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 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [pro]
#8 of 62 in Text-to-Image
HiDream I1 Fast
#50 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [pro]
100.0%
win rate
Ties
0.0%
HiDream I1 Fast
0.0%
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 photographic realism with natural depth of field.
- + Accurate interpretation of 'small blue sphere' relative to the cube size.
- + Perfect glass refraction and realistic caustic shadow on the table.
- − The window light on the left is very bright, slightly washing out the background.
HiDream I1 Fast
- + Strong colors and clear visibility of all objects.
- + Good adherence to the basic spatial requirements of the prompt.
- − The sphere is disproportionately large for the description 'small'.
- − Lighting and glass transparency feel less realistic compared to Model A.
- − The sphere appears to be floating rather than sitting on the base of the cube.
Verdict: FLUX.2 [pro] followed the prompt more accurately, particularly with the scale of the sphere and the subtle details of glass transparency. While HiDream I1 Fast captured all elements, it struggled with realistic scale and physics, making the sphere look like it was floating. FLUX.2 [pro] is the clear winner for its superior visual quality and adherence to the 'small' descriptor in the prompt.
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 'repairing' aspect of the prompt
- + Superior water ripple physics and wet pavement reflections
- + Highly realistic skin textures and clothing materials
- − The bicycle chain and pedal assembly is physically nonsensical close up
- − A slight blue fringe artifact on the man's hair against the background
HiDream I1 Fast
- + Strong composition with centered focus and good reflections
- + Accurate representation of an elderly Japanese man
- − The man appears to be sitting on or walking over the bike rather than repairing it
- − The car in the background is sharp, missing the requested motion blur
- − The bike's frame geometry is warped where it meets the man's hands
Verdict: FLUX.2 [pro] is the clear winner as it accurately captures the 'repairing' action and the secondary prompt requirements like motion blur and realistic skin textures. While both models struggled with complex bicycle mechanics, HiDream I1 Fast failed to include the requested motion blur on the cars and interpreted 'repairing' as simply standing with the bike.
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 realism in skin texture and lighting, with natural dirt and sweat.
- + Highly detailed material rendering on the leather straps and woven cloth underlayer.
- + Very natural integration of the bokeh sparks within the composition.
- − The engraving on the armor is a bit soft compared to the sharpness of the face.
- − The braids are slightly messy, though this fits the battle-worn theme.
HiDream I1 Fast
- + Impressive sharpness and intricate detail on the ornate armor engravings.
- + Strong adherence to the braid and bead requirement with clean, distinct styling.
- + Vibrant colors and high contrast create a striking visual.
- − The skin texture and hair look somewhat synthetic or plastic compared to a real photograph.
- − The 'scar' on the forehead looks like face paint or a superficial mark rather than a realistic healed or fresh wound.
- − The lighting feels a bit more like a digital painting than a lifelike portrait.
Verdict: FLUX.2 [pro] produces a significantly more lifelike and realistic image with superior textures on the skin and leather, perfectly capturing the 'battle-worn' aesthetic. While HiDream I1 Fast excels at rendering the fine details of the armor's engravings, its overall character rendering feels more artificial and less like the requested 'lifelike' portrait.
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 text legibility and correct spelling of key headers.
- + Coherent and logical layout with clear sections for appetizers, pizza, and mains.
- + Professional aesthetic that realistically mimics a modern casual dining menu.
- − The content under the headers repeats the same items multiple times.
- − The food photos are slightly generic and small in scale within the grid.
HiDream I1 Fast
- + Features a clear grid of colorful food photos as requested.
- + Bold sans-serif header style aligns with the minimalist theme.
- − Text is largely nonsensical or distorted, including the main title.
- − Layout is less professional with irregular spacing and overlapping text in headers.
- − The menu structure is confusing, combining categories into one list.
Verdict: FLUX.2 [pro] is the clear winner as it successfully follows the structural requirements of a restaurant menu, maintaining high text legibility and a clean, professional layout. In contrast, HiDream I1 Fast produces significant text artifacts and lacks the organizational coherence required for a readable menu design.
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 clean, flaming effects and perfect spelling.
- + Highly photorealistic food textures, especially the glistening patties and crisp lettuce.
- + Strong sense of motion with orbiting sauce droplets and dynamic crumbs.
- − The burger is slightly less 'exploded' than Model B, keeping most central ingredients close together.
HiDream I1 Fast
- + Bright, eye-catching color palette with high contrast.
- + Good use of the fiery background elements like hot coals.
- − Text rendering is poor, with garbled characters in the secondary message.
- − The burger is mostly collapsed rather than 'exploded' with suspended components as requested.
- − The floating white ring objects are unidentifiable and look out of place.
Verdict: FLUX.2 [pro] followed the prompt with significantly higher technical accuracy, producing professional-grade typography and realistic food textures. In contrast, HiDream I1 Fast struggled with the text rendering and failed to deliver the 'exploded' view of the burger ingredients, opting for a mostly stacked composition with floating artifacts.
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 no spelling errors or overlapping characters.
- + Very realistic chalk texture with genuine variations in letter thickness and dust.
- + Correctly completed the truncated prompt 'Brown But...' as 'Brown Butter Chocolate Chip Cookies'.
- − The 'elegant cursive' for the title is a bit simplified compared to the rest of the handwriting.
- − The slate background is slightly chipped at the edges, which might be too rustic for some tastes.
HiDream I1 Fast
- + Good use of space and composition within a framed chalkboard.
- + The lighting and café environment are well-rendered and atmospheric.
- − Severe artifacting and overlapping text in the price areas ($24, $28, $9).
- − Spelling errors present, such as 'Buter' and 'Risoto'.
- − The handwriting looks more like a digital font than natural chalk variations.
Verdict: FLUX.2 [pro] followed the prompt almost perfectly, delivering clear, legible, and realistic chalk handwriting with no spelling errors. HiDream I1 Fast struggled significantly with text rendering, producing garbled characters and several spelling mistakes, resulting in a much less professional 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 [pro]
- + Successfully followed the difficult spatial instruction of horse on top.
- + High resolution with cinematic lighting and backgrounds.
- + Creative surreal interpretation that blends several horse elements into the astronaut's form.
- − The transition where the horse's legs meet the astronaut is anatomically messy.
- − The horse has five or six visible legs due to the surreal blending.
HiDream I1 Fast
- + Clean anatomy and sharp textures for both the horse and astronaut.
- + Realistic dust and lighting effects for a desert setting.
- − Completely failed the negative spatial constraint to have the horse on top.
- − Ignored the 'in space' setting, placing the subject in a desert.
- − Lacks the requested 'surreal' quality.
Verdict: FLUX.2 [pro] followed the complex prompt requirements, successfully placing a horse on top of an astronaut in a space setting, whereas HiDream I1 Fast generated a generic image of an astronaut riding a horse in a desert. Although FLUX.2 [pro] has some anatomical glitches due to the surrealism, it is the clear winner for its prompt adherence and creativity.
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 photorealism in lighting and textures
- + Accurate depiction of animal paws on the steering wheel
- + Very convincing taxi interior with realistic reflections and rain on windows
- − The capybara's head is slightly disproportionate to its body
HiDream I1 Fast
- + Strong composition and clear subject separation
- + Accurately places the passenger and her phone in the scene
- + Vibrant, clean city bokeh in the background
- − The capybara has human hands instead of paws
- − The capybara is positioned in the passenger seat despite holding the wheel, while the woman is in the driver's seat
- − The image has a more artificial, digital sheen compared to the first
Verdict: FLUX.2 [pro] is the clear winner due to its superior realism and adherence to biological details, such as giving the capybara paws instead of human hands. HiDream I1 Fast struggles with spatial logic, placing the businesswoman in the driver's seat while the capybara attempts to drive from the passenger side.
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]
- + Flawless text rendering with zero spelling errors.
- + Cinematic lighting on the central jack-o-lantern.
- + Elegant gothic composition with high-quality textures on the parchment and border.
- − The thorns and webs are slightly subtle in the outer corners.
HiDream I1 Fast
- + Clear use of gothic-style illustrations such as the twisted trees.
- + Dynamic parchment shape with torn edges.
- − Major text errors including 'D are invited' and garbled event details.
- − Lower overall image resolution and visual fidelity.
- − Failed to include the word 'Invitation' in the main header.
Verdict: FLUX.2 [pro] is the clear winner as it perfectly rendered all requested text without a single error, which is critical for an invitation. While HiDream I1 Fast has a charming illustrative style, it suffers from significant typos, overlapping text artifacts at the bottom, and a lack of overall polish compared to the cinematic lighting and sharp details of FLUX.2.
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]
- + Perfectly followed the isometric perspective and composition requested.
- + Excellent text rendering with 'JAPAN' and 'SUSHI' cleanly stacked as specified.
- + High-quality PBR-style textures, particularly on the relief of the rice and the ginger rose.
- − The fish texture on the nigiri appears slightly more geometric than organic.
- − The 'flag' icon is a bit small compared to the text.
HiDream I1 Fast
- + Soft, vibrant cartoon aesthetic that fits the 'miniature' theme well.
- + Good use of shadows and gentle lighting to create depth.
- − Failed the isometric perspective request, opting for a lower eye-level view.
- − Text layout is cluttered with horizontal lines and distorted secondary icons.
- − Includes chopsticks which were not requested, and they are rendered with floating artifacts.
Verdict: FLUX.2 [pro] followed every aspect of the prompt, specifically the isometric angle, the clean diorama base, and the exact text arrangement. HiDream I1 Fast failed the perspective requirement and produced messy text with artifacts around the extra elements like the chopsticks.
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]
- + Successfully includes all four requested animal species correctly.
- + Incredible detail in the fur texture and grass.
- + More natural interaction between the animals and the butterflies.
- − The kitten has an oddly large human-like eye shape.
- − Puppy's tongue placement looks slightly unnatural against the bunny's ear.
HiDream I1 Fast
- + Beautiful golden lighting and bokeh effect.
- + Consistent and cute art style across all animals.
- − Failed to include the requested baby bunny.
- − Included two kittens instead of one.
- − Lower overall resolution and fine detail compared to Model A.
Verdict: FLUX.2 [pro] followed the complex prompt much more accurately by including all four distinct animal species, whereas HiDream I1 Fast missed the bunny entirely and duplicated the kitten. FLUX.2 [pro] also offers significantly higher detail in the fur and floral background, despite some slight anatomical oddities in the kitten's eye.
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 including the correct grave accent on 'Caffè'
- + Superior vector-style shading and texture
- + Clear and accurate rendering of the requested 'Est. 1720' text
- − The steam effect is slightly abstract compared to the rest of the realism
HiDream I1 Fast
- + Strong high-contrast color palette
- + Good use of the cloche silhouette for the name placement
- − Significant spelling error with '17210' instead of '1720'
- − Messy graphic artifacts around the cloche and circle borders
- − The banner construction is asymmetrical and clunky
Verdict: FLUX.2 [pro] followed the prompt with high precision, delivering a professional-grade vector emblem with perfect spelling and balanced typography. HiDream I1 Fast struggled with the text, adding an extra digit to the date, and the overall image quality appeared unrefined with several clipping and linework artifacts.
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 adherence to the clean, flat-vector style requested.
- + Accurately represents the sequential flow of the mission steps from top to bottom.
- + Clean typography and professional layout with consistent NASA-inspired colors.
- − The placeholder text for descriptions is gibberish.
- − The Saturn V icon looks more like a shuttle orbiter than a Saturn V rocket.
HiDream I1 Fast
- + Large, clear title text for 'Apollo 11'.
- + Includes a flag icon representing the landing phase.
- − Fails to follow the sequential numbering or logical order for the mission steps.
- − Poor text rendering with many spelling errors and distorted characters.
- − Graphical elements are messy with artifacting and lack the requested 'crisp lines'.
Verdict: FLUX.2 [pro] followed the design instructions much better, producing a professional-looking infographic with a logical flow and beautiful vector aesthetics. HiDream I1 Fast struggled with the layout and text rendering, resulting in a disorganized image that failed to accurately represent the specific mission steps requested.
Explore each model
Distilled version of HiDream AI's 17B parameter text-to-image model