Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [max] Black Forest Labs HiDream I1 Full HiDream AI

Settled by community votes across 16 shared challenges, with an AI judge weighing in on each.

FLUX.2 [max]

25.8 arena score

#10 of 62 in Text-to-Image

Skill signature · Text-to-Image

HiDream I1 Full

15.2 arena score

#60 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [max]

0%

win rate

Ties

0%

HiDream I1 Full

0%

win rate

Shared challenges 16

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent texture on the red book cover.
  • + Sharp, realistic reflections on the bottom surface of the cube.
  • + Accurate and coherent lighting from the left.
  • The glass cube looks more like a frame or assembly than a single solid object.

HiDream I1 Full

  • + Natural look of the green plant through the glass.
  • + Accurate positioning of all requested elements.
  • + Warm, inviting lighting.
  • The sphere appears to be floating mid-air rather than resting normally.
  • Internal reflections within the glass are a bit muddy.

Verdict: FLUX.2 [max] produced a superior image in terms of resolution and surface textures, particularly the leather-like grain of the red book. While HiDream I1 Full followed the prompt perfectly, the floating blue sphere felt less physically grounded than the one in FLUX.2 [max], which looks more like a high-end product photograph.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent adherence to technical prompts like motion blur and imperfect framing.
  • + Highly realistic skin textures and hand anatomy for the subject.
  • + Bicycle mechanical details are complex and convincing.
  • The motion blur on the car in the background is slightly streaky and digital.

HiDream I1 Full

  • + Good atmospheric lighting and beautiful pavement reflections.
  • + Natural looking candid pose for the subject.
  • Failed to include motion blur on cars as requested.
  • The bicycle anatomy is broken, particularly where the frame meets the back wheel.
  • The subject appears to be sitting mid-air rather than on the bike or kneeling.

Verdict: FLUX.2 [max] is the clear winner for its superior technical execution of the prompt, successfully capturing the specific motion blur and skin textures requested. While HiDream I1 Full creates a nice atmosphere, it suffers from significant anatomical errors in the bicycle structure and fails to include the requested motion blur effect.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Natural and lifelike skin textures with subtle, realistic scarring
  • + Exceptional detail on the engraved armor patterns and material physics
  • + Coherent and sophisticated lighting that feels integrated with the environment
  • The hair beads are somewhat small and less prominent than implied by the prompt

HiDream I1 Full

  • + Strong implementation of the hair braids with clear beading
  • + Good use of bokeh and sparks in the background
  • + Direct, intense eye contact as requested
  • Slightly over-sharpened, 'digital' look to the skin and hair
  • The engraving on the armor looks flatter and less detailed compared to Model A
  • Unrealistic glowing spots on the face that don't match the light source

Verdict: FLUX.2 [max] provides a significantly more professional and photorealistic image with superior material rendering, particularly on the complex metal engravings and leather straps. While HiDream I1 Full captures the braids and beads well, it suffers from over-processing and less believable skin textures. FLUX.2 [max] is the winner due to its artistic composition and lifelike fidelity.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography with readable headings and price alignment.
  • + Professional use of color blocking and grid-based layout.
  • + Includes all requested sections (Appetizers, Pizza, Mains) distinctively.
  • Internal food labels do not match the item headers (e.g., 'Pizza' listed under 'Mains').
  • The text contains typical AI gibberish characters.

HiDream I1 Full

  • + Very clean, minimalist aesthetic with high-quality food photography.
  • + Large, appetizing imagery that fills the frame well.
  • + Bold, legible header fonts.
  • Combined 'Appetizers / Pizza' into one section instead of separating them as requested.
  • Layout is slightly more basic and less like a realistic commercial menu.
  • Poor price alignment and significant spelling errors in text.

Verdict: FLUX.2 [max] captures the essence of a 'professional layout' much more effectively, utilizing a clear grid system, color-coded sections, and aligned pricing that resembles a real-world menu. While HiDream I1 Full produces high-quality individual food photos, it fails the structural requirements of the prompt by merging sections and lacks the sophisticated typographic hierarchy seen in FLUX.2.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent prompt adherence with flawless text rendering of the specific menu items requested.
  • + Very realistic chalk texture including authentic smudges and dust on the board surface.
  • + Consistent handwriting style that feels human-made rather than a font.
  • The lighting creates a slight glare that makes the bottom text a bit harder to read, though it adds to the realism.

HiDream I1 Full

  • + Clean layout with a nice illustration of a coffee cup.
  • + Correct title and date rendering.
  • Fails completely to include the requested menu items, generating nonsensical gibberish instead.
  • The text looks more like a digital font overlay than hand-drawn chalk.
  • Prices are unrealistic and repetitive ($50 for everything).

Verdict: FLUX.2 [max] followed the prompt perfectly, accurately rendering all specific food items and prices with a highly realistic chalk texture. HiDream I1 Full failed significantly, ignoring the requested items in favor of illegible placeholder text and a generic layout. FLUX-like font style that lacked the requested 'handwritten' variations.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent anatomical detail of the horse and spacesuit hardware.
  • + Superior cinematic lighting and atmosphere with the nebula background.
  • + High-resolution textures on the asteroid and horse's coat.
  • Failed the specific spatial instruction for the horse to be 'on top' of the astronaut.

HiDream I1 Full

  • + Dynamic sense of movement and speed.
  • + Clear focus on the subject with good contrast against the planet background.
  • Failed the specific spatial instruction for the horse to be 'on top' of the astronaut.
  • Visible anatomical distortions in the horse's legs and hooves.
  • Lower overall fine detail compared to the competitor.

Verdict: Both FLUX.2 [max] and HiDream I1 Full failed the negative constraint/spatial instruction of placing the 'horse on top' of the astronaut, both defaulting to the standard 'astronaut riding horse' trope. However, FLUX.2 [max] is the superior image due to its significantly higher level of detail, realistic lighting, and better anatomical consistency, whereas HiDream I1 Full exhibits artifacts 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.”

FLUX.2 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent atmospheric lighting and realistic taxi interior details.
  • + Captures a high-quality cinematic 'night in the city' aesthetic.
  • + Correctly depicts a businesswoman looking at her phone in the back seat.
  • The capybara has realistic human hands instead of capybara paws.
  • The human woman's face is slightly blurry and lacks fine detail.

HiDream I1 Full

  • + Depicts actual capybara paws/hands on the steering wheel as requested.
  • + Very sharp focus on the main subject's face and professional expression.
  • + Clearer text rendering on the driver's cap.
  • The passenger appears to be in the front/middle seat due to weird spatial perspective.
  • The lighting is a bit too bright and clean for a nighttime scene, feeling less 'photorealistic'.

Verdict: FLUX.2 [max] creates a more immersive and atmospheric scene with authentic taxi interior details, but fails significantly by giving the capybara human hands. HiDream I1 Full followed the anatomy requirement much better by including paws, though the spatial arrangement of the passenger feels cramped and less like a standard taxi layout compared to FLUX.2 [max].

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Perfect text rendering for all requested details including date and location.
  • + Highly atmospheric cinematic lighting with a realistic jack-o-lantern.
  • + Excellent border integration with thorns and webs as requested.
  • The parchment texture is slightly less 'aged' looking compared to Model B.

HiDream I1 Full

  • + Good gothic aesthetic for the central parchment element.
  • + Includes all thematic elements like bats and twisted trees.
  • Fails significantly on text accuracy, hallucinating words like 'Yootmber'.
  • Missed the specific event details like 'The Arches, NYC' and '7pm'.
  • The layout feels more like clip-art than a cinematic poster.

Verdict: FLUX.2 [max] is the clear winner as it followed every instruction, including the complex text requirements for dates and addresses, while maintaining a high-quality cinematic atmosphere. HiDream I1 Full struggled with text rendering, generated nonsense words, and failed to include the specific location and time requested.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.2 [max]
Before After
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Successfully added full, natural-looking hair that matches the beard color and texture.
  • + Preserved the original person's face, clothing, and background with high fidelity.
  • + Maintained consistent lighting and skin texture at the hairline.
  • The forehead height remains slightly high, creating a very prominent brow line.
  • Some slight blurring where the hair meets the background bushes.

HiDream I1 Full

  • + Added a ponytail to the back of the head as an interpretation of 'full head of hair'.
  • Failed to preserve the source image, completely changing the person's face and eyes.
  • Changed the entire background and added a bizarre black object/mask merged into the face.
  • Did not actually add hair to the top/front of the head as requested by 'full head' and 'natural hairline'.

Verdict: FLUX.2 [max] performed a near-perfect edit, successfully adding realistic hair while keeping every other detail of the source image intact. HiDream I1 Full failed significantly, generating a different person, changing the environment, and adding nonsensical artifacts like a black mask over the mouth.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent adherence to all text requirements including the flag icon.
  • + Superior diorama composition with a multi-tiered base and consistent 45-degree isometric projection.
  • + Clean, professional typography and graphic design layout.
  • The scale of the sushi on the plate is slightly small relative to the diorama base.

HiDream I1 Full

  • + Appealing 3D textures on the individual grains of rice and fish.
  • + Good color contrast and bright, vibrant lighting.
  • Failed to include the requested flag icon.
  • The text 'SUSHI' is relatively small and less balanced compared to the heading.
  • The diorama base is less 'miniature' in feel and lacks the refined layering requested.

Verdict: FLUX.2 [max] followed the prompt more accurately by including all requested elements, such as the Japan flag icon and a tiered diorama base. While HiDream I1 Full has nice tactile textures on the food, FLUX.2 [max] produced a more cohesive and professional-looking isometric graphic with superior layout and typography.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.2 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Perfectly incorporates all requested elements including the TV anchor desk, hockey rink setting, and multiple dogs.
  • + Excellent caricature style with exaggerated proportions while maintaining recognizable features and outfit from the source.
  • + High visual quality with clean illustration lines and creative background details like the scoreboard.
  • Text on the desk and scoreboard is somewhat nonsensical.

HiDream I1 Full

  • + Strong facial likeness to the source image within the caricature style.
  • + Includes a well-rendered dog and preserves the denim jacket detail.
  • Fails to include any visual reference to hockey.
  • The TV anchor profession is barely represented, appearing more like a casual living room than a broadcast environment.
  • Less creative 'exaggeration' compared to a traditional caricature.

Verdict: FLUX.2 [max] is the clear winner as it successfully incorporated every element of the prompt (TV anchor, dogs, and hockey) into a cohesive and humorous caricature. HiDream I1 Full failed to include the hockey theme and the setting does not clearly communicate the TV anchor profession, resulting in a more generic portrait.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Perfectly captured all four requested animals (dog, kitten, bunny, fox).
  • + Dynamic composition showing movement and playfulness as requested.
  • + Exquisite lighting with realistic god rays, dew sparkles, and morning atmosphere.
  • The kitten's anatomy is slightly stiff compared to the other animals.

HiDream I1 Full

  • + Very cute, expressive eyes and vibrant colors.
  • + Clear, soft fur textures on the puppy and fox.
  • Failed to include the bunny, providing two kittens instead.
  • The animals are mostly static and posing rather than 'playfully chasing' or 'tumbling'.
  • Over-saturated lighting looks more like a digital illustration than a 'hyper-photorealistic scene'.

Verdict: FLUX.2 [max] followed the prompt instructions precisely, including all four distinct animals and capturing a dynamic, playful action scene in a realistic morning environment. HiDream I1 Full failed on prompt adherence by omitting the bunny and doubling the kittens, while also producing a more static and artificial-looking composition.

Studio Ghibli Anime Style

Editing
Edit instruction

“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”

Source
FLUX.2 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent source preservation, keeping the exact poses, clothing patterns, and composition of the original meme.
  • + Very accurate Ghibli-esque color palette with soft pastels and watercolor textures.
  • + Captures the emotional nuances of the original expressions while translating them into an anime style.
  • The texture overlay is slightly uniform across the entire image, reducing depth.

HiDream I1 Full

  • + Distinctive Ghibli-inspired character designs and vibrant 'Kiki's Delivery Service' style backgrounds.
  • + Clean linework and bold, cheerful colors.
  • Poor source preservation; it adds hats, floral patterns, and changes the man's beard and pose.
  • The 'distracted' narrative of the original meme is weakened by the man's facial expression and eye direction.
  • The hand rendering on the man is poor, with an unnatural wrist and finger count.

Verdict: FLUX.2 [max] is the clear winner as it successfully performs the edit while preserving the identity of the source image, keeping the exact clothing and iconic 'distracted boyfriend' pose. HiDream I1 Full creates a decent illustration but changes too many details of the original photo, such as adding floral patterns and hats, which makes it feel like an entirely new creation rather than a stylistic edit.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.2 [max]
Before After
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent source preservation, maintaining the woman's face, clothing, and the dog perfectly.
  • + Accurately adds wind-blown hair and flying leaves as requested.
  • + The lighting and color consistency are indistinguishable from the source image.
  • The leaf motion blur is a bit inconsistent across the frame.

HiDream I1 Full

  • + Successfully captures a high sense of energy and movement through pose and environment changes.
  • + Hair and leaves show dynamic motion consistent with the prompt.
  • Failed to preserve the source image, completely removing the dog and changing the woman's face and outfit.
  • The background environment was significantly altered, losing the pond and bridge.

Verdict: FLUX.2 [max] is the clear winner as it successfully applied the requested edits while keeping the source image almost entirely intact. HiDream I1 Full failed the fundamental task of image editing, essentially generating a new image that removed the dog and completely changed the woman's appearance.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography including the correct name and accent mark.
  • + Clean and professional vector emblem composition.
  • + Subtle, high-quality papery texture that fits the vintage theme.
  • The cloche dome is slightly cut off at the bottom within its own circular frame.

HiDream I1 Full

  • + Strong minimalist graphic style with bold contrast.
  • + Accurate 'Est. 1720' banner with a classic look.
  • Completely failed to include the primary text 'Caffè Florian'.
  • The cloche handle is slightly off-center and unrefined.

Verdict: FLUX.2 [max] is the superior model because it successfully included all text elements from the prompt, whereas HiDream I1 Full omitted the name of the restaurant entirely. FLUX.2 [max] also shows a more sophisticated handle on texture and classic vector aesthetics.

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 [max]
HiDream I1 Full

AI Judge Analysis

FLUX.2 [max]

  • + Excellent adherence to the logical sequence of the mission steps.
  • + Very clean typography and correct spelling of astronaut names and mission phases.
  • + Professional flat-vector aesthetic with a cohesive color palette.
  • Repeats the text 'Earth Orbit' in two separate boxes instead of following the unique step labels.
  • The rocket design is a generic shuttle/rocket hybrid rather than a specific Saturn V icon.

HiDream I1 Full

  • + Bold, high-impact graphic design with a strong central focus.
  • + Accurate NASA-inspired color palette with vibrant application.
  • + Includes a clear 'Apollo 11' header.
  • Text contains several hallucinated words and typos like 'UNG' and 'UNLY'.
  • Fails to include all requested steps, stopping after Translunar.
  • The iconography is inconsistent, featuring a planet that looks more like Saturn than the Moon.

Verdict: FLUX.2 [max] is the superior choice because it actually functions as an infographic, following the mission logic from launch to landing with legible, accurate text. HiDream I1 Full creates a visually striking poster but fails on the technical requirements of the prompt, including missing steps and significant text errors.

Next steps

Explore each model