Head to head
Esc

Models · slot A

to navigate to pick

P-Image Edit PrunaAI Wan 2.6 Alibaba

Settled by community votes across 6 shared challenges, with an AI judge weighing in on each.

P-Image Edit

9.5 arena score

#29 of 32 in Image Editing

Skill signature · Image Editing

Wan 2.6

23.3 arena score

#28 of 62 in Text-to-Image

Top 2 in Image-to-Video
Vote tally

Where the votes landed

P-Image Edit

0%

win rate

Ties

0%

Wan 2.6

0%

win rate

Shared challenges 6

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
P-Image Edit
Wan 2.6

AI Judge Analysis

P-Image Edit

  • + Excellent preservation of the car's original design and perspective
  • + High-quality motion blur on the wheels and road
  • The man is barely visible and does not clearly resemble the subject from the source image
  • The man is positioned too far back relative to the steering wheel

Wan 2.6

  • + Successfully preserves the identity of the man including his specific hairstyle and plaid coat
  • + Natural integration of the subject into the driver's seat
  • + Beautiful and clear California coastline background
  • Cropped the front of the car significantly compared to the original composition

Verdict: Wan 2.6 is the clear winner as it successfully integrated both source images by placing the specific man from the second image into the car from the first image. P-Image Edit maintained the car's full profile but failed to include a recognizable version of the requested person, opting for a generic far-off silhouette.

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
P-Image Edit
Wan 2.6

AI Judge Analysis

P-Image Edit

  • + Excellent adherence to all outfit components including the coat, scarf, and jeans.
  • + Successfully maintained the source person's unique skin patterns and facial features.
  • + Includes creative but logic-based interpretations for the shoes based on the outfit style.
  • The scale of the person relative to the beach structure is slightly smaller than the original.
  • The gold chains added were not in the source image of the outfit.

Wan 2.6

  • + Perfect preservation of the original image's framing, head size, and background.
  • + Maintains the sand texture on the face and the skin vitiligo patterns accurately.
  • + Successfully added the sunglasses from the outfit image.
  • Fails to include the full outfit, cutting off at the chest.
  • Misinterprets the scarf pattern and colors, opting for a generic red plaid instead of the specific green/red/thin-white plaid.

Verdict: P-Image Edit successfully applied the full-body edit requested, capturing including the coat, scarf, and jeans while adapting them to the subject's pose. Wan 2.6 provided a much higher fidelity face and head preservation that exactly matches the source, but it failed to render the full outfit as requested, cutting off at the torso and changing the scarf's design.

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.”

Before After
P-Image Edit
Before After
Wan 2.6

AI Judge Analysis

P-Image Edit

  • + Successfully added a large volume of hair as requested
  • + Preserved face and clothing details almost perfectly
  • + Maintained the original lighting and desert environment
  • Hair texture looks somewhat synthetic/digital
  • The hairline connection to the forehead is a bit abrupt
  • The choice of hairstyle feels less 'natural' for the character's existing beard

Wan 2.6

  • + Excellent integration of the hairline and temples
  • + Highly realistic hair texture and movement
  • + Style matches the character and lighting perfectly
  • Slight alteration to the forehead and eyebrow shape
  • The glasses frames seen more embedded in the face than the original

Verdict: P-Image Edit successfully followed the instruction but the hair texture looks slightly artificial and disconnected from the scalp. Wan 2.6 achieved a much more realistic result with a natural hairline and texture that integrates seamlessly with the original subject's features, despite very minor changes to the forehead area.

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
P-Image Edit
Wan 2.6

AI Judge Analysis

P-Image Edit

  • + Excellent preservation of the subject's facial features and denim shirt style.
  • + Creative integration of hockey by placing the anchor desk directly on an ice rink.
  • + High-quality digital caricature art style with good shading.
  • The dog is very small and has a strange red object on its back.
  • The text on the background screens is nonsensical/gibberish.

Wan 2.6

  • + Very clear and prominent inclusion of dogs and hockey equipment (stick and puck).
  • + Humorous and expressive caricature style that fits the 'exaggerated' request.
  • + Stronger 'TV anchor' vibe with the professional suit and studio lighting.
  • Subject loses the specific likeness and denim clothing from the source image.
  • Anatomical issues with the subject's hands and the pug's grip on the hockey stick.

Verdict: P-Image Edit is the winner because it successfully creates a caricature that still looks remarkably like the woman in the source image, even down to her denim shirt. While Wan 2.6 captures more of the requested props (like the hockey stick and better dogs), it fails as an edit because it generates a generic cartoon character that bears little resemblance to the original person.

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
P-Image Edit
Wan 2.6

AI Judge Analysis

P-Image Edit

  • + Successfully replaces the urban city background with a dreamy, Ghibli-esque park setting
  • + Maintains strong color vibrance and clear character expressions
  • + Good preservation of the original pose and facial orientation
  • The art style leans closer to modern webtoon or generic digital illustration than hand-painted Ghibli art
  • The lighting feels a bit flat compared to the requested dreamy atmosphere

Wan 2.6

  • + Excellent adherence to the 'hand-painted textures' requirement with a watercolor aesthetic
  • + Perfectly captures the soft, nostalgic, and dreamy Ghibli mood
  • + Preserves the original street background while stylizing it effectively
  • The added white sparkles/bokeh can be a bit distracting
  • Slightly less facial detail in the background character compared to Model A

Verdict: Both models did an excellent job preserving the composition and characters of the original 'Distracted Boyfriend' meme. P-Image Edit creates a cleaner, more colorful illustration but changes the background to a park, while Wan 2.6 captures the specific 'Studio Ghibli' hand-painted watercolor aesthetic much more accurately and evocatively.

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.”

Before After
P-Image Edit
Before After
Wan 2.6

AI Judge Analysis

P-Image Edit

  • + Strong adherence to the 'hair blow' instruction with a dramatic, energetic effect
  • + High density of falling leaves added throughout the frame
  • + Perfect preservation of the background and original subjects
  • The hair flow is perhaps slightly too symmetrical, looking a bit unrealistic
  • The dog's tail is slightly altered compared to the source

Wan 2.6

  • + Naturalistic hair movement that looks realistic
  • + Preserves the original image elements perfectly
  • + Clean integration of flying leaves with motion blur
  • The wind effect on the hair is subtle and less energetic
  • Fewer leaves added compared to the other model
  • The leaf shapes appear slightly more generic and less integrated

Verdict: P-Image Edit followed the instructions more aggressively, creating a much more 'energetic and lively' feel by significantly blowing out the woman's hair and adding many more leaves. While Wan 2.6 is more subtle and realistic, it fails to capture the 'dynamic motion' requested as effectively as P-Image Edit.

Next steps

Explore each model