PrunaAI's sub-1-second multi-image editing model supporting up to 5 reference images with state-of-the-art quality
Settled by community votes across 1 shared challenge, with an AI judge weighing in on each.
P-Image Edit
#24 of 23 in Image Editing
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Wan 2.7
#34 of 44 in Text-to-Image
Where the votes landed
P-Image Edit
0%
win rate
Ties
0%
Wan 2.7
0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Outfit Transfer Challenge
Editing“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.”
AI Judge Analysis
P-Image Edit
- + Excellent adherence to the specific clothing items (peacoat, plaid scarf, blue jeans) from Image 2.
- + Maintains the person's identity and facial features with high accuracy.
- + Correctly preserves the wood structure and environment from the base image.
- − Added a thick gold chain and yellow-laced boots that were not in either source image.
- − The body proportions appear slightly shortened and compressed compared to the original person's height.
Wan 2.7
- + Successfully preserves the subject's face, skin patterns (vitiligo), and general hair style.
- + Good integration of the person into the beach environment with realistic lighting.
- − Failed the clothing instruction entirely by generating a generic ornate coat instead of the specific peacoat/scarf outfit from Image 2.
- − Anatomical issues with the hands, including an extra thumb/finger structure on the right hand.
- − Source preservation is weak as it changed the subject's pose significantly.
Verdict: P-Image Edit successfully followed the core instruction to dress the person in the specific outfit from Image 2, including the blue peacoat, jeans, and plaid scarf. While it took some creative liberties with the shoes and jewelry, Wan 2.7 failed the primary task by generating a completely different, unrelated outfit and introduced significant anatomical artifacts in the hands.
Explore each model
Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits