Springus

Image-Guided Editing Models - Benchmarks

Overview

In this benchmark we evaluate image editing models on their ability to perform image-guided transformations while preserving identity-defining details from an input image. This benchmark requires models to integrate information from:

  • An input image a "fit pic" containing the subject of interest within its broader outfit context.
  • A query image a "e-commerce style flat-lay" containing the desired pose, composition, or spatial configuration of the output
  • A text prompt guiding the edit (templated, serving to introduce both images)

Goal: Generate an image that combines the garment from the input with the pose/composition of the query image while preserving identity-defining details such as text, logos, printed graphics, and complex patterns.

Fashion garment transfer workflow diagram

Figure 1: The image editing task - transferring garment identity with fine-grained attribute preservation


Results

Overall Winner
Nano Banana Pro 8 / 12
Best average performance across all four tasks
Runner Up
Nano Banana 7 / 12
Strong consistency with minor misses on multi-image
Honorable mention
GPT-Image 1
Stand out performance on multi-image task
Model Total ( /12) Graphic Reconstruction Pattern Reconstruction Small Segment Multi Image
Nano Banana Pro Winner 8 3/3 3/3 1/3 1/3
Nano Banana Runner Up 7 3/3 2/3 1/3 1/3
GPT Image-1 4 0/3 1/3 0/3 3/3
Seedream 4 3 1/3 1/3 0/3 1/3
Qwen 2 2/3 0/3 0/3 0/3

These benchmarks stress true one-shot performance with a bias towards consistancy over best possible outcome. Each model must hit quality targets with minimal inputs. Across Tasks 1–3, Nano Banana Pro consistently demonstrates strong one-shotting, delivering reliable outputs with limited context.

When holistically evaluating the performance gap between the Nano Banana and Nano Banana Pro model, the differences are negligible. While outside the scope of this study, Nano Banana Pro is unlikely to see usage in prod due to its significantly worse cost and latency when compared to Nano Banana.

Future work should deepen few-shot tasks; early signals suggest GPT Image-1 may benefit from richer input sets, and expanded multi-image tests could surface that advantage. Such tasks would also be a better reflection of image editing models in the Springus App.

Graphic Reconstruction

Our first benchmark task tests the models' ability to preserve text and graphic details when transferring a garment to a new pose.
Input Image
Source t-shirt with graphic text
Query Image
Target pose reference
Prompt
Using the t-shirt in the outfit image, render it in the layout, pose, and background of the query image. Preserve all visible text, graphics, and patterns from the outfit image. Keep all structural cues from the query image unchanged.
Nano Banana Pro
Nano Banana Pro output
3/3

Pros

  • Flawless text preservation and graphic retention
  • Impeccable pose matching to query image
  • Clean background transfer with no artifacts
  • Natural lighting and shadows

Cons

  • Minor edge sharpening visible on one run
Nano Banana
Nano Banana output
3/3

Pros

  • Perfect text preservation and graphic retention
  • Perfect pose matching

Cons

  • Graphic size and placement off in one run
Qwen
Qwen output
2/3

Pros

  • Perfect graphic reconstruction
  • Stable colour preservation across runs

Cons

  • Poor brand text reconstruction
  • Graphic placement off on one attempt
Seedream 4
Seedream output
1/3

Pros

  • Good graphic reconstruction
  • Strong colour match

Cons

  • Text font doesn't match on most runs
GPT Image-1
GPT Image-1 output
0/3

Pros

  • Fair graphic reconstruction in isolated regions

Cons

  • Colours don't match
  • Graphic size off
  • Brand text illegible

Nano Banana Pro, Nano Banana and Qwen are all roughly evenly matched here. Logo reconstruction is perfect across all of theirs runs. The smaller (and less important) brand logo is the only differentiator here.

Pattern Reconstruction

Our second benchmark task tests the models' ability to retain patterns while transfering a garment into a new pose.
Input Image
Source pants with pattern
Query Image
Target pose reference
Prompt
Using the pants in the outfit image, render them in the layout, pose, and background of the query image. Preserve all visible text, graphics, and patterns from the outfit image. Keep all structural cues from the query image unchanged.
Nano Banana Pro
Nano Banana Pro output
3/3

Pros

  • Flawless pattern preservation and detail retention
  • Strong pose matching to query image
  • Clean background transfer with no artifacts

Cons

  • Minor fabric stiffness on one variation
Nano Banana
Nano Banana output
2/3

Pros

  • Flawless pattern preservation and detail retention
  • Strong pose matching to query image
  • Clean background transfer with no artifacts

Cons

  • Waist crease slightly softened in one run
Qwen
Qwen output
0/3

Pros

  • Strong pattern match
  • Good color fidelity

Cons

  • Waist style not matching
  • Graphic hallucinations
Seedream 4
Seedream output
1/3

Pros

  • Good lighting and shadows
  • Strong pattern matching

Cons

  • Pose doesn't match query image input
GPT Image-1
GPT Image-1 output
1/3

Pros

  • Fair pattern matching
  • Strong representation of input image

Cons

  • Waist style not matching (hallucinated waistband)

Once again, Nano Banana Pro, Nano Banana excel. Failure modes are interesting to note here, Qwen and Seedream 4 both retain the distinct blotch on the upper left leg yet both hallucinate larger important details like fly or pocket placement.

Small Segment Enhancement

Our third benchmark task tests the models' ability to reconstruct small but detailed objects that occupy minimal image space while preserving identity and fine details. As a side task, we also examine some elements of world modeling as part of the sections of interest in the query image aren't visible within the input image.
Input Image
Source shoes in outfit
Query Image
Target pose reference
Prompt
Using the shoes in the outfit image, render them in the layout, pose, and background of the query image. Preserve all visible text, graphics, and patterns from the outfit image. Keep all structural cues from the query image unchanged.
Nano Banana Pro
Nano Banana Pro output
1/3

Pros

  • Fantastic detail enhancement, brand logo displayed despite not being visible
  • Fair jibbit reconstruction
  • Strong pose matching
  • Incredible display of world knowledge—accurate under-shoe details despite being invisible

Cons

  • Minor sole over-sharpening on one run
Nano Banana
Nano Banana output
1/3

Pros

  • Accurate pose matching
  • Fair jibbit reconstruction

Cons

  • Incorrect under shoe details on one variation
Qwen
Qwen output
0/3

Cons

  • Complete hallucination. Input not visible in output
Seedream 4
Seedream output
0/3

Pros

  • Accurate shoe structure
  • Identifiable result.

Cons

  • "Sport mode" strap hallucination
  • Inaccurate pose
GPT Image-1
GPT Image-1 output
0/3

Cons

  • Complete hallucination. Input not visible in output

This task borders on unfair. We're testing the model on some zero-shot elements by looking for the crocs sole in the output. Its remarkable how strong the passing output of Nano Banana Pro is. Not only does it get the texture of the bottom of the shoes right, but both the logo and size placement. It's worth noting too that it's other failure modes are due to query misalignment rather than any sort of hallucination (As is the case with all other outputs).

Multi Image Reconstruction

Our fourth benchmark task tests the models' ability to reconstruct multiple images simultaneously, preserving consistency across inputs. This is the only example few shot inference in this benchmark.
Input Image 1
Input 1
Query Image
Query
Prompt
Using the t-shirts in the outfit images, render them in the layout, pose, and background of the query image. Preserve all visible text, graphics, and patterns from the outfit image. Keep all structural cues from the query image unchanged.
Nano Banana Pro
Nano Banana output
1/3

Pros

  • Accurate and consistent colour matching
  • Consistent text spacing

Cons

  • Inconsistent text reconstruction between inputs
  • Inconsistent shirt size across runs
Nano Banana
Nano Banana output
1/3

Pros

  • Consistent matching query image sizing and pose
  • Failure cases are less visibly jarring

Cons

  • Inconsistent coloring on one attempt
Qwen
Qwen output
0/3

Pros

  • Incredibly consistent text reconstruction

Cons

  • Core prompt alignment
Seedream 4
Seedream output
1/3

Pros

  • Incredibly consistent text reconstruction

Cons

  • Poor prompt alignment
  • Hallucinations of shirt damage
GPT Image-1
GPT Image-1 output
3/3

Pros

  • Incredibly consistent text reconstruction
  • Consistent sizing
  • Consistent font

This task shows a major shortcoming of the Nano Banana family. Text reconstruction given multiple angles seems like a relatively easy task for the models, but the Nano Banana family fails to do so. This hints they might struggle with tasks that benefit from few-shot reasoning. More testing is needed to confirm this.


Controlled Variables

Our benchmark ensures fair comparison across all models:

  • Same prompt across all models (minimal mechanical adjustments)
  • Best of 3 generations - We generate 3 outputs per model and show the best result
  • Same resolution (1024×1024)
  • Same format JPEG (no compression)
  • Same aspect ratio (square)
  • Same test images for fair comparison

References & Acknowledgments

This benchmark builds on the excellent work by Shaun Pedicini in the original GenAI Image Editing Showdown, summarized by Simon Willison.

Model providers: - ByteDance (Seedream 4) - Google (Gemini 2.5 Flash) - Qwen Team (Qwen-Image-Edit-Plus) - Black Forest Labs (FLUX.1 Kontext) - OmniGen Community - OpenAI (gpt-image-1)

Platform: Replicate for unified model access

Try Springus for Free

Upload your fit pics. Know what works. Dress with confidence.

Get Started