Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
18.4
arena score
#50 of 62 in Text-to-Image
Skill signature
· Text-to-Image
HiDream I1 Fast
17.9
arena score
#51 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX1.1 [pro]
0%
win rate
Ties
0%
HiDream I1 Fast
0%
win rate
Shared challenges
13
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent photorealistic texture on the red book cover
- + Very sharp and clear glass edges and reflections
- + High contrast and vibrant colors that make the subjects pop
- − The glass is more of a tall rectangular prism than a perfect cube
- − The blue sphere is levitating rather than sitting on the bottom surface
HiDream I1 Fast
- + The glass container is a more accurate cube shape
- + Good adherence to the orientation of the green plant and lighting
- + Realistic interaction between the sphere and the bottom of the cube
- − Lower overall resolution and slightly blurry textures on the plant
- − The lighting on the cube edges looks a bit artificial/thin
- − The red book looks slightly plastic and lacks fine paper/fabric texture
Verdict: FLUX1.1 [pro] captures a much higher level of detail and professional lighting, looking nearly like a real photograph, though it failed to create a perfect cube. HiDream I1 Fast followed the geometric instruction of a 'cube' more accurately but lacked the texture quality and sharpness found in the other model. FLUX1.1 [pro] is the preferred choice for its superior visual quality and realism.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent handling of wet pavement textures and reflections
- + Realistic skin and clothing textures consistent with a 50mm lens
- + Convincing bokeh and background light blooms
- − Serious anatomical and structural failure with the bicycle and man's legs
- − The bicycle frame is nonsensical and disconnected
HiDream I1 Fast
- + Much better structural integrity of the bicycle
- + Captures the 'light rain' and atmospheric lighting very effectively
- + Better composition and clearer subject focus
- − Minimal motion blur from passing cars as requested
- − Slightly more 'digital' look to the skin compared to Flux 1.1
Verdict: While FLUX1.1 [pro] excels at realistic material textures and lighting, it suffers from a major structural failure where the bicycle and the man's legs are fused into a mess of artifacts. HiDream I1 Fast produces a far more coherent image with a functional-looking bicycle and a clearer narrative, making it the superior choice despite slightly less intricate skin textures.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Exceptional photorealistic skin texture and lifelike eyes
- + Excellent depth of field with cinematic lighting and natural dirt patterns
- + Realistic hair and facial hair integration
- − The braids with small beads are present but very subtle and partially out of focus
- − Less of the ornate armor is visible due to the tight cropping
HiDream I1 Fast
- + Clearly follows the requirement for braids with colorful beads
- + Intricate engraving on the plate armor is highly visible
- + Good use of warm torchlight and bokeh elements
- − Skin texture and scars look somewhat artificial and airbrushed
- − Armor engraving looks a bit flat and computer-generated compared to the rest of the image
- − Lighting on the face is a bit too uniform, losing the 'battle-worn' gritty feeling
Verdict: FLUX1.1 [pro] produces a significantly more lifelike and cinematic portrait with superior skin textures and lighting, though it crops very tightly on the face. HiDream I1 Fast better captures the specific geometric details of the armor and the colorful beads in the hair, but the overall image quality feels more like a 3D render than a real photograph. FLUX1.1 [pro] is the winner for its professional-grade realism and mood.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Features a highly professional layout that mimics a real-world restaurant mockup.
- + Accurately represents multiple sections like appetizers and pizza with a clean grid of photos.
- + Excellent use of whitespace and typography that adheres to the minimalist request.
- − The text content within the menu sections is mostly garbled and illegible.
- − Includes unnecessary cutlery props that weren't explicitly requested.
HiDream I1 Fast
- + Uses bold, high-contrast colors and a clear grid for food photography.
- + Larger font size makes the category headers easy to identify.
- − The 'NOEPINEINIALIST' text at the top is nonsensical and distracting.
- − The layout is cramped and lacks the professional design aesthetic requested in the prompt.
- − Fails to include a clear 'mains' section as specified.
Verdict: FLUX1.1 [pro] significantly outperforms HiDream I1 Fast by delivering a polished, professional menu mockup that looks like a real design project. While neither model achieved perfect text, FLUX1.1 [pro] followed the aesthetic cues of minimalism and layout hierarchy much more effectively than HiDream I1 Fast, which produced a cluttered and amateurish result.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent photorealistic detail on the burger components
- + High-quality, professional lighting and fire effects
- + Text is rendered clearly with no spelling errors
- − Failed to create an 'exploded' burger, keeping it largely assembled
- − Did not include the requested starburst for the price element
- − Title text is neon blue rather than the requested fiery, glowing effect
HiDream I1 Fast
- + Successfully integrated all requested text elements including the price starburst
- + Captured the 'fiery, glowing effect' for the text more accurately
- + Better inclusion of the fiery background elements
- − Image quality is lower with some blurriness and visual artifacts
- − Failed to create an 'exploded' burger with suspended components
- − Text in the price starburst contains minor rendering artifacts
Verdict: FLUX1.1 [pro] produced a much higher quality, photorealistic image, but it missed several key prompt instructors like the 'exploded' structure and the starburst. HiDream I1 Fast followed the prompt more closely by including the starburst and the correct fiery text style, but the overall visual fidelity and burger detail are significantly lower than its competitor. Despite missing some layout elements, FLUX1.1 [pro] is the preferred choice for a professional advertisement look.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent font consistency and realistic chalk texture
- + Professional composition with warm, atmospheric lighting
- + High adherence to the requested date and menu sequence
- − Serious hallucination on prices and line repetition
- − Substantial spelling errors in the final items like 'Chipkies' and 'giluten'
HiDream I1 Fast
- + Text has a very authentic chalk 'smudge' effect and varying pressure
- + Good bright lighting and cafe environment
- + Captured the 'Brown Butter' item prompt more completely than Model A
- − Messy overlapping text and price fragments
- − Inconsistent cursive vs. print styles
- − Poor formatting of the menu items with text clashing into prices
Verdict: FLUX1.1 [pro] produced a much cleaner and more professional-looking image with consistent handwriting, though it failed the logic test by repeating the octopus dish with two different prices ($228 and $98). HiDream I1 Fast achieved a more realistic chalk texture but suffered from significant layout issues where text and numbers overlapped, making the menu unreadable. FLUX1.1 [pro] is the winner for its superior visual quality and cleaner text rendering despite the line repetition.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent adherence to the 'cinematic' and 'space' setting with a dramatic, cosmic background.
- + High level of detail on the astronaut's suit and the horse's anatomy.
- + Captures the surreal quality with the dynamic pose and atmospheric lighting.
- − Completely failed the negative constraint to have the horse riding the astronaut.
- − Minor anatomical strange mess where the saddle meets the horse's back.
HiDream I1 Fast
- + Natural lighting and clear, sharp focus on the subjects.
- + Realistic textures on the horse's coat and sand.
- − Completely ignored the spatial setting, placing the image in a desert.
- − Failed the negative constraint; the astronaut is riding the horse.
- − The horse's front right leg is missing its lower half.
Verdict: Both models failed the specific prompt constraint of 'horse on top', instead defaulting to the standard imagery of an astronaut riding a horse. FLUX1.1 [pro] is the stronger image because it actually utilized the space setting and cinematic lighting requested, whereas HiDream I1 Fast placed the scene in a terrestrial desert and suffered from significant anatomical errors in the horse's legs.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent atmospheric lighting and bokeh
- + High level of fur texture and detail on the capybara
- + More accurate perspective from inside the taxi
- − The capybara's anatomy blends into the seat/jacket awkwardly
- − The woman and capybara are positioned side-by-side rather than front/back seat
HiDream I1 Fast
- + Clearer street scene that feels more like New York
- + Both the passenger and driver are visible in a logical spatial arrangement
- + High clarity on the capybara's face
- − Human hands on the steering wheel instead of capybara paws
- − The capybara and woman appear to be in the same row of seats, failing the 'back seat' instruction
- − Slightly less photorealistic lighting compared to Model A
Verdict: Both models failed to place the passenger in the back seat, instead seating them next to the driver. FLUX1.1 [pro] produced a more cinematically realistic image with superior textures, whereas HiDream I1 Fast had a major anatomical error by giving the capybara human hands on the steering wheel.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent cinematic lighting and atmospheric depth
- + Highly detailed thorns and background elements
- + Professional layout and clear text rendering for the event details
- − Redundant text output with repetitive lines at the bottom
- − Title text on scroll is partially cut off/duplicated
HiDream I1 Fast
- + Strong 'vintage parchment' aesthetic that fits the gothic theme
- + Good use of spiderweb borders in the corners
- + Better adherence to the 'square format' request
- − Several spelling errors in the scroll and event details
- − Lower overall image resolution and flatter lighting compared to the opponent
- − Text layout feels cluttered and overlaps in the location section
Verdict: FLUX1.1 [pro] produces a much more atmospheric and visually striking image with superior lighting and texture, though it struggled with layout redundancy. HiDream I1 Fast better captured the requested parchment and square format, but failed significantly on text legibility and fine detail. FLUX1.1 [pro] is the preferred choice for its high-quality rendering and successful gothic mood.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent typography with a friendly 3D cartoon style
- + Higher level of detail in the variety of sushi pieces
- + Soft, refined textures that perfectly match the cartoon miniature aesthetic
- − Missed the small flag icon request
- − Included some non-sushi garnishes like small tomatoes
HiDream I1 Fast
- + Successfully included the requested flag icon
- + Correctly included the small raised diorama base and plate
- + Clear and bold text rendering
- − Lighting is a bit harsh compared to Model A
- − The sushi piece contains a strange texture error on the side of the rice
- − Composition is slightly less 'miniature' in feel
Verdict: FLUX1.1 [pro] produced a more polished and visually appealing 3D scene with superior textures and lighting, though it missed the specific flag icon. HiDream I1 Fast followed more specific prompt details like the flag and the diorama structure, but suffered from lower overall image quality and a strange artifact on the main piece of sushi.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent depiction of warm golden light and rim lighting on the fur
- + High resolution texture with very fine hair and whisker details
- + Clear attention to the 'big expressive eyes' and 'joyful' aspect of the prompt
- − Missed prompt requirement for a red fox kit (shows a puppy, kitten, and bunny)
- − Butterflies are stylized and lack realistic anatomical detail
- − The animals are sitting still rather than 'tumbling together' as requested
HiDream I1 Fast
- + Successfully included the red fox kit alongside the puppy and kittens
- + Better butterfly renditions with recognizable monarch-like patterns
- + Followed the group composition more closely by including more animals from the list
- − Missed the baby bunny requested in the prompt
- − Visual quality is lower with some blurring and less defined fur textures compared to Model A
- − Lighting is a bit flat and several flowers in the foreground exhibit digital artifacts
Verdict: Both models failed to include the full list of four animals, with FLUX1.1 [pro] missing the fox and HiDream I1 Fast missing the bunny. FLUX1.1 [pro] is the superior image in terms of photographic quality, lighting, and detail, capturing the '8K masterpiece' aesthetic much better. However, HiDream I1 Fast adhered better to the specific character list and butterfly descriptions.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent vector emblem style with sophisticated ornate details.
- + Maintains a high-quality vintage aesthetic through subtle textures and classic line work.
- + Perfectly captures the 'warm brown and cream tones' requested.
- − Failed to spell the main brand name correctly, rendering it as 'CAFFÈ FRANILIAN'.
- − The central icon looks more like an architectural dome (cupola) than a restaurant cloche dome.
HiDream I1 Fast
- + Accurately depicts a cloche dome as specifically requested in the prompt.
- + Follows the brand name spelling 'Caffè Florian' correctly.
- + Clean, minimalist composition that fits the 'logo' requirement well.
- − Included a typo in the date, listing '17210' instead of '1720'.
- − The line work on the steam and banner feels slightly less polished than a vector professional logo.
Verdict: This is a trade-off between style and accuracy. FLUX1.1 [pro] produced a much more professional and aesthetically pleasing 'vintage emblem' design, but it hallucinated the brand name. HiDream I1 Fast followed the prompt's specific subject matter (the cloche) and brand name better, but failed on the date and had a simpler artistic execution. Overall, HiDream I1 Fast is slightly more useful as a concept because it features the correct business name and icon type.
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.”
FLUX1.1 [pro]
HiDream I1 Fast
AI Judge Analysis
FLUX1.1 [pro]
- + Strong composition with a clear sense of space and perspective.
- + Clean, modern flat-vector aesthetic that fits the 'infographic' request.
- + Excellent use of the requested NASA-inspired color palette.
- − Text is largely gibberish and includes significant numbering errors (repeating number 6 and misinterpreting 'Saturn V' as 'Saturn Vicon').
- − The diagram layout is confusing and does not follow a clear chronological step-by-step path.
HiDream I1 Fast
- + Layout follows a more traditional, readable infographic grid structure.
- + Icons are bold and clearly visible against the white background.
- + Captures the requested color scheme effectively.
- − Lower visual quality with fuzzy edges and artifacts on the icons.
- − Iconography is inconsistent and messy, particularly the 'Earth orbit' and 'Lunar' icons.
- − Text rendering is poor with significant spelling errors like 'DESCENG' and 'EOXH OPBIT'.
Verdict: FLUX1.1 [pro] is the superior image in terms of artistic execution and design, offering a professional vector look that matches the 'modern infographic' prompt, though it fails significantly on text legibility and logical numbering. HiDream I1 Fast attempts a more logical grid, but the technical quality is much lower, with messy lines and poor icon coherence. FLUX1.1 [pro] is preferred for its high-quality aesthetics, though it would require manual text correction.
Next steps
Explore each model
Distilled version of HiDream AI's 17B parameter text-to-image model