Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Settled by community votes across 15 shared challenges, with an AI judge weighing in on each.
FLUX.2 [max]
#10 of 62 in Text-to-Image
OmniGen v2
#57 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [max]
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 [max]
- + Excellent photorealistic rendering of glass and mirror reflections
- + Highly detailed book texture and realistic lighting
- + Perfect adherence to all spatial instructions including the plant behind the glass
- − The glass cube is more of a glass frame/display case with a mirrored base rather than a solid glass object
OmniGen v2
- + Successfully includes all core elements of the prompt
- + Clean composition with vibrant colors
- + Good representation of the glass cube's form
- − Lower overall visual fidelity compared to the competitor
- − The 'plant behind the cube' is mostly just behind the cube, with less clear visibility through the glass itself
- − The lighting feels a bit more flat and generic
Verdict: FLUX.2 [max] produces a significantly more realistic and detailed result with sophisticated lighting and material textures. While OmniGen v2 follows the prompt well, it lacks the professional photographic quality and intricate reflections found in FLUX.2 [max].
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 [max]
- + Excellent adherence to the 'repairing' action with tools visible on the ground.
- + Highly realistic motion blur on the background vehicles.
- + Superior skin texture and natural lighting that captures a documentary-style aesthetic.
- − The composition is a bit tight on the bicycle frame.
- − A minor physics issue with the bicycle seat being slightly high relative to the frame style.
OmniGen v2
- + Strong reflections on the wet pavement.
- + Good color contrast between the red bike and the green trees in the background.
- − Failed the core 'repairing' prompt; the man is simply standing with the bike.
- − The rain effect looks like a digital filter rather than natural precipitation.
- − Noticeable anatomy issues with the hands merged into the handlebars.
Verdict: FLUX.2 [max] is the clear winner as it successfully captured the 'repairing' interaction and the gritty, cinematic realism requested in the prompt. OmniGen v2 failed on most technical aspects, including the specific action, and suffered from artificial-looking rain and significant AI artifacts in the hands and bicycle structure.
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 [max]
- + Excellent adherence to textural details like weathered leather and scratched metal.
- + Highly realistic skin rendering with convincing scars and dirt.
- + Complex, ornate engraving on the plate armor that looks physically authentic.
- − The braids are somewhat messy or blended into the hair structure rather than being distinct clean braids.
OmniGen v2
- + Clean, distinct braids that clearly follow the prompt's request for beads.
- + Strong, vibrant lighting with a clear bokeh effect in the background.
- + Symmetric and aesthetically pleasing facial features.
- − Armor looks too clean and 'smooth' despite the 'battle-worn' and 'engraved' prompts.
- − Dirt on the face looks like digital specks rather than realistic grime.
- − Overall lacks the gritty, high-fidelity texture of the cloth and leather requested.
Verdict: FLUX.2 [max] is the clear winner as it perfectly captures the 'battle-worn' aesthetic with incredible textural detail on the armor, leather, and skin. OmniGen v2 produces a much cleaner, more 'cosplay' style image that misses the gritty realism and fine surface detail requested in the prompt.
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 [max]
- + Excellent typography and readability for main section headers.
- + Professional grid layout with high-quality, consistent food photography.
- + Accurate adherence to requested sections: Appetizers, Pizza, and Mains.
- − Placeholder text beneath headers contains gibberish spelling.
- − Misalignment between headers and the food photos displayed next to them (e.g., sandwiches next to 'Appetizers').
OmniGen v2
- + Strong use of vibrant color blocks in the grid design.
- + Maintains a clean minimalist aesthetic across a two-page spread.
- − Significant spelling errors in every headline (e.g., 'RESTAURATED MENTS', 'APPTETIZES').
- − The small body text is completely illegible 'greeking' or lines.
- − Composition feels scattered with too much white space between related elements.
Verdict: FLUX.2 [max] produces a much more functional and professional menu design with clear, bold typography and realistic food imagery that fits the 'casual dining' brief. While OmniGen v2 has a nice creative use of color accents, it fails significantly on text rendering and logical layout, making it unusable as a design template.
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 [max]
- + Excellent adherence to the 'exploded' and 'suspended' burger requirement
- + Professional level typographical integration with fiery effects
- + Highly photorealistic textures on the bun and vegetables
- − The starburst graphic is a bit flat compared to the realism of the burger
OmniGen v2
- + Strong, clean graphic design suitable for a cartoonish style
- + Good use of the fiery background
- + All required text elements are present
- − Failed to create an 'exploded' burger, showing it fully assembled instead
- − Missing the euro symbol (€) in the price
- − Less photorealistic and more illustrative/rendered in style
Verdict: FLUX.2 [max] significantly outperformed OmniGen v2 by accurately following the complex instruction for an 'exploded' burger with suspended components. While OmniGen v2 produced a clear graphic, it failed the primary spatial composition request and missed the price's currency symbol, whereas FLUX.2 [max] achieved high photorealism and dynamic motion.
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 [max]
- + Perfect text rendering with zero spelling errors.
- + Realistic chalk texture including smudges and dust on the board.
- + Excellent lighting and atmospheric cafe setting.
- − The 'Brown Butter' text is cut off slightly early, though it captures the essence of the prompt well.
OmniGen v2
- + Attempts a variety of handwriting styles as requested.
- + Handled the wooden frame border clearly.
- − Significant spelling errors and illegible characters throughout the text.
- − Poor layout with text overlapping and messy formatting.
- − Failed to render the specific menu items accurately.
Verdict: FLUX.2 [max] significantly outperforms OmniGen v2 by producing a near-perfect, professional-looking chalkboard with crisp, accurate text and realistic chalk physics. OmniGen v2 struggled with basic legibility, spelling, and compositional logic, resulting in a cluttered and confused image.
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 [max]
- + Excellent cinematic lighting and atmospheric depth in the space background.
- + High level of texture detail on the astronaut suit and horse's fur.
- + Dynamic composition with the inclusion of an asteroid and a spiral galaxy.
- − Failed the negative constraint to have the horse on top of the astronaut.
- − The horse's legs are clipping through the asteroid
OmniGen v2
- + Clean, illustrative style with bold colors.
- + Good anatomical consistency for the horse and astronaut.
- − Failed the negative constraint to have the horse on top of the astronaut.
- − The composition is quite flat and lacks the 'cinematic' and 'surreal' quality requested.
- − Floating moons look poorly integrated into the background.
Verdict: Both models failed to follow the specific spatial instruction for the horse to be 'on top' of the astronaut, instead defaulting to the standard horse-riding trope. However, FLUX.2 [max] is significantly better in terms of visual quality, offering a cinematic and detailed environment, whereas OmniGen v2 produced a flat, generic image that lacks the requested surrealism.
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 [max]
- + Excellent photorealistic lighting and depth of field
- + Accurate depiction of a capybara's head and fur texture
- + Correct placement of the passenger in the back seat
- − Gave the capybara human hands instead of front paws
- − Small anatomical glitch in the human passenger's hand
OmniGen v2
- + Strong composition and vibrant colors
- + Captures the bored expression of the businesswoman well
- − Incorrectly placed the passenger in the front seat
- − Used human hands for the capybara
- − Lower level of photorealism compared to Model A
Verdict: FLUX.2 [max] produced a much more realistic and atmospherically accurate scene, correctly placing the passenger in the back seat as requested. While both models failed by giving the animal human hands, FLUX.2 [max] is the superior image due to its superior lighting, texture, and composition which better captures the requested 'New York at night' vibe.
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 [max]
- + Excellent typography with perfect spelling in all requested sections.
- + Cinematic lighting and high-quality textures on the pumpkin and parchment.
- + Creative and effective use of the thorns and spiderwebs as a natural border.
- − The parchment texture is slightly modern around the edges rather than looking like an old scroll.
OmniGen v2
- + Stronger 'vintage parchment' aesthetic for the main card backing.
- + Good use of color contrast between the moon and the silhouettes.
- − Multiple spelling errors and garbled text in the scroll and event details.
- − More cartoony aesthetic that lacks the 'cinematic' polish requested.
- − Layout is cluttered with overlapping and repetitive text elements.
Verdict: FLUX.2 [max] significantly outperforms OmniGen v2 by providing a professional, polished design with 100% accurate text rendering. While OmniGen v2 captures a nice vintage paper feel, its failure to correctly spell the invitation details and its somewhat amateurish illustration style make it much less usable for its intended purpose.
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 [max]
- + Excellent adherence to the isometric diorama request with a tiered base.
- + Perfect text rendering and accurate Japanese flag icon.
- + Higher detail in the sushi variety including nigiri and maki.
- − Texture on the salmon looks slightly more matte than 'realistic PBR' expectations.
OmniGen v2
- + Bright, vibrant colors that fit a 3D cartoon aesthetic.
- + Clear 3D-styled text with drop shadows.
- + Good sense of volume in the sushi models.
- − Failed to render the correct Japanese flag, showing a generic yellow and red flag instead.
- − The sushi design is nonsensical, combining a nigiri-style topping with a maki-style roll interior.
- − Composition is less isometric and more of a standard 3D perspective.
Verdict: FLUX.2 [max] followed the prompt more accurately, providing a true isometric diorama and a correct flag icon. While OmniGen v2 produced a vibrant image, it failed on the specific cultural icon (flag) and created anatomically incorrect sushi that merged different styles awkwardly.
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 [max]
- + Excellent adherence to the prompt by including all four requested animals correctly.
- + Achieves a high level of photorealism with detailed fur textures and realistic lighting.
- + Natural, dynamic composition that captures the requested action of 'tumbling together'.
- − The fox kit has black front legs which is common but the overall anatomy is slightly merged with the puppy's space.
OmniGen v2
- + Bright, vibrant colors that evoke a joyful vibe.
- + Clear, large expressive eyes on the characters.
- − Failed to include the baby bunny requested in the prompt.
- − The style is high-contrast 3D animation rather than the requested 'hyper-photorealistic' masterpiece.
- − The butterflies are disproportionately large and basic in design.
Verdict: FLUX.2 [max] followed the prompt strictly, including the puppy, kitten, bunny, and fox in a realistic, beautifully lit scene. OmniGen v2 missed the bunny entirely and produced a stylized, cartoon-like image that ignored the 'photorealistic' requirement.
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 [max]
- + Perfectly captures the Studio Ghibli watercolor aesthetic with hand-painted textures.
- + Preserves the exact poses, expressions, and clothing details of the original meme.
- + Excellent use of soft pastel colors and a hazy, nostalgic atmosphere.
OmniGen v2
- + Matches the general positioning of the characters in the source image.
- + Provides a clean, vibrant anime-style illustration.
- − Fails to capture the specific Ghibli texture, looking more like standard digital vector art.
- − Changes the girlfriend's facial expression from angry/shocked to a neutral or smiling look, losing the meme's context.
- − The background and lighting are too sharp and modern, missing the 'dreamy' and 'soft' requirements.
Verdict: FLUX.2 [max] is the clear winner as it successfully transposes the meme into a Studio Ghibli style while maintaining the integrity of the original photo's composition and emotions. OmniGen v2 provides a generic anime style and fails to preserve the crucial jealous expression of the woman on the right, which is essential to the source image's identity.
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 [max]
- + Excellent adherence to the 'windy' hair request with natural-looking movement
- + High quantity and variety of falling leaves that look integrated with the scene
- + Perfect preservation of the original subjects and background details
- − Some leaves in the foreground are slightly blurry, though this adds to the motion feel
OmniGen v2
- + Successfully applied hair movement and added falling leaves
- + Maintained the overall composition of the source image
- − Significant change in the lighting and texture, making the image look more saturated and 'AI-generated' than the original
- − The leaves look like flat clip-art superimposed on the image rather than physical objects in the scene
- − Subtle changes to the woman's facial features and the dog's fur texture
Verdict: FLUX.2 [max] performed a near-perfect edit by seamlessly integrating hair movement and realistic leaves while leaving the rest of the image untouched. OmniGen v2 failed to preserve the source image's integrity, fundamentally altering the lighting and textures of the characters, resulting in a less realistic and less accurate edit.
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 [max]
- + Excellent typography including the requested accent mark on 'Caffè'.
- + Beautifully executed subtle paper texture that matches the vintage theme.
- + Sophisticated vector emblem layout with balanced circular framing.
- − The 'Est. 1720' text is slightly off-center within the banner.
OmniGen v2
- + Strong minimalist aesthetic with high contrast.
- + Good quality line work on the cloche icon.
- + Clear, bold presentation of the 'Est. 1720' text.
- − Significant spelling error in the main brand name ('CAFFFLORIN').
- − Lacks the subtle texture requested in the prompt.
- − The banner layout is a bit clunky with overlapping dark elements.
Verdict: FLUX.2 [max] followed the prompt nearly perfectly, delivering a professional-grade logo with accurate spelling, a classic accent mark, and the requested vintage texture. OmniGen v2 failed on the text rendering, misspelling the brand name and missing the accent, while also ignoring the request for a textured background.
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 [max]
- + Excellent typography with mostly correct spelling of astronaut names and mission phases.
- + Clean, modern flat-vector aesthetic that perfectly matches the requested NASA-inspired palette.
- + Logical layout that shows the progression of the mission with relevant icons.
- − Incorrectly labels the first module as 'Earth Orbit' instead of 'Launch'.
- − The rocket icon looks more like a generic shuttle than a Saturn V.
OmniGen v2
- + Stronger vector-style graphic design with bold circular icons.
- + Accurately represents the requested muted red and navy color scheme.
- − Severe spelling errors throughout the text (e.g., 'Apolo 17', 'NSA', 'ALDD').
- − Fails to follow the 6-step mission sequence requested in the prompt.
- − Confuses Apollo 11 with Apollo 17.
Verdict: FLUX.2 [max] is the clear winner as it successfully follows the complex instructions for a multi-step infographic with readable, mostly accurate text. While it has some labeling repetition, OmniGen v2 fails significantly on text legibility and mission accuracy, even getting the mission number wrong.
Explore each model
Unified multimodal model for text-to-image generation, instruction-guided image editing, personalized generation, and virtual try-on