Qwen Image Edit 2509 Alibaba Vidu Q2 ShengShu Technology

Settled by community votes across 7 shared challenges, with an AI judge weighing in on each.

Qwen Image Edit 2509

7.8 arena score

#32 of 32 in Image Editing

Skill signature · Image Editing

Vidu Q2

19.8 arena score

#42 of 62 in Text-to-Image

Vote tally

Where the votes landed

Qwen Image Edit 2509

win rate

Ties

Vidu Q2

win rate

Shared challenges 7

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Man and Car in California

Editing

Edit instruction

“Make a photo of the man driving the car down the California coastline”

Source

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Excellent preservation of the car's original design and color
+ Beautiful atmospheric lighting and motion blur on wheels
+ Correctly identifies character features like the dreadlocks

− The driver is sitting too low and is partially obscured by the car door

Vidu Q2

+ Successfully places the specific man from the source image behind the wheel
+ High detail in the background coastline scenery
+ Strong composition with leading lines on the road

− Minor distortion to the car's proportions relative to the source
− The driver's scale and pose look slightly artificial in the cockpit

Verdict: Both models performed the image editing task exceptionally well, maintaining the car and the man's identity. Qwen Image Edit 2509 produces a more cinematic shot with superior lighting and motion effects, whereas Vidu Q2 does a better job of making the face of the man clearly visible and recognizable as the subject from the source image.

Pose & Character Mashup

Editing

Edit instruction

“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”

Source

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Preserves the overall composition of Image 1.

− Completely failed to use the character from Image 2.
− Provides almost no visible edit compared to the original Image 1.
− Added heavy artificial sharpening and saturation to the original image.

Vidu Q2

+ Accurately transplants the character identity from Image 2, including the face and sunglasses.
+ Faithfully replicates the clothing style, colors, and accessories (scarf, watch) from Image 2.
+ Successfully maps the character into the complex pose and yellow studio environment of Image 1.

− The fingers on the lower left hand are distorted with extra digits.
− The hair texture and forehead area look slightly blended with the original pose's structure.

Verdict: Qwen Image Edit 2509 failed the task entirely, returning the original person from Image 1 with slightly increased saturation. Vidu Q2 successfully integrated the man from Image 2 into the specific pose, lighting, and environment of Image 1 while maintaining his facial features, sunglasses, and clothing details, despite some minor anatomical errors in the hands.

Outfit Transfer Challenge

Editing

Edit instruction

“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”

Source

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Successfully captured the entire outfit including shoes and pose from Image 2.
+ Maintained the wooden structure from the background effectively.

− Failed to preserve the face and identity of the person from Image 1, merging features with the person in Image 2.
− Low image resolution and significant artifacts around the edges of the person.
− Added objects like sunglasses and a mustache that were not on the target person.

Vidu Q2

+ Excellent preservation of the person's identity and facial structure from Image 1.
+ High visual quality and seamless blending of the clothing layers.
+ Accurately included accessories like the watch and rings from Image 2.

− The clothing on the right arm is transparent or incorrectly rendered, showing skin where fabric should be.
− Changed the background significantly, extending the beach and adding grass not present in Image 1.

Verdict: Vidu Q2 is the superior model because it successfully maintained the identity of the person from Image 1, whereas Qwen Image Edit 2509 essentially replaced the subject with the person from Image 2. While Vidu Q2 had a rendering error on the sleeve and altered the background, its ability to keep the facial features and skin patterns of the original person while applying the new outfit was much more aligned with the instructions.

Bald man challenge

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Excellent preservation of the original face and eye details.
+ Very high-volume, thick hair that matches the 'full' instruction.
+ Good integration of the hair with the sideburns and beard.

− The hair has a slightly oily or plastic texture that looks a bit less natural.
− The hairline on the forehead is a bit high and rounded.

Vidu Q2

+ Extremely realistic hair texture with fine, individual strands.
+ The hairline looks very natural and follows a believable growth pattern.
+ Perfectly preserves the source image's identity and background.

− The hair volume is slightly more conservative compared to the 'full, thick' request in Model A.

Verdict: Both models performed exceptionally well at preserving the source image while adding hair. Qwen Image Edit 2509 provided a more dramatic 'thick' head of hair, but Vidu Q2 produced a significantly more realistic texture and a much more convincing hairline, making it look like a real photograph rather than an edit.

Over-the-top cartoon caricature

Editing

Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Expertly captures the cartoon caricature style with exaggerated facial features.
+ Strong adherence to the selfie perspective of the source image.
+ Effectively combines all three requested themes: TV news, hockey, and dogs.

− The text in the speech bubble and on the screen is gibberish.
− The dog at the bottom is very small and relatively simple compared to the rest of the image.

Vidu Q2

+ Excellent integration of the hockey theme with a puck and stadium background.
+ High-quality rendering of the dogs, including one in a tiny jersey.
+ Clean, professional illustration style while maintaining the subject's likeness.

− Anatomy issues with the hand holding the microphone (broken wrist/finger placement).
− Failed to preserve the selfie-style composition of the original photo.
− A bit cluttered, with a mix of a news desk and a hockey rink that feels slightly disjointed.

Verdict: Qwen Image Edit 2509 is the winner because it successfully transforms the original photo into an 'exaggerated and humorous' caricature while maintaining the original selfie perspective. While Vidu Q2 produces a very clean illustration with better animal details, the catastrophic anatomical failure of the hand and the loss of the source image's composition makes it less successful as an edit.

Studio Ghibli Anime Style

Editing

Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Excellent adherence to the 'Studio Ghibli' aesthetic with soft, rounded character designs.
+ Strong color palette consistency with warm, nostalgic pastel tones.
+ Clean, consistent line work and textures throughout the image.

− The man's expression is a bit too calm and misses the 'surprised' look of the original meme.
− The background is slightly more simplified than needed.

Vidu Q2

+ Successfully captures the specific facial expressions of the original meme characters.
+ Displays lovely hand-painted watercolor textures that match the prompt well.
+ Preserves the original facial structures and features more closely than Model A.

− The line work on the man's shirt and the woman's face is a bit jagged and less polished.
− The background architecture feels slightly messy and less cohesive.

Verdict: Both models performed very well on this editing task. Qwen Image Edit 2509 delivered a more authentic 'anime' look that feels like a professional screen capture, while Vidu Q2 excelled at preserving the comedic expressions and specific likenesses from the source photo. Vidu Q2 is the winner because it successfully balances the heavy stylistic transformation with the iconic 'distracted boyfriend' expressions, whereas Qwen Image Edit 2509 made the characters feel a bit too generic.

Golden Hour Stroll

Image Editing

Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Qwen Image Edit 2509

Vidu Q2

AI Judge Analysis

Qwen Image Edit 2509

+ Successfully adds a high volume of floating maple leaves.
+ Manipulates the hair significantly to show strong wind direction.
+ Maintains the identity of the person and dog very well.

− The hair strands look somewhat artificial and overly stylized.
− Some leaves appear flat or lack realistic depth and motion blur.

Vidu Q2

+ Leaves have varied sizes and motion blur, creating better depth of field.
+ Hair motion looks more natural and integrated with the face.
+ Excellent preservation of the original image's lighting and subjects.

− The wind effect on the hair is slightly less dramatic than the other model.
− Minor inconsistencies in leaf illumination relative to the sun's position.

Verdict: Both models followed the instructions well, preserving the core subjects while adding the requested motion. Vidu Q2 is the preferred winner because its leaves and hair motion feel more photographically realistic, whereas Qwen Image Edit 2509 has a more illustrative quality to the added wind effects.