Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [flex] Black Forest Labs OmniGen v2 VectorSpaceLab

Settled by community votes across 15 shared challenges, with an AI judge weighing in on each.

FLUX.2 [flex]

24.8 arena score

#14 of 62 in Text-to-Image

Skill signature · Text-to-Image

OmniGen v2

16.9 arena score

#56 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [flex]

0%

win rate

Ties

0%

OmniGen v2

0%

win rate

Shared challenges 15

Challenge by challenge

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

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent photographic quality with realistic depth of field.
  • + Accurate glass refraction and reflections including the sphere's reflection on the bottom glass.
  • + Soft lighting feels natural and consistent with the left-side window source.
  • The sphere appears slightly large relative to the word 'small' in the prompt.

OmniGen v2

  • + Successfully includes all requested elements in the correct positions.
  • + Bright, saturated colors make the blue sphere and red book pop.
  • + Clearly shows the plant through the glass as requested.
  • The red book is floating noticeably above the top surface of the glass cube.
  • Physics issues with the sphere appearing to float above the bottom of the cube.
  • The perspective of the cube's top edge is slightly distorted.

Verdict: FLUX.2 [flex] produces a much more realistic and physically grounded image, with impressive handling of glass reflections and material textures. OmniGen v2 correctly identifies all prompt elements but suffers from significant alignment issues, such as the book and sphere appearing to float without contact.

Candid Street Photography

Text-to-Image

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent adherence to the 'imperfect framing' and 'candid' street photography style.
  • + Realistic motion blur on passing vehicles and high-quality skin texture.
  • + Authentic bicycle mechanics and repair posture.
  • The bike frame geometry is slightly warped near the front.

OmniGen v2

  • + Strong reflections on the wet pavement.
  • + Clear depiction of light rain.
  • Fails to show the man 'repairing' the bike; he is simply standing over it.
  • Lacks the requested motion blur on cars and 50mm shallow depth of field effect.
  • The composition feels too centered and staged rather than candid.

Verdict: FLUX.2 [flex] successfully captured all the technical nuances of the prompt, including the specific lens feel, candid framing, and motion blur. OmniGen v2 failed on several key instructions, presenting a man just standing with a bike rather than repairing it, and missing the realistic motion effects.

Fantasy Warrior

Text-to-Image

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Exquisite detail on the engraved plate armor and leather straps.
  • + Excellent facial skin texture with realistic scars and dirt.
  • + Perfect adherence to all prompt elements including beads, sparks, and lighting.

OmniGen v2

  • + Smooth, aesthetically pleasing facial features.
  • + Good bokeh effect in the background.
  • Texture on the armor is soft and lacks the requested intricate engravings.
  • The 'dirt' on the face appears like stamps rather than organic grime.
  • Fails to show significant wear or authentic battle-worn characteristics.

Verdict: FLUX.2 [flex] successfully captured all the fine details of the prompt, particularly the 'ornate engraved plate armor' and the 'texture on leather straps' which were highly realistic. OmniGen v2 produced a cleaner, more idealized image that lacked the grit, complex textures, and authentic 'battle-worn' feeling requested.

Modern Clean Menu

Text-to-Image

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent typography with clean, legible sans-serif fonts
  • + Professional grid layout that looks like a real-world menu
  • + Accurate food item headers including Pizza and Mains
  • Internal category logic is slightly confused (e.g., Bruschetta listed under Pizza section)
  • Text descriptions are mostly gibberish despite clear headers

OmniGen v2

  • + Colorful and vibrant food photography
  • + Includes a double-page spread layout with distinct color blocks
  • Significant spelling errors in all headers (e.g., 'PIZZZZAN', 'APPTETIZES')
  • Body text is completely illegible pixel noise
  • Messy composition that lacks the professional 'modern minimalist' feel

Verdict: FLUX.2 [flex] successfully captures the modern minimalist aesthetic with a clean, functional layout and high-quality typography that makes it look like a usable design template. In contrast, OmniGen v2 suffers from severe spelling errors, illegible text, and a cluttered composition that fails to meet the professional standard requested.

Magic Burger Explosion: Fiery Photorealism Challenge

Text-to-Image

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent typography with a glowing fire effect that matches the background
  • + Superior photorealistic textures on the lettuce, patty, and buns
  • + Dynamic 'exploded' composition with believable physics and floating particles
  • The starburst for the price is a bit large and overlaps the burger slightly

OmniGen v2

  • + Matches the 'starburst' shape for the price point well
  • + Clean graphic design suitable for a mobile app or casual game icon
  • The burger is not exploded or suspended as requested
  • Text is cut off and lacks the 'fiery' rendering style
  • Lower visual quality with a more cartoonish, less photorealistic appearance

Verdict: FLUX.2 [flex] far outperformed OmniGen v2 by accurately following the 'exploded burger' instruction and delivering high-end photorealistic textures. OmniGen v2 failed to separate the burger components, cut off the secondary text, and produced a flatter, more illustrative style that lacked the requested dynamic energy.

Chalkboard Menu

Text-to-Image

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent text rendering with perfect spelling across all items.
  • + Highly realistic chalk texture with smudges and natural variations.
  • + Perfect adherence to the requested date and price details.

OmniGen v2

  • + Includes handwritten-style variations in letter size.
  • Numerous spelling errors including 'SPECALS', 'Musonhom', and 'Lemont'.
  • Text is messy, overlapping, and disorganized.
  • Failed to correctly render the requested prices and full menu item names.

Verdict: FLUX.2 [flex] produced a professional, legible, and aesthetically pleasing chalkboard that followed every detail of the prompt perfectly. OmniGen v2 struggled significantly with spelling, composition, and logical text flow, resulting in an unreadable menu.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent adherence to the 'horse on top' spatial instruction
  • + Highly detailed and cinematic background with realistic nebula and asteroid belt effects
  • + Expressive lighting and dynamic posing of both the horse and astronaut
  • The horse's front legs are morphing into the astronaut's hands in a slightly messy way

OmniGen v2

  • + Clear, clean digital art style
  • + Good representation of space elements like moons and stars
  • Completely failed the key instruction to have the horse on top
  • The horse's legs are cut off at the bottom and lack interaction with the environment
  • Composition is very static and lacks the requested cinematic feel

Verdict: FLUX.2 [flex] successfully followed the difficult spatial constraint of placing the horse on top of the astronaut, resulting in a unique and surreal image that fits the prompt. OmniGen v2 ignored the specific 'not vice versa' instruction and produced a generic image of an astronaut riding a horse. FLUX.2 [flex] is the clear winner for its superior prompt adherence and artistic detail.

The Capybara Taxi Driver

Text-to-Image

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent photorealism with detailed textures on the capybara fur and jacket.
  • + Accurate composition with the passenger in the back seat as requested.
  • + Realistic New York street bokeh and lighting integration through the window.
  • The capybara's hands are a bit humanoid, appearing more like primate hands than capybara paws.

OmniGen v2

  • + Accurately depicts the capybara wearing a dark jacket and a cap.
  • + Clear focus on the central subject.
  • Severe logic failure where the woman sitting behind the driver has human arms growing out of her that are steering the car.
  • The woman is sitting in the front/middle rather than the back seat.
  • The capybara lacks front paws on the steering wheel as requested.

Verdict: FLUX.2 [flex] successfully captures the entire scene including the specific placement of the passenger in the back seat and a high level of realistic detail. OmniGen v2 fails significantly on anatomical logic, depicting the passenger's arms reaching around the driver to steer the vehicle while the capybara has no arms at all.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent typography and spelling accuracy for all requested text.
  • + High-quality, cinematic lighting on the central jack-o-lantern.
  • + Authentic vintage parchment texture with integrated gothic border elements.
  • The twisted trees in the background are somewhat blurry and lack fine detail.

OmniGen v2

  • + Strong, vibrant color contrast between the silhouettes and the glowing background.
  • + Creates a clear, graphic layout.
  • Numerous spelling errors and garbled text throughout the secondary details.
  • The text layout is messy, with information overlapping and repeating.
  • Fails to render the 'scroll banner' correctly, using a stylized ribbon with gibberish instead.

Verdict: FLUX.2 [flex] significantly outperforms OmniGen v2 by providing perfect text rendering and a sophisticated, atmospheric composition that adheres strictly to the gothic aesthetic. While OmniGen v2 has good color contrast, its failure to spell basic words and its disorganized layout make it unusable as a functional invitation.

Isometric Miniature Diorama Scenes

Text-to-Image

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent typography rendering with clean, black font.
  • + Accurate representation of the Japanese flag.
  • + High-quality soft textures and realistic lighting that match the 'miniature' aesthetic.
  • The diorama base is very thin and lacks the distinct 'raised block' feel found in some isometric art.

OmniGen v2

  • + Good isometric 3D perspective and diorama base construction.
  • + Strong vibrant colors that create high visual impact.
  • The flag icon is incorrect, showing a yellow and red stripe instead of the Japanese flag.
  • The text rendering has slight artifacts and inconsistent drop shadows.
  • The sushi design is somewhat repetitive and less detailed than model A.

Verdict: FLUX.2 [flex] is the clear winner as it followed every instruction, specifically the inclusion of a correct Japanese flag and perfectly rendered text. OmniGen v2 failed the flag requirement and provided slightly lower quality text rendering, though it did have a nice stylized diorama base.

Adorable Baby Animals in Sunny Meadow

Text-to-Image

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent adherence to the 'hyper-photorealistic' instruction with realistic fur and lighting.
  • + Correctly includes all four requested animals (dog, cat, rabbit, fox).
  • + Beautiful implementation of god rays, dew sparkles, and a complex wildflower meadow.
  • The fox's front right leg has a slightly awkward joint angle during movement.

OmniGen v2

  • + Bright, saturated colors that fit a 'joyful' vibe.
  • + The animals are centered and clearly visible.
  • Failed to include the requested baby bunny.
  • The style is cartoonish/3D render rather than the requested 'hyper-photorealistic'.
  • The anatomy of the fox is highly stylized and not anatomically realistic.

Verdict: FLUX.2 [flex] significantly outperformed OmniGen v2 by following every prompt instruction, including proper animal counts and a high-fidelity photorealistic style. OmniGen v2 missed the rabbit entirely and defaulted to a generic 3D animation style that disregarded the 'hyper-photorealistic' requirement.

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 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Perfectly captures the hand-painted, soft-textured watercolor style of Studio Ghibli.
  • + Highly accurate preservation of the source image composition and character poses.
  • + Uses the requested soft pastel color palette beautifully.
  • The characters' expressions are slightly softened, losing a bit of the 'shocked' intensity of the original meme.

OmniGen v2

  • + Successfully translates the scene into a clean anime aesthetic.
  • + Maintains clear character recognition from the original photo.
  • The facial expressions are changed too much; the man and the girlfriend both look happy/neutral rather than the iconic distracted/angry look.
  • The art style feels more like modern digital vector art than the requested 'hand-painted' Ghibli style.
  • The colors are too saturated and bold, missing the 'soft pastel' requirement.

Verdict: FLUX.2 [flex] is the clear winner as it perfectly captured the specific 'hand-painted watercolor' aesthetic of Studio Ghibli while maintaining the exact composition and poses of the iconic meme image. OmniGen v2 produced a generic anime style with digital flat coloring and failed to preserve the core emotional narrative of the original image, making the characters look cheerful instead of conflicted.

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 [flex]
Before After
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent preservation of the original person and dog's identity.
  • + Realistic hair movement that fans out naturally.
  • + High density of green leaves matches the lush summer background.
  • Some leaves appear to be floating rather than flying through the scene.

OmniGen v2

  • + Successfully added both hair motion and flying leaves.
  • + Good color contrast between the orange leaves and green background.
  • Significantly altered the face of the woman compared to the source image.
  • Heavy smoothing/filtering applied to the entire image, losing the original texture.
  • The character's hair becomes much longer and changes structure.

Verdict: FLUX.2 [flex] wins this challenge because it successfully applied the requested edits while maintaining the integrity of the original photo's subjects. OmniGen v2 failed on source preservation, significantly changing the woman's face and the overall texture and style of the image.

Vintage Cafe Logo

Text-to-Image

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent typography including the grave accent on 'Caffè'.
  • + Perfect adherence to all prompt elements including the banner and steam.
  • + Clean, professional vector aesthetic suitable for an actual logo.
  • Texture is very subtle, almost unnoticeable.

OmniGen v2

  • + Strong 'vintage' color palette with high contrast.
  • + Good use of the cloche dome as a central graphic element.
  • Significant spelling error in the primary text ('CAFFFLORIN').
  • Lacks the accent on the 'e' as requested in the brand name.
  • The composition feels a bit cramped compared to the other model.

Verdict: FLUX.2 [flex] provides a superior logo that accurately renders the requested text 'Caffè Florian' and successfully integrates the 'Est. 1720' banner. OmniGen v2 fails on basic prompt adherence by misspelling the brand name and omitting several requested characters.

Apollo 11: Journey to Tranquility

Text-to-Image

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

FLUX.2 [flex]
OmniGen v2

AI Judge Analysis

FLUX.2 [flex]

  • + Excellent text rendering with accurate spelling of all mission phases.
  • + Clean, professional vector aesthetic that perfectly matches the 'modern infographic' request.
  • + Consistent and high-quality iconography representing the Saturn V and Lunar Module.
  • Omitted the final step (Landing on the surface) despite labeling 'Descent'.
  • The layout of the translunar trajectory is a bit fragmented across the center line.

OmniGen v2

  • + Follows the color palette requirements accurately.
  • + Attempts a structured grid layout common in infographics.
  • Severe spelling errors throughout, including 'APOLO 17' and 'NSA'.
  • Iconography is generic and abstract, failing to clearly represent specific mission steps like the Saturn V.
  • Incorrect mission number (17 instead of 11).

Verdict: FLUX.2 [flex] is the clear winner as it produced a highly professional, readable, and aesthetically pleasing infographic with perfect text rendering. While OmniGen v2 adhered to the color scheme, it failed significantly on text accuracy, mission facts, and the specific iconography requested in the prompt.

Next steps

Explore each model