Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [dev] Turbo fal HiDream I1 Fast HiDream AI

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

FLUX.2 [dev] Turbo

27.8 arena score

#4 of 62 in Text-to-Image

Skill signature · Text-to-Image

HiDream I1 Fast

18.3 arena score

#51 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev] Turbo

100.0%

win rate

Ties

0.0%

HiDream I1 Fast

0.0%

win rate

100.0% 0.0% ties 0.0%
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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent photorealism with realistic glass reflections and refractions.
  • + Highly accurate proportions for the small blue sphere.
  • + Superior texture rendering on the wooden table and book cover.
  • The sphere is slightly off-center which might be a stylistic choice but loses some geometric purity.

HiDream I1 Fast

  • + Strong adherence to all prompt elements.
  • + Clean, modern aesthetic with vibrant colors.
  • The sphere is very large, ignoring the 'small' descriptor in the prompt.
  • The sphere appears to be floating rather than sitting on the bottom of the cube.
  • The perspective of the cube's back edge is physically impossible.

Verdict: FLUX.2 [dev] Turbo followed the prompt much more accurately, particularly regarding the size of the 'small' sphere and the physical placement of objects. While HiDream I1 Fast created a bold image, it struggled with spatial logic (floating sphere) and ignored the size constraint for the sphere.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent adherence to the 'repairing' prompt with visible tools and a realistic posture.
  • + Highly detailed facial texture and realistic skin tones.
  • + Accurate motion blur on passing vehicles while maintaining a sharp subject.
  • The bike basket has a slightly warped texture under close inspection.
  • The front wheel of the bicycle appears slightly detached from the frame geometry.

HiDream I1 Fast

  • + Beautiful cinematic lighting and strong reflections on the wet pavement.
  • + Good atmosphere with soft bokeh in the background.
  • The man is sitting on the bike rather than repairing it, failing a key part of the prompt.
  • The background cars are static and lack the requested motion blur.
  • Noticeable anatomy issues with the hands and feet blending into the bike/pavement.

Verdict: FLUX.2 [dev] Turbo followed the prompt much more accurately, capturing the specific act of repairing a bicycle with realistic skin textures and effective motion blur. HiDream I1 Fast produced a visually pleasing but generic image where the subject is simply sitting on the bike, failing several specific technical requirements like motion blur and the action of 'repairing'.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent skin texture with realistic dirt and faint scarring.
  • + Incredibly high detail on the engraved armor, leather straps, and cloth underlayer.
  • + Natural integration of bokeh sparks and torchlight reflecting on surfaces.
  • The beads in the hair look a bit modern/plastic in some spots.

HiDream I1 Fast

  • + Strong composition with a heroic, symmetrical framing.
  • + Good use of warm torchlight highlighting the face and armor.
  • The character looks too clean and 'perfect' for the 'battle-worn' prompt.
  • The skin and hair have a slightly waxy, artificial CGI appearance.
  • Texture on the leather and fabric is less detailed compared to Model A.

Verdict: FLUX.2 [dev] Turbo significantly outperforms HiDream I1 Fast by capturing the grit and detailed textures requested in the prompt. While HiDream I1 Fast produces a clean, stylized image, FLUX.2 achieves a lifelike quality with realistic skin imperfections, intricate armor engravings, and tangible material textures like worn leather and rough cloth.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography with clean, readable sans-serif fonts.
  • + High-quality, professional food photography that looks realistic.
  • + Strict adherence to the layout requirements for sections and grid.
  • Prices are unnaturally high (e.g., $260 for a pizza).

HiDream I1 Fast

  • + Follows the grid layout for food photos.
  • + Includes vibrant color accents as requested.
  • Text is largely gibberish and distorted.
  • Low resolution with significant AI artifacts in the food images.
  • Failed to create discrete sections for appetizers, pizza, and mains.

Verdict: FLUX.2 [dev] Turbo produced a near-professional quality menu with crisp text, realistic imagery, and an effective grid layout. In contrast, HiDream I1 Fast suffered from poor resolution and unreadable text, failing to meet the 'clean professional' requirement of the prompt. FLUX.2 clearly followed the design hierarchy and aesthetic instructions much better.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography with perfect spelling and fiery glowing effects
  • + Superior photorealistic textures on the food components
  • + True exploded view with dynamic motion and suspended sauce droplets
  • The starburst for the price is a bit busy and overlaps the main text slightly

HiDream I1 Fast

  • + Clear glow on the main title text
  • + Good use of embers and fire at the base of the image
  • Fails to create an 'exploded' burger, keeping components mostly stacked
  • Mangled secondary text ('LIMITED TIMIN')
  • Price and text elements are cluttered and less professional

Verdict: FLUX.2 [dev] Turbo followed the prompt instructions perfectly, delivering a high-quality exploded burger with crisp, readable text and professional-grade food photography. In contrast, HiDream I1 Fast failed to properly separate the burger components and struggled significantly with the text rendering and layout.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent text rendering with no spelling errors.
  • + Authentic chalk texture and realistic handwriting variation.
  • + Strong adherence to the layout requested in the prompt.
  • The pricing for the cookies is slightly repetitive.

HiDream I1 Fast

  • + Follows the cursive title instruction well.
  • + Cosey cafe background is bright and aesthetically pleasing.
  • Several spelling errors such as 'Risott', 'Herbs', and 'Buter'.
  • The text and price rendering becomes cluttered and overlaps in the middle.
  • The handwriting looks more like a digital font than actual chalk on a board.

Verdict: FLUX.2 [dev] Turbo followed the prompt with high precision, accurately rendering every word from the menu with a realistic chalk texture. In contrast, HiDream I1 Fast struggled with text legibility, manifesting several typos and overlapping characters that made the menu difficult to read.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent adherence to the 'in space' environment
  • + Highly detailed rendering of both the spacesuit and the horse
  • + Cinematic lighting and composition with a grand scale
  • Failed the specific spatial instruction for the horse to be on top of the astronaut

HiDream I1 Fast

  • + Clear and clean rendering of the subjects
  • + Good texture work on the horse and saddle
  • Completely missed the 'in space' setting, placing the scene in a desert
  • Failed the specific spatial instruction for the horse to be on top of the astronaut
  • Lacks the surreal and cinematic quality requested

Verdict: Both models failed the specific trick prompt instruction to place the horse on top of the astronaut. However, FLUX.2 [dev] Turbo followed the environment and stylistic cues perfectly, creating a beautiful cinematic space scene, whereas HiDream I1 Fast ignored the space setting entirely in favor of a mundane desert background.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent photorealism with gritty, cinematic lighting
  • + Accurately places the passenger in the back seat as requested
  • + Detailed capybara paws interacting naturally with the steering wheel
  • The 'TAX' sign on top is slightly oddly placed over the windshield

HiDream I1 Fast

  • + Sharp focus on the capybara's face
  • + Good bokeh effect on the background city lights
  • Failed the spatial request by putting the passenger in the front seat
  • Anatomical failure with human hands emerging from the capybara's jacket
  • The capybara and passenger are lit differently, making them look composited

Verdict: FLUX.2 [dev] Turbo followed all instructions, including the specific instruction for the passenger to be in the back seat, while maintaining a high level of photorealism. HiDream I1 Fast failed on both spatial logic and anatomy, placing the passenger in the front seat and giving the capybara human hands.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent text rendering with no spelling errors.
  • + Sophisticated composition with high-quality illustrations and moody lighting.
  • + Accurately follows all prompt elements including the thorn border and scroll placement.
  • The text is a bit large, slightly crowding the background art.

HiDream I1 Fast

  • + Features a classic vintage illustration style.
  • + Clear distinction between the parchment and the background sky.
  • Frequent text errors and illegible characters in the scroll and event details.
  • Failed to include the requested thorn border.
  • Lower overall image resolution and visual polish compared to the competition.

Verdict: FLUX.2 [dev] Turbo produced a professional-grade invitation with perfect typography and a cohesive gothic aesthetic. In contrast, HiDream I1 Fast struggled significantly with text legibility and missed specific prompt instructions like the thorn border.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent PBR material rendering with highly realistic textures on the salmon and rice.
  • + Perfect typography and layout of the requested text and flag icon.
  • + Superior lighting and shadowing that gives a premium 3D render feel.
  • The camera angle is slightly lower than the requested 45° isometric view.

HiDream I1 Fast

  • + Closer adherence to the 45° isometric camera angle.
  • + Clean 3D cartoon style that matches the 'miniature scene' description.
  • + Good inclusion of extra elements like chopsticks to fill the square format.
  • The text layout is cluttered with extra lines and artifacts near the flag icon.
  • The salmon texture is very simplified and lacks the requested 'refined texture' or PBR realism.
  • A strange graphic of Japan appears to be floating/bleeding into the text.

Verdict: FLUX.2 [dev] Turbo produced a significantly higher quality image with superior material physics and cleaner typography. While HiDream I1 Fast better captured the isometric angle, its textures look flat and the text area contains visual glitches. FLUX.2 [dev] Turbo's rendering of the sushi grains and fish texture makes it the clear winner for quality.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent adherence to the prompt including all four distinct animal species.
  • + Dynamic and active composition that captures the 'tumbling' and 'chasing' actions perfectly.
  • + High technical quality with sharp details, visible dew sparkles, and realistic god rays.

HiDream I1 Fast

  • + Warm and appealing lighting that captures the golden sunrise vibe.
  • + Cute and expressive facial features on the animals.
  • Failed to include the bunny requested in the prompt.
  • Included two kittens instead of one, deviating from the list of specific animals.
  • The image lacks the sense of action or 'tumbling' described in the prompt, appearing more like a static pose.

Verdict: FLUX.2 [dev] Turbo successfully included all four requested animals (dog, cat, fox, bunny) in a dynamic, playful scene with exceptional detail. Conversely, HiDream I1 Fast failed the prompt by omitting the bunny and providing a static composition that lacked the requested movement and complexity.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography including the grave accent in 'Caffè'.
  • + Perfect adherence to all text elements including the date '1720'.
  • + Beautiful vintage texture on the background and emblem.
  • The steam lines are a bit thick compared to the rest of the fine line work.

HiDream I1 Fast

  • + Good use of the requested warm brown and cream color palette.
  • + Creative incorporation of the text into the cloche dome.
  • Significant typo in the date, rendering '17210' instead of '1720'.
  • The steam and surrounding circular lines are somewhat messy and inconsistent.
  • Missed the accent mark on the 'e' in 'Caffè'.

Verdict: FLUX.2 [dev] Turbo followed the prompt perfectly, delivering a professional-grade vector emblem with accurate spelling and a convincing vintage texture. HiDream I1 Fast struggled with the text, adding an extra digit to the date and failing to include the accent mark in 'Caffè'.

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.”

FLUX.2 [dev] Turbo
HiDream I1 Fast

AI Judge Analysis

FLUX.2 [dev] Turbo

  • + Excellent typography with nearly perfect spelling of labels and astronaut names.
  • + High adherence to the requested icons and specific mission steps.
  • + Professional layout that feels like a cohesive instructional poster.
  • Includes a literal text string 'Saturn Vicon' instead of just 'Saturn V'.
  • The composition is a bit cluttered with repeating elements and landing sites.

HiDream I1 Fast

  • + Successfully uses the requested color palette (navy, white, muted red).
  • + Clean, centralized composition with a distinct vector style.
  • Significant spelling errors in almost every label (e.g., 'DESCENG', 'EH OPBIT').
  • Icons do not match the requested steps, such as using a ringed planet for 'Translunar'.
  • Lacks the specific technical details or iconography requested in the prompt.

Verdict: FLUX.2 [dev] Turbo significantly outperforms HiDream I1 Fast by delivering legible text, accurate mission steps, and a professional aesthetic that matches the 'NASA-inspired' request. While it interprets parts of the prompt literally (e.g., 'Saturn Vicon'), its layout and iconography are far more coherent than HiDream I1 Fast, which suffers from severe spelling issues and nonsensical icon choices.

Next steps

Explore each model