Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [max] Black Forest Labs Qwen Image Edit 2509 Alibaba

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

FLUX.2 [max]

25.8 arena score

#10 of 62 in Text-to-Image

Skill signature · Text-to-Image

Qwen Image Edit 2509

7.8 arena score

#32 of 32 in Image Editing

Vote tally

Where the votes landed

FLUX.2 [max]

0%

win rate

Ties

0%

Qwen Image Edit 2509

0%

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
FLUX.2 [max]
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Excellent preservation of the car's original geometry and details.
  • + Specifically preserved the man's hair, scarf, and coat pattern from the source image.
  • + High photorealism with accurate lighting on the coastline.
  • The man is placed in the right-hand seat (UK configuration) but the car's steering wheel appears to be on the left based on the dashboard shape.
  • The man's expression is a bit stiff compared to the source image.

Qwen Image Edit 2509

  • + Dynamic sense of motion with high-quality motion blur on the wheels and road.
  • + Excellent atmospheric lighting for a California coastal scene.
  • + Correctly places the man in the driver's seat for a US road.
  • Lost almost all specific details of the man's clothing and face from the source image.
  • Significant deformation of the car's headlights and front grille compared to the source.
  • Hair physics looks exaggerated and digitally stretched.

Verdict: FLUX.2 [max] is the winner for its exceptional ability to preserve the identity of both the man and the car from the source images, maintaining specific clothing patterns and the car's exact design. While Qwen Image Edit 2509 creates a more dynamic composition with better motion blur, it fails as an editing tool by losing the man's likeness and distorting the car's physical features.

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
FLUX.2 [max]
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Excellent character preservation, including sunglasses, scarf, and black clothing details from Image 2.
  • + Accurately recreates the pose and environment from Image 1.
  • + High anatomical realism and photographic quality.
  • The pose is slightly less extreme/compressed than the source image, with the legs positioned differently on the stool.

Qwen Image Edit 2509

  • + Maintains the exact background and stool from Image 1.
  • Completely failed to incorporate the character from Image 2.
  • Essentially just a lower-quality filtered version of Image 1.
  • Did not change the person, outfit, or features as requested.

Verdict: FLUX.2 [max] successfully performed the complex task of grafting the character's identity and outfit from Image 2 onto the dynamic pose of Image 1, though it modified the stool and legs slightly. Qwen Image Edit 2509 failed the prompt entirely, simply returning a stylized version of the first source image without any attributes from the second.

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
FLUX.2 [max]
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Excellent preservation of the subject's facial features and distinctive vitiligo patterns.
  • + High-fidelity recreation of the specific pea coat, plaid scarf, watch, and ring from Image 2.
  • + Superior lighting integration with natural-looking shadows that match the beach environment.
  • The crop is tighter than the original, losing the lower legs and feet requested in the prompt.
  • Slight alteration to the hair texture compared to Image 1.

Qwen Image Edit 2509

  • + Successfully includes the full body, including shoes, as requested in the prompt.
  • + Maintains the original composition and aspect ratio of the source image.
  • Failed to preserve the subject's face, blending it with the person from Image 2 and adding a mustache.
  • Low image quality with significant artifacts, smearing, and harsh contrast.
  • Anatomical issues with the legs and poor integration of the clothing onto the body.

Verdict: FLUX.2 [max] is the clear winner for its exceptional ability to preserve the subject's identity and perfectly replicate the requested clothing textures and accessories. While it cropped the image and missed the shoes, the quality and realism of the edit far surpass Qwen Image Edit 2509, which failed completely at the primary task of keeping the person's face unchanged.

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
FLUX.2 [max]
Before After
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Natural and realistic hair texture
  • + Excellent preservation of the original facial features and lighting
  • + The hair integrates perfectly with the sideburns and existing beard
  • None notable

Qwen Image Edit 2509

  • + Follows the instruction to add thick hair
  • + Good preservation of the background and clothing
  • The hair has a 'plastic' or overly styled look that feels artificial
  • The hair texture is too wavy and uniform compared to the natural beard texture

Verdict: FLUX.2 [max] is the winner as it provides a much more convincing and natural hair texture that matches the rugged aesthetic of the original image. Qwen Image Edit 2509 adds a significant amount of hair, but the texture is overly smooth and reflective, making it look like a wig rather than natural growth.

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
FLUX.2 [max]
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Excellent integration of all three themes: TV anchor, dogs, and hockey.
  • + High-quality digital illustration style with polished lighting and clean lines.
  • + Strong adherence to the caricature 'big head' style while maintaining subject likeness.
  • Text on the news desk and scoreboards is nonsensical.
  • The character is sitting on top of the hockey rink ice instead of in a booth.

Qwen Image Edit 2509

  • + Maintains the selfie perspective of the source image well.
  • + Incorporates a hockey player and rink in the background for context.
  • + The facial expression is highly exaggerated in line with traditional caricature humor.
  • The dog element is very small and feels like an afterthought compared to Model A.
  • Text in the speech bubble and screens is illegible.
  • Visual quality is slightly lower with more jagged lines and less refined shading.

Verdict: FLUX.2 [max] is the winner as it successfully incorporated all three requested elements (TV anchor, dogs, and hockey) into a cohesive and high-quality illustration. While Qwen Image Edit 2509 did a better job of maintaining the original selfie pose, it failed to give the dog element proper prominence and the overall artistic finish was less professional than FLUX.2 [max].

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
FLUX.2 [max]
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Captures the soft, hand-painted watercolor aesthetic of Studio Ghibli perfectly.
  • + Maintains the distinct textures and pastel lighting requested in the prompt.
  • + Preserves the composition and expressions of the original meme accurately.
  • The woman in the foreground is slightly more focused than the background compared to Ghibli's usual landscape-style depth.

Qwen Image Edit 2509

  • + Excellent preservation of the original image's layout and character features.
  • + Clean line work and colors that follow the prompt.
  • The style looks more like a modern digital webtoon or manhwa than the requested Studio Ghibli illustration.
  • Lacks the soft, textured, 'washy' watercolor feel inherent to the target aesthetic.

Verdict: FLUX.2 [max] is the clear winner as it perfectly captures the specific atmospheric and textural qualities of a Studio Ghibli film, using soft edges and painterly textures. Qwen Image Edit 2509 produces a high-quality illustration, but the style is too crisp and digital, missing the nostalgic and dreamy mood requested in the prompt.

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
FLUX.2 [max]
Before After
Qwen Image Edit 2509

AI Judge Analysis

FLUX.2 [max]

  • + Excellent integration of flying leaves with natural motion blur.
  • + Maintains the identity and facial features of the woman and dog perfectly.
  • + Highly realistic wind effect on the hair that flows naturally from the scalp.
  • The leash is slightly disconnected/broken compared to the source.

Qwen Image Edit 2509

  • + Successfully adds both blowing hair and flying leaves.
  • + Good preservation of the background and the dog's appearance.
  • The leaves look like flat clip-art stickers without depth or motion blur.
  • The hair rendering is a bit more stylized/painterly compared to the photographic source.
  • Small artifact on the woman's left hand where it grips the leash.

Verdict: FLUX.2 [max] provides a much more realistic edit, incorporating motion blur into the leaves and hair which makes the 'wind' feel authentic to the scene. Qwen Image Edit 2509 successfully follows the instructions but the added elements lack the necessary lighting and motion integration, appearing more like an overlay.

Next steps

Explore each model