10

MTEB

98.436%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
1
sample size
1
aggregation scope
splits
  • test
subsets
  • default
task_count
1
task_names
  • CIFAR10
sample_size
1
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • d8c2e37b439f4fc47c649dc8b90cdcd3a4e0c80e
source model id
LanguageBind/LanguageBind_Image
Original result ↗

MTEB

98.436%

source id
mteb
leaderboard name
MTEB Other
dimension
embedding
metric
Average task score
rank
3
sample size
1
aggregation scope
splits
  • test
subsets
  • default
task_count
1
task_names
  • CIFAR10
sample_size
1
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • d8c2e37b439f4fc47c649dc8b90cdcd3a4e0c80e
source model id
LanguageBind/LanguageBind_Image
Original result ↗

LMArena

1,077.924

source id
lmarena
leaderboard name
LMArena Text To Image Portraits
dimension
multimodal
metric
Arena rating
rank
66
sample size
28634
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1073.2225689670076
confidence upper
1082.6245953096507
Original result ↗

LMArena

1,068.985

source id
lmarena
leaderboard name
LMArena Text To Image Commercial Design
dimension
multimodal
metric
Arena rating
rank
66
sample size
17799
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1063.9540170423224
confidence upper
1074.0153863548237
Original result ↗

LMArena

1,065.049

source id
lmarena
leaderboard name
LMArena Text To Image 3d Modeling
dimension
multimodal
metric
Arena rating
rank
66
sample size
6773
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1056.8838868059308
confidence upper
1073.2147635793426
Original result ↗

LMArena

1,056.989

source id
lmarena
leaderboard name
LMArena Text To Image Overall
dimension
multimodal
metric
Arena rating
rank
67
sample size
84293
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1054.346914850294
confidence upper
1059.6302467485405
Original result ↗

LMArena

1,056.395

source id
lmarena
leaderboard name
LMArena Text To Image Art
dimension
multimodal
metric
Arena rating
rank
67
sample size
8463
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1048.8518902022242
confidence upper
1063.9388035897582
Original result ↗

LMArena

1,053.08

source id
lmarena
leaderboard name
LMArena Text To Image Cartoon
dimension
multimodal
metric
Arena rating
rank
67
sample size
33603
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1048.9884522291457
confidence upper
1057.171852182041
Original result ↗

LMArena

1,062.589

source id
lmarena
leaderboard name
LMArena Text To Image Photorealistic
dimension
multimodal
metric
Arena rating
rank
68
sample size
42849
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1058.7953900846987
confidence upper
1066.3835411579594
Original result ↗

LMArena

1,048.753

source id
lmarena
leaderboard name
LMArena Text To Image Text Rendering
dimension
multimodal
metric
Arena rating
rank
68
sample size
15421
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen-Image
confidence lower
1043.409944795941
confidence upper
1054.0968800549617
Original result ↗

Published prices

1–1 / 1

Qwen/Qwen-Image ↗

$0.02

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
image
Currency
USD
Billing conditions
Billing label
Image

Provider specifications & access

1–9 / 9

Qwen/Qwen-Image ↗

source model id
HuggingFace/qwen-qwen-image@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • image
capabilities

    Qwen/Qwen-Image ↗

    source model id
    HuggingFace/qwen-qwen-image@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    apache-2.0
    architecture
    input_modalities
    • text
    output_modalities
    • image
    capabilities

      Qwen/Qwen-Image ↗

      source model id
      HuggingFace/qwen-qwen-image@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      apache-2.0
      architecture
      input_modalities
      • text
      output_modalities
      • image
      capabilities

        Qwen/Qwen-Image ↗

        source model id
        HuggingFace/qwen-qwen-image@4
        hosting
        foundry-managed-compute
        platforms
        • Microsoft Foundry
        license
        apache-2.0
        architecture
        input_modalities
        • text
        output_modalities
        • image
        capabilities

          Qwen/Qwen-Image ↗

          source model id
          HuggingFace/qwen-qwen-image@5
          hosting
          foundry-managed-compute
          platforms
          • Microsoft Foundry
          license
          apache-2.0
          architecture
          input_modalities
          • text
          output_modalities
          • image
          capabilities

            Qwen/Qwen-Image ↗

            source model id
            HuggingFace/qwen-qwen-image@6
            hosting
            foundry-managed-compute
            platforms
            • Microsoft Foundry
            license
            apache-2.0
            architecture
            input_modalities
            • text
            output_modalities
            • image
            capabilities

              Qwen-Image ↗

              source model id
              publishers/qwen/models/qwen-image@qwen-image
              hosting
              vertex-self-deployed
              platforms
              • Google Cloud Vertex AI
              architecture
              input_modalities
              • text
              output_modalities
                capabilities

                  qwen-image ↗

                  source model id
                  qwen/qwen-image
                  hosting
                  nvidia-catalog
                  platforms
                  • NVIDIA Build / NIM
                  architecture
                  input_modalities
                    output_modalities
                      capabilities
                      • imageOutput

                      Qwen-Image ↗

                      source model id
                      Qwen/Qwen-Image
                      hosting
                      siliconflow-hosted
                      platforms
                      • SiliconFlow
                      architecture
                      input_modalities
                      • text
                      output_modalities
                      • image
                      capabilities

                        Safety assessments

                        1–1 / 1

                        Foundation Model Transparency Index 2025 ↗

                        26 / 100

                        source id
                        stanfordFMTI
                        canonical model id
                        siliconFlow/Qwen/Qwen-Image
                        taxonomy
                        transparency
                        hazard category
                        transparency
                        hazard name
                        Organization transparency
                        policy area
                        Alibaba
                        assessment type
                        organization-level disclosure
                        metric
                        disclosure_score
                        result label
                        26 / 100
                        sample size
                        100
                        updated at
                        2026-11-09T18:08:05.227Z

                        Source specification observations

                        1–1 / 1

                        siliconFlow ↗

                        field
                        context_length
                        value
                        0K
                        scope
                        source-model
                        source id
                        siliconFlow
                        confidence
                        1

                        Original sources

                        1–20 / 23

                        SiliconFlow · Model page ↗

                        qianwen-res.oss-cn-beijing.aliyuncs.com · Model reference ↗

                        Hugging Face · Model repository ↗

                        Google Cloud · Model page ↗

                        Microsoft Foundry · Model page ↗

                        Microsoft Foundry · Model page ↗

                        Microsoft Foundry · Model page ↗

                        Microsoft Foundry · Model page ↗

                        Microsoft Foundry · Model page ↗

                        Microsoft Foundry · Model page ↗

                        NVIDIA · Model page ↗

                        SiliconFlow · Playground ↗

                        Microsoft Foundry · Model documentation ↗

                        NVIDIA · Documentation ↗

                        SiliconFlow · API documentation ↗

                        Epoch AI · Catalog ↗

                        GitHub · Catalog ↗

                        Google Cloud · Catalog ↗

                        Hugging Face · Catalog ↗

                        LMArena · Catalog ↗

                        Source links

                        1–8 / 8

                        Explore more models

                        Models

                        Loading
                        EVIDENCE / COMPARISON

                        Benchmarks

                        Explore every benchmark

                        Loading

                        These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

                        Install TensorTrace