Black Forest Labs' state-of-the-art image generation model with maximum quality and speed, supporting text-to-image and multi-reference image editing with up to 4MP output
Settled by community votes across 15 shared challenges, with an AI judge weighing in on each.
FLUX.2 [pro]
#8 of 62 in Text-to-Image
OmniGen v2
#57 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [pro]
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 [pro]
- + Excellent photo-realism with natural textures on the book and table.
- + Very accurate glass refraction and reflections.
- + Superior depth of field and soft lighting that matches the requested window light source.
- − The plant in the background is quite blurry, making it less distinct through the glass.
OmniGen v2
- + Perfect adherence to all prompt elements including the specific placement of objects.
- + The blue sphere has a vibrant, glossy finish.
- + The plant is clearly visible through the glass cube as requested.
- − The book has a slightly 'CG' or artificial look compared to Model A.
- − The base of the glass cube looks thick and somewhat murky, less like pure glass.
Verdict: Both models followed the complex spatial prompt perfectly. FLUX.1 [pro] produced a more sophisticated, photorealistic image with beautiful lighting, while OmniGen v2 provided a clearer view of the plant through the glass at the cost of some realism in the textures.
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 [pro]
- + Excellent adherence to the 'candid' and 'imperfect framing' prompts
- + Highly realistic skin texture and environmental details like the puddle ripples
- + Captures a believable 50mm shallow depth of field with cinematic lighting
- − The structural layout of the bicycle chain and rear frame is slightly nonsensical
OmniGen v2
- + Reflections on the wet pavement are clear and well-defined
- + The bicycle is logically rendered in terms of basic components
- + Clean color palette with vibrant reds
- − Lacks the requested 'short depth of field' and 'motion blur' effects
- − The man is standing and holding the bike rather than 'repairing' it
- − The rain effect looks like a static overlay rather than a natural environmental element
Verdict: FLUX.2 [pro] followed the complex technical requirements of the prompt much better, capturing the cinematic lighting, shallow depth of field, and the specific action of repairing the bike. OmniGen v2 produced a cleaner but more generic image that failed to incorporate the requested motion blur and candid aesthetic, resulting in a less realistic 'staged' feel.
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 [pro]
- + Excellent texture on leather straps and armor engraving
- + Strong adherence to 'battle-worn' with realistic scars and dirt
- + Captures the braided hair with beads very effectively
- − Lighting is a bit harsh on the forehead and side of the face
- − The beads in the hair are a bit varied in color, which may not suit all interpretations of the prompt
OmniGen v2
- + Soft, cinematic lighting with a pleasing bokeh background
- + Clean composition with clear focus on the face
- + Features detailed braided hair as requested
- − Lacks the 'battle-worn' aesthetic; skin looks too clear and dirt looks like makeup
- − Armor engraving is less intricate than the competitor
- − Does not capture the grit or textile textures as specified in the prompt
Verdict: FLUX.2 [pro] followed the prompt much more closely, delivering a gritty, battle-worn character with hyper-detailed textures on the leather and metal. OmniGen v2 produced a cleaner, more stylized image that lacked the requested wear-and-tear and 'lifelike' skin textures. FLUX.2 [pro] is the clear winner for its superior technical detail and prompt adherence.
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 [pro]
- + Excellent typography with mostly legible text and prices
- + Very clean, professional layout that matches high-end desktop publishing
- + Strong adherence to section requests including appetizers, pizza, and mains
- − Repeated use of the same dish names (Margherita Pizza) across different categories
- − Minor spelling error in the 'MINS' (Mains) heading
OmniGen v2
- + Dynamic use of color blocks and varied food photography
- + Good use of white space to create a modern minimalist feel
- − Severe spelling issues in almost every heading (e.g., 'RESTAURATED MENTS', 'PIZZZZAN')
- − Text body is mostly illegible scribble or lines
- − The layout feels more like a template placeholder than a finished menu
Verdict: FLUX.2 [pro] produced a realistic and usable menu design with clean bold fonts and a logical structure, despite some repetitive naming of items. OmniGen v2 struggled significantly with text rendering and basic spelling, resulting in a layout that feels much less professional and lacks the functional clarity of its competitor.
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 [pro]
- + Excellent typography with a glowing fire effect that perfectly matches the background.
- + Highly realistic food textures on the patties, lettuce, and bun.
- + Dynamic 'exploded' composition that follows the suspended in mid-air instruction.
- − The starburst for the price is a bit modern and sterile compared to the fiery theme.
OmniGen v2
- + Bold, bright colors that create a high-impact advertisement look.
- + Clear and legible main logo text.
- − Failed to create an 'exploded' burger, showing an almost fully assembled one instead.
- − The secondary text 'LIMITED TIME ONLY' is partially cut off and poor quality.
- − The burger looks like a plastic render rather than photorealistic food.
Verdict: FLUX.2 [pro] followed every aspect of the prompt, including the difficult 'exploded' burger requirement and the specific fiery effects for the text. OmniGen v2 failed to separate the burger components and struggled with the secondary text and overall realism, resulting in a much more generic and less professional-looking ad.
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 [pro]
- + Excellent text rendering with perfect spelling of all requested items.
- + Highly realistic chalk texture, including dust and natural stroke variations.
- + Sophisticated composition with a convincing café atmosphere in the background.
- − The 'Brown Butter' item is truncated, though it follows the prompt's cut-off text style.
OmniGen v2
- + Features a clear wooden frame around the chalkboard.
- + Includes all information requested despite spelling errors.
- − Contains numerous spelling errors and gibberish characters like 'Specals' and 'glite free'.
- − The text looks more like a digital brush than authentic chalk handwriting.
- − The layout is cluttered and messy, with overlapping prices and garbled words.
Verdict: FLUX.2 [pro] significantly outperformed OmniGen v2 by providing perfect text legibility, realistic chalk textures, and a believable aesthetic. OmniGen v2 struggled with basic spelling and failed to produce a coherent layout, resulting in overlapping text and numerous typographical artifacts.
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 [pro]
- + Strictly followed the difficult spatial instruction of horse on top of astronaut.
- + Exceptional cinematic detail in the spacesuit texture and the planetary background.
- + Effective surreal atmosphere with multiple galaxies and floating elements.
- − The anatomy is slightly glitched where the horse's legs merge with the astronaut's backpack.
- − Features a secondary floating horse body that adds confusion to the composition.
OmniGen v2
- + Clean, vibrant colors and high contrast.
- + Technically coherent anatomy for both the horse and the astronaut.
- − Main prompt instruction failed: the astronaut is on top of the horse.
- − Visual style is more illustrative/clip-art than 'cinematic' or 'highly detailed'.
- − Composition is very basic with a flat blue background rather than space.
Verdict: FLUX.2 [pro] is the clear winner as it successfully interpreted the challenging 'horse on top' spatial requirement, whereas OmniGen v2 defaulted to the common trope of an astronaut riding a horse. FLUX.2 [pro] also provided a much more sophisticated, cinematic, and detailed environment compared to the flat, simplistic rendering of OmniGen v2.
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 [pro]
- + Excellent photorealistic texture on the capybara fur and jacket.
- + Accurate passenger placement in the back seat with a shallow depth of field.
- + Highly detailed and realistic taxi dashboard and window reflection.
OmniGen v2
- + Clear representation of the yellow taxi exterior.
- + Good lighting on the subject's face.
- − Failed the prompt by putting human hands on the steering wheel instead of capybara paws.
- − The passenger is in the front seat alongside the driver rather than the back seat.
- − The overall image quality looks more like a 3D render than a photorealistic scene.
Verdict: FLUX.2 [pro] followed all instructions perfectly, creating a highly realistic and atmospheric scene with the capybara correctly placed and the passenger in the back seat. OmniGen v2 failed significantly on spatial reasoning, placing the passenger in the front and merging human hands onto the capybara driver's body.
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 [pro]
- + Perfect text rendering for all requested fields including the specific date and location.
- + High visual quality with a sophisticated, cinematic lighting style.
- + Excellent adherence to the 'vintage gothic' aesthetic through dark parchment and thorny borders.
- − The jack-o-lantern is a bit more of a 3D asset style compared to a flat illustration.
OmniGen v2
- + Good use of vibrant lighting and a strong graphic illustration style.
- + Captures the 'twisted trees' and 'webs' elements clearly in the composition.
- − Frequent spelling errors and garbled text elements (e.g., 'ARCRETSOIEW', 'ARCAS').
- − Missing the full phrase 'You are invited to a night of frights' on the scroll.
- − Artifacts and overlapping text make the event details difficult to read.
Verdict: FLUX.2 [pro] followed the prompt with near-perfect accuracy, generating legible and correctly spelled text for every requested detail, while maintaining a high-quality cinematic atmosphere. OmniGen v2 struggled significantly with the text rendering, resulting in several typos and a cluttered layout at the bottom of the invitation. FLUX.2 [pro] is the clear winner for its professional finish and adherence to complex instructions.
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 [pro]
- + Excellent prompt adherence for the text and flag icon layout.
- + Very clean 3D miniature aesthetic with soft, refined textures.
- + High visual clarity and perfectly centered composition.
- − The sushi rice texture is a bit repetitive and looks like beads rather than individual grains.
OmniGen v2
- + Appealing 3D cartoon style with vibrant colors.
- + Clean text rendering and isometric layout.
- − Failed to include a Japanese flag, providing a generic multicolored rectangle instead.
- − The sushi design is biologically confusing, combining a shrimp tail with a salmon-like roll.
Verdict: FLUX.2 [pro] followed the prompt instructions near-perfectly, including the specific Japanese flag icon and precise text placement. While OmniGen v2 produced a pleasant image, it failed on the flag icon and had less realistic sushi geometry. FLUX.2 [pro] is preferred for its superior adherence to the specific details requested.
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 [pro]
- + Excellent adherence to the 'hyper-photorealistic' request with highly detailed fur textures.
- + Includes all requested animals: puppy, kitten, bunny, and fox kit.
- + Natural-looking lighting with subtle god rays and realistic bokeh in the meadow.
- − The 'tumbling together' action is more of a static pose than active play.
OmniGen v2
- + Bright, vibrant colors that capture the 'joyful vibe'.
- + Very expressive, stylized 'big eyes'.
- − Failed to include the requested baby bunny.
- − The style is cartoonish/3D rendered rather than 'hyper-photorealistic'.
- − Anatomical issues on the fox's hind legs and floating butterflies.
Verdict: FLUX.2 [pro] followed the prompt more accurately by including all four animals and maintaining a photorealistic style. OmniGen v2 missed the rabbit entirely and opted for a stylized, semi-artificial look 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 [pro]
- + Excellent adherence to the 'Studio Ghibli' style with watercolor textures and soft line art.
- + Maintains the original facial expressions, including the suspicious/annoyed look of the woman on the right.
- + High level of background detail that feels hand-painted and atmospheric.
- − The colors are slightly more washed out than a typical vibrant Ghibli landscape.
OmniGen v2
- + Successfully translates the scene into a clean anime style.
- + Preserves the composition and character placement of the source image well.
- − Fails to capture the specific Ghibli aesthetic, appearing more like a generic modern digital anime style.
- − Lost the original expressions; the woman on the right is smiling instead of looking upset.
- − Lacks the requested 'hand-painted textures' and 'dreamy background' details.
Verdict: FLUX.2 [pro] followed the artistic instructions perfectly, capturing the specific textural and atmospheric qualities of a Studio Ghibli film while maintaining the emotional context of the original meme. OmniGen v2 produced a generic anime style and failed to preserve the core narrative of the image by making all characters appear happy and removing the conflict.
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 [pro]
- + Excellent source preservation, maintaining the original subject's face, clothing, and the background details perfectly.
- + Highly creative motion effect with the jacket flapping symmetrically with the hair.
- + Large, realistically detailed leaves that provide a strong sense of depth through blurring.
- − The wind effect on the hair is slightly symmetrical and looks a bit less natural than wind from one direction.
OmniGen v2
- + Creates a realistic directional wind effect with hair blowing specifically to one side.
- + Adds vibrant, contrasting autumn leaves to the scene.
- − Significant loss of source identity as the woman's face has been completely regenerated into a different person.
- − The background and overall image texture have been smoothed over, losing the photographic realism of the source image.
- − The dog's features and the leash geometry have changed from the original.
Verdict: FLUX.2 [pro] is the clear winner as it successfully adds the requested dynamic motion while perfectly preserving the original person, dog, and background. OmniGen v2 fails the primary task of an image edit by regenerating the entire scene, resulting in a different woman and a more 'illustrated' look compared to the source.
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 [pro]
- + Excellent typography with correct spelling and accent mark.
- + Professional vector shading and subtle background texture.
- + Perfect adherence to all prompt elements including the circular frame and banner.
- − The steam trails are slightly asymmetrical compared to the rigid geometry of the dome.
OmniGen v2
- + Strong minimalist aesthetic with high contrast.
- + Good interpretation of the cloche dome silhouette.
- − Spelling error in the main brand name ('CAFFFLORIN').
- − Lacks the subtle textures requested in the prompt.
- − The banner layout feels slightly cluttered with two overlapping ribbon styles.
Verdict: FLUX.2 [pro] followed the prompt perfectly, delivering a professional-grade logo with correct spelling, excellent typography, and the requested textures. OmniGen v2 struggled with the text rendering, misspelling the restaurant name and producing a much simpler graphic that missed the 'subtle texture' aspect of 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 [pro]
- + Excellent professional vector aesthetic with crisp lines and icons.
- + Strong text rendering of the primary headers and astronaut names.
- + Logical flow that follows the trajectory from Earth to the Moon surface.
- − Missed the distinct 'Lunar Orbit' step as a separate labeled section.
- − The Saturn V icon at the top looks more like a shuttle than a rocket.
OmniGen v2
- + Adheres strictly to the color palette requested.
- + Clean geometric layout for the individual icons.
- − Failed to include most required steps and mislabeled the mission as 'APOLO 17'.
- − Text rendering is highly garbled with many spelling errors.
- − The icons do not accurately represent the space craft described in the prompt.
Verdict: FLUX.2 [pro] followed the complex multi-step prompt almost perfectly, delivering a cohesive and educational infographic layout with clear text. OmniGen v2 failed on nearly every content requirement, getting the mission number wrong, misspelling words, and omitting the intended steps of the mission.
Explore each model
Unified multimodal model for text-to-image generation, instruction-guided image editing, personalized generation, and virtual try-on