Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.
Settled by community votes across 15 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Turbo
#4 of 62 in Text-to-Image
OmniGen v2
#57 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
0%
win rate
Ties
0%
OmniGen v2
0%
win rate
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent photorealistic rendering of glass and wood textures.
- + Accurate spatial arrangement with the plant visible through the glass as requested.
- + Realistic soft window lighting from the left.
- − The glass cube has a thin vertical artifact line running behind the sphere.
OmniGen v2
- + Clean, vibrant colors and sharp focus on the central objects.
- + Perfectly rendered blue sphere with high specular highlight.
- − The glass cube appears to be filled with water, which was not requested.
- − The plant is entirely behind the cube and its visibility through the glass is distorted/unrealistic.
- − The book is floating slightly above the top edge of the glass.
Verdict: FLUX.2 [dev] Turbo produces a much more realistic and physically coherent scene that perfectly follows the request for a plant partially visible through the glass cube. OmniGen v2 has issues with spatial logic, such as the floating book and the glass appearing to be a tank filled with liquid rather than an empty cube.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent adherence to the 'imperfect framing' and 'motion blur' technical requirements.
- + Highly realistic skin textures and detailed mechanical components on the bicycle.
- + Superior rendering of wet pavement reflections and rainy atmosphere.
- − The anatomy of the front wheel and bike frame has some minor clipping issues near the basket.
- − The man's hands have slightly garbled finger details upon close inspection.
OmniGen v2
- + Clean composition with a very clear subject-background separation.
- + Good reflection quality on the wet asphalt.
- − Failed to include motion blur on passing cars as requested.
- − The bicycle is missing a chain connecting to the front sprocket.
- − Overall look is too clean and lacks the 'candid street photo' grit requested in the prompt.
Verdict: FLUX.2 [dev] Turbo followed the complex technical prompt much more effectively, successfully capturing the motion blur, imperfect framing, and cinematic realism requested. OmniGen v2 produced a generic, overly clean image that missed key prompt details like motion blur and had significant logical errors in the bicycle's anatomy (missing chain).
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent adherence to textural details like the weathered leather and engraved metal.
- + Very realistic depiction of braided hair with numerous small beads.
- + Authentic battle-worn appearance with convincing scars and dirt.
- − The torch in the background looks slightly like a floating object with a soft handle.
OmniGen v2
- + Warm lighting creates a strong dramatic effect on the gold-toned armor.
- + Clean composition with a clear focus on the face.
- − The character looks too pristine and 'glamorous' for the 'battle-worn' description.
- − The beads in the hair are sparse and look like plastic dots rather than integrated ornaments.
- − Texture on the cloth and leather is less defined compared to Model A.
Verdict: FLUX.2 [dev] Turbo significantly outperformed OmniGen v2 by capturing the 'battle-worn' essence of the prompt through grittier skin textures, realistic scars, and highly detailed engraving. OmniGen v2 produced a much cleaner, more stylized image that lacked the specific complex textures requested for the leather and underlayers.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent typography with clean, legible sans-serif fonts
- + Superior composition that looks like a real professional layout
- + Very high-quality food photography with realistic textures
- − Nonsensical pricing ($250 for a pizza)
- − Some text elements contain minor gibberish characters
OmniGen v2
- + Aesthetic use of color blocking for food backgrounds
- + Good variety of dish categories displayed
- − Poor spelling in headings ('APPTETIZES', 'PIZZZZAN', 'RESTAURATED MENTS')
- − The text content is largely unreadable placeholder scribbles
- − Composition feels sparse and less like a functional menu
Verdict: FLUX.2 [dev] Turbo produces a much more professional and realistic menu design that adheres to modern graphic design principles, especially in its typography and image grid. OmniGen v2 struggles significantly with spelling and produces illegible text for the menu descriptions, making it far less useful for this specific prompt.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent adherence to the 'exploded' burger concept with dynamic mid-air suspension.
- + Superior photographic texture and realism in the food components.
- + Perfectly executed fiery, glowing text effects for all requested elements.
- − The sauce droplets have a slightly unnatural, viscous shape.
OmniGen v2
- + Bold, clean graphic design suitable for a standard fast-food poster.
- + Integrated a starburst for the price as requested.
- − Failed to create an 'exploded' burger, showing a mostly assembled stack instead.
- − Text and price are missing the requested fiery/glowing effect, opting for flat colors.
- − The 'LIMITED TIME' text is partially cut off or poorly placed on the left edge.
Verdict: FLUX.2 [dev] Turbo significantly outperformed OmniGen v2 by accurately following the complex instruction for an 'exploded' burger and applying the fiery glow effect to the text. While OmniGen v2 produced a clean commercial image, it missed several key prompt details including the motion, the suspension of ingredients, and the specific text styling.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent text rendering with near-perfect spelling and coherent layout.
- + Highly realistic chalk texture with natural smudging and varied handwriting styles.
- + Excellent background integration within a believable café environment.
- − Repeated the price for the cookie item unnecessarily.
OmniGen v2
- + Followed the framing request with a simple wooden border.
- + Maintained a consistent white-on-black color scheme.
- − Numerous spelling errors including 'Specals', 'Musonhom', and 'Lemont'.
- − Text is jumbled and overlapping inSeveral areas, making it difficult to read.
- − Lacks the realistic chalk texture requested, looking more like a digital brush.
Verdict: FLUX.2 [dev] Turbo followed the prompt nearly perfectly, rendering complex menu items with high legibility and a very convincing chalk aesthetic. In contrast, OmniGen v2 struggled significantly with text accuracy and layout, resulting in many spelling errors and illegible overlapping characters. FLUX.2 also provided a much more realistic environmental context for the chalkboard.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent cinematic lighting and texture details on the spacesuit and horse.
- + Sophisticated background with realistic planetary bodies and nebulae.
- + Highly detailed and dynamic composition that feels epic and professional.
- − Failed the negative constraint; the astronaut is riding the horse, not vice-versa.
OmniGen v2
- + Cleaner, more graphical aesthetic with distinct colors.
- + The horse and astronaut are clearly defined with smooth shading.
- − Failed the negative constraint; the astronaut is riding the horse.
- − The background is very basic and lacks the requested cinematic quality.
- − Lower overall realism and detail compared to Model A.
Verdict: Both models failed the specific instruction to have the 'horse on top' of the astronaut, choosing instead to generate the standard trope of an astronaut riding a horse. FLUX.2 [dev] Turbo is the superior image due to its incredible cinematic detail, lighting, and complex background, whereas OmniGen v2 produced a much simpler, less detailed illustration.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent adherence to the prompt, placing the passenger in the back seat as requested.
- + Very realistic textures on the capybara's fur and the taxi's exterior/interior.
- + Captures the 'bored' expression of the passenger perfectly, creating a cohesive humorous scene.
- − The capybara's paws look slightly more like human hands than actual capybara paws.
- − The placement of the 'TAX' sign on the roof looks slightly detached from the vehicle body.
OmniGen v2
- + Clean, vibrant color palette with high contrast.
- + The capybara's face is very well-rendered and recognizable.
- − Fails the spatial prompt entirely by putting the passenger in the front passenger seat.
- − The steering wheel is being held by human hands that appear to belong to the capybara, creating a disturbing hybrid effect.
- − The passenger is looking at her phone with a slight smile rather than the requested bored expression.
Verdict: FLUX.2 [dev] Turbo successfully followed all spatial instructions, correctly placing the woman in the back seat and capturing the requested cynical, 'normal' atmosphere. OmniGen v2 failed significantly on composition, placing the woman in the front seat and merging human arms onto the capybara's body. FLUX.2 is the clear winner for its superior realism and prompt adherence.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent text rendering with no spelling errors.
- + Perfect adherence to all detailed prompt elements including the thorn border and scroll banner.
- + Sophisticated cinematic lighting and a cohesive vintage gothic aesthetic.
- − The jack-o-lantern's glow is slightly dull compared to the overall dark palette.
OmniGen v2
- + Strong vibrant colors and high contrast.
- + Good overall layout for an invitation.
- − Significant text errors including 'FRIGTS', 'THE ARCAS', and '7pum'.
- − Simplified vector-like illustration style lacks the requested 'vintage gothic' polish.
- − The small scroll banner contains illegible gibberish.
Verdict: FLUX.2 [dev] Turbo significantly outperforms OmniGen v2 by accurately rendering every requested text element with perfect spelling and an appropriate gothic font. While OmniGen v2 captures the general layout, its spelling failures and more cartoonish style do not meet the 'polished' and 'vintage' requirements of the prompt.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent text rendering and placement that feels professionally designed.
- + High-quality textures, especially the realistic rice grains and salmon marbling.
- + Perfect adherence to the Japanese flag icon request.
- − The lighting is a bit flat compared to the soft PBR look requested.
OmniGen v2
- + Strong isometric composition with a clear diorama base.
- + Bold, stylized cartoon aesthetic that matches one aspect of the prompt well.
- + Good use of shadows to ground the objects.
- − The 'flag' icon is incorrect, showing three horizontal stripes instead of the Japanese flag.
- − Text rendering is slightly less clean than Model A, with some minor artifacts.
- − The sushi design is a bit anatomically strange for 'miniature' style.
Verdict: FLUX.2 [dev] Turbo followed the prompt with high precision, particularly in the text elements and the specific flag icon. While OmniGen v2 captured the isometric diorama feel well, it failed at the flag detail and lacked the refined texture quality seen in the rice and fish of Model A.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent photorealism with detailed fur textures and life-like eyes.
- + Accurately includes all four requested animals: puppy, kitten, bunny, and fox.
- + Masterful use of lighting, dew drops, and atmospheric god rays.
- − None notable; the image follows all prompt instructions perfectly.
OmniGen v2
- + Bright, colorful, and cheerful aesthetic.
- + Clear, high-contrast subjects.
- − Failed the prompt's request for 'hyper-photorealistic' and '8K masterpiece' by using a cartoon/illustration style.
- − Missing the baby bunny requested in the prompt.
- − Lacks the complex interaction and tumbling described.
Verdict: FLUX.2 [dev] Turbo perfectly executed the prompt, delivering a hyper-realistic scene with all four animals and sophisticated lighting effects. OmniGen v2 failed the prompt's stylistic requirements, producing a digital illustration rather than a photo, and missed one of the required animals.
Studio Ghibli Anime Style
Editing“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”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent adherence to the 'hand-painted' texture and 'nostalgic' mood requested.
- + Highly accurate preservation of the source image poses and character expressions.
- + Sophisticated watercolor aesthetic with soft pastel tones and dreamy background elements.
- − The woman in the foreground is significantly less blurry than the source, changing the depth-of-field narrative slightly.
OmniGen v2
- + Successfully captures a generic anime style that is clean and readable.
- + Maintains the basic composition of the original meme perfectly.
- − Fails to capture the specific 'Ghibli' painterly look, opting for clean digital vectors instead.
- − Completely loses the original character expressions, making the girlfriend look happy instead of jealous.
- − Misses the 'soft pastel' and 'hand-painted' texture requirements.
Verdict: FLUX.2 [dev] Turbo is the clear winner as it perfectly captures the requested Studio Ghibli watercolor aesthetic, including the texture, lighting, and mood, while maintaining the specific emotional expressions of the source meme. OmniGen v2 produced a generic modern anime style and failed to preserve the core narrative element of the image—reciprocating the jealous expression of the woman on the right.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent preservation of the original image's lighting, textures, and details.
- + Highly effective interpretation of 'hair blowing in the wind' with realistic strand physics.
- + Abundant leaves add a strong sense of chaotic, dynamic motion.
OmniGen v2
- + Successfully modifies the hair to show motion.
- + Follows the instructions by adding leaves and wind effects.
- − Significant loss of source image fidelity, resulting in an 'AI-smoothed' or cartoonish look.
- − The leaves are sparse and look like flat clip-art rather than being part of the environment.
- − Distorts the dog's anatomy and the woman's facial features compared to the original.
Verdict: FLUX.2 [dev] Turbo is the clear winner as it performs a high-fidelity edit that preserves almost every pixel of the original background and subjects while overlaying the requested effects. In contrast, OmniGen v2 regenerates the image with a different stylistic look, losing the realistic texture of the original and introducing anatomical distortions in the dog.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent typography with perfect spelling and correct accent marks.
- + Superb paper texture that matches the requested vintage aesthetic.
- + Balanced composition with high-quality vector-style shading.
- − None
OmniGen v2
- + Follows the basic layout and color scheme requested.
- + Minimalist approach matches part of the prompt.
- − Spelling error in the main brand name ('CAFFFLORIN').
- − Lacks the subtle texture requested, appearing too flat.
- − The steam element is overly simplistic and less artistic.
Verdict: FLUX.2 [dev] Turbo produced a near-perfect result, accurately rendering all text including the accent in 'Caffè' and providing a sophisticated vintage texture. OmniGen v2 failed on text accuracy and lacked the professional detail and texture requested in the prompt.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent typography including correctly spelled names and stages.
- + Detailed icons that accurately represent the Saturn V and Lunar Module.
- + Comprehensive layout that includes all six requested steps plus astronaut portraits.
- − Layout is a bit cluttered with redundant elements like 'Translunar' and 'Landing Site' appearing twice.
- − Some stray vector lines and arrows overlap in the center.
OmniGen v2
- + Strong minimalist graphic design and color blocking.
- + Follows the NASA-inspired color palette strictly.
- − Severe spelling errors throughout (e.g., 'APOLO 17', 'NSA', 'LANDEN ATE COLINS').
- − Fails to follow the specific 6-step sequences requested.
- − Icons are generic and do not resemble the specific NASA hardware mentioned in the prompt.
Verdict: FLUX.2 [dev] Turbo significantly outperforms OmniGen v2 by providing a highly detailed, accurate, and legible infographic with complex vector illustrations. While OmniGen v2 has a clean grid layout, its failure to render the correct text or the specific imagery requested (like the Saturn V) makes it unusable compared to the comprehensive response from FLUX.2 [dev] Turbo.
Explore each model
Unified multimodal model for text-to-image generation, instruction-guided image editing, personalized generation, and virtual try-on