Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs HiDream I1 Full HiDream AI

Settled by community votes across 12 shared challenges, with an AI judge weighing in on each.

FLUX.1 [dev]

24.6 arena score

#16 of 62 in Text-to-Image

Skill signature · Text-to-Image

HiDream I1 Full

13.8 arena score

#60 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0%

win rate

Ties

0%

HiDream I1 Full

0%

win rate

Shared challenges 12

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent optical realism with sharp reflections and refractions on the glass.
  • + The book has a high-quality leather-like texture.
  • + Very clean, professional-grade lighting and composition.
  • The plant is mostly to the side rather than behind the cube.
  • The sphere is quite large, bordering on filling the entire width of the cube interior.

HiDream I1 Full

  • + Successfully places the plant behind the cube visible through the glass.
  • + Captures the 'small' scale of the sphere better than Model A.
  • + Realistic wood grain and warm lighting on the table.
  • The glass box has slightly wavy, inconsistent edges.
  • The perspective of the sphere's reflections on the inner glass walls is physically impossible.

Verdict: FLUX.1 [dev] produces a much more polished and photorealistic image with superior rendering of glass and leather textures, though it struggles to place the plant directly behind the cube as requested. HiDream I1 Full follows the spatial instructions of the prompt more closely by placing the plant behind the glass and keeping the sphere small, but it suffers from lower technical quality and warped geometry in the glass cube.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent realism in skin texture and clothing materials
  • + Accurate 50mm lens feel with a shallow depth of field
  • + Effective motion blur on the passing vehicle in the background
  • The man is holding the bicycle but not actively 'repairing' it as requested
  • The red bicycle is a modern mountain bike rather than a traditional city bike commonly found in Japan

HiDream I1 Full

  • + Better captures the 'repairing' aspect of the prompt with the man's posture and items on the ground
  • + Superior reflections on the wet pavement
  • + The red bicycle design feels more authentic to a Japanese street scene
  • Anatomical issues with the man's legs which appear disconnected or poorly proportioned given his seated position
  • Background cars lack the specific 'motion blur' requested, appearing mostly static
  • The man's skin and hair texture look slightly more processed compared to Model A

Verdict: FLUX.1 [dev] produces a much higher degree of photographic realism and better handles technical camera requests like motion blur, but it fails to show the man actually repairing the bike. HiDream I1 Full captures the narrative and atmosphere of a Japanese street better, but is let down by significant anatomical errors and a lack of motion blur. FLUX.1 [dev] is the winner for its superior visual quality and adherence to the 50mm lens look.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent skin texture and realistic, lifelike eyes.
  • + Clean, professional lighting and shallow depth of field.
  • + Natural hair rendering and soft bokeh.
  • Failed to include the requested beads in the braids.
  • Armor is relatively plain and lacks the requested 'ornate engraved' detail.
  • Subject looks too clean and youthful, missing the 'battle-worn' and 'scarred' attributes.

HiDream I1 Full

  • + Perfectly captures 'battle-worn' with clear scars and dirt.
  • + Includes specific details like beads in braids and ornate engravings on the armor.
  • + Highly detailed texture on leather straps and metal as requested.
  • Image has a slightly artificial, over-sharpened digital look.
  • The light sources (torches) in the background look a bit muddy/low-resolution.

Verdict: HiDream I1 Full is the clear winner for prompt adherence as it included every specific detail from the beads in the hair to the scars and ornate armor engravings. While FLUX.1 [dev] produced a more photorealistic face, it ignored several key descriptive elements of the prompt, resulting in a character that looks too pristine for a 'battle-worn' paladin.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent professional graphic design layout with whitespace conservation.
  • + Consistent use of bold sans-serif fonts and clear hierarchy.
  • + High-quality, isolated food photography that fits a minimalist aesthetic.
  • Missed the 'grid' request for the photos, placing them more decoratively.
  • Body text is largely illegible gibberish.

HiDream I1 Full

  • + Successfully incorporated a grid layout for the images as requested.
  • + Very bold headings that are easy to read.
  • + Accurately included the pizza section in the header.
  • Repetitive food photos all showing the same pizza.
  • The layout feels cramped and lacks professional design finesse.
  • Font rendering for secondary text is inconsistent in size and alignment.

Verdict: FLUX.1 [dev] produces a much more professional and realistic menu design that adheres to the 'modern minimalist' aesthetic, despite missing the specific 'grid' prompt for photos. HiDream I1 Full satisfies the grid requirement but fails on variety, using nearly identical pizza photos and a much more cluttered, less polished composition. FLUX.1 [dev] is the winner for its superior visual quality and authentic graphic design feel.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent adherence to the menu items and prices requested in the prompt.
  • + Superior text rendering with almost zero spelling errors.
  • + Realistic chalk texture and weight in the handwriting.
  • The 'cursive' requirement for the title is not fully met, as it uses more of a print-style font.
  • Bottom text becomes slightly garbled with phrases like 'fresh drish'.

HiDream I1 Full

  • + Successfully used elegant cursive for the title as requested.
  • + Good chalk illustration of the coffee cup adds to the cafe aesthetic.
  • Complete failure to follow the specific menu items requested in the prompt.
  • Significant amount of gibberish text and nonsensical prices.
  • The font looks more like a digital overlay than natural hand-written chalk.

Verdict: FLUX.1 [dev] followed the prompt instructions very closely, capturing the specific menu items and pricing with high legibility, whereas HiDream I1 Full ignored the specific content requirements in favor of generic placeholder text. While HiDream I1 Full executed the cursive style for the title better, the overall utility and accuracy of FLUX.1 [dev] make it the clear winner.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Successfully followed the difficult spatial prompt of horse on top of astronaut.
  • + Clean, cinematic lighting with a high-quality finish.
  • + Strong adherence to the 'surreal' aspect of the prompt.
  • The horse's legs and hindquarters are physically distorted/anatomically incorrect.
  • The composition feels slightly static.

HiDream I1 Full

  • + Dynamic sense of movement and speed.
  • + High level of detail in the space suit and celestial background.
  • + Generally better anatomical rendering of the horse itself.
  • Failed the primary spatial constraint of the prompt: astronaut is riding the horse.
  • Cluttered composition with many background elements.

Verdict: This was a prompt-adherence challenge involving a specific spatial instruction: 'horse on top, not vice versa'. FLUX.1 [dev] is the winner because it actually followed this logic, creating a surreal image where the horse is the rider, whereas HiDream I1 Full ignore the specific instruction and produced a standard astronaut-on-a-horse image.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealistic texture on the capybara's fur.
  • + Accurate text rendering on the hat.
  • + High-quality lighting and realistic skin tones for the human character.
  • The woman appears to be in the front passenger seat rather than the back seat.
  • The hands and paws are a bit small and less distinct on the wheel.

HiDream I1 Full

  • + Correctly places the passenger in the back seat as requested.
  • + The capybara's paws are well-defined and clearly gripping the steering wheel.
  • + Composition better captures the depth of the taxi interior.
  • The woman's hand and phone interaction is physically distorted.
  • The background lighting/bokeh and fur texture feel slightly more artificial than Image A.

Verdict: FLUX.1 [dev] produced a more photorealistic image with superior textures and lighting, but failed the spatial requirement of placing the passenger in the back seat. HiDream I1 Full correctly interpreted the prompt's layout with the passenger clearly in the rear, though it suffered from anatomical issues in the passenger's hands. HiDream I1 Full is the likely winner for better adherence to the specific composition requested.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with a vibrant glowing jack-o-lantern.
  • + The thorny border is intricate and well-integrated into the composition.
  • + Most event details are present, though with some minor repetition.
  • The main title text is heavily distorted and misspelled as 'Falloween Rancy'.
  • The layout feels slightly cramped with the moon overlapping the pumpkin stem.

HiDream I1 Full

  • + Excellent parchment texture and overall vintage 'invitation' aesthetic.
  • + Included the requested spiderweb border elements along the corners.
  • + The 'You are invited' banner text is perfectly legible and aesthetically pleasing.
  • Completely failed to render the specific date, time, and location requested in the prompt.
  • The main title 'Halloween Party' is missing the word 'Invitation'.
  • The bottom text is gibberish ('Yootmber', '30 cm').

Verdict: Both models failed to deliver a perfect text-to-image result, but FLUX.1 [dev] followed the specific data instructions (date, time, location) much better than HiDream I1 Full. While HiDream I1 Full has a superior vintage artistic style and clearer banner text, its complete failure to include the correct event details makes it less useful as a requested invitation compared to FLUX.1 [dev].

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft lighting and refined textures that match the diorama feel.
  • + High artistic quality with delicate flower accents.
  • + Accurate sushi anatomy for nigiri pieces.
  • Significant text errors including 'SUSH CATON' and extra characters above Japan.
  • Text is very small and lacks the 'large bold' impact requested.

HiDream I1 Full

  • + Perfect adherence to text instructions with large bold 'JAPAN' and 'SUSHI'.
  • + Clean isometric representation with a professional UI-style aesthetic.
  • + Greater variety of sushi types (rolls, nigiri, gunkan) providing visual interest.
  • Missing the specific flag icon requested.
  • The textures are slightly more plastic/simple compared to the PBR request in model A.

Verdict: FLUX.1 [dev] produces a more beautiful, high-quality render with soft lighting, but fails significantly on the text typography. HiDream I1 Full perfectly captures the bold text layout and clean isometric diorama requested, making it the more functional output for the prompt despite slightly flatter textures.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft lighting with a warm, joyful atmosphere
  • + Clean, balanced composition
  • + Captures the sense of movement and 'tumbling' mentioned in the prompt
  • Fails to include a kitten, instead generating two dogs and two fox/rabbit hybrids
  • Stylization is more 'Disney-esque' / 3D render than hyper-photorealistic
  • Anatomy of the smaller animals is vague and cartoonish

HiDream I1 Full

  • + High level of detail in the fur textures and whiskers
  • + Successfully includes the kitten and fox as requested
  • + Stronger adherence to the photorealistic request compared to the competition
  • Missing the baby bunny from the requested list of four animals
  • The lighting is a bit harsh and lacks the 'god rays' effect of the other model
  • Composition feels a bit static and posed rather than playful

Verdict: Both models failed to include all four specific animal types correctly, but HiDream I1 Full is the winner for its superior texture detail and more realistic rendering style. FLUX.1 [dev] produced a very charming, polished image, but its failure to include a kitten and its shift toward a cartoon/3D animation aesthetic makes it less faithful to the 'hyper-photorealistic' prompt.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Elegant vector emblem style with clean lines
  • + Includes all requested text elements like Est. 1720 and a variation of the name
  • + Features a nicely detailed cloche and steam icon
  • Major spelling errors with 'Flarilaan' and 'Reseaurant'
  • The addition of random numbers '11011' and '1941' was not in the prompt

HiDream I1 Full

  • + Accurate rendering of the banner and 'Est. 1720' text
  • + Very clean, minimalist vector aesthetic fits the 'logo' requirement well
  • + Integrates a coffee cup theme inside the cloche creatively
  • Completely missing the primary text 'Caffè Florian'
  • The cloche handle is slightly off-center

Verdict: Both models struggled with the full prompt requirements. FLUX.1 [dev] produced a more complete emblem but suffered from significant spelling hallucinations, while HiDream I1 Full failed to include the brand name entirely despite a cleaner minimalist execution. FLUX.1 [dev] is slightly preferred for providing a layout that closer resembles a finished brand logo with all components present, even with the typos.

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.1 [dev]
HiDream I1 Full

AI Judge Analysis

FLUX.1 [dev]

  • + Captures the requested navy and muted red color palette perfectly.
  • + Includes icons for Lunar Orbit and Descent as requested in the specific mission steps.
  • + Maintains a clean, consistent vector style with a more complex, professional layout.
  • Text rendering is mostly nonsensical gibberish.
  • The trajectory shown depicts multiple planets with rings (like Saturn), which is inaccurate for an Apollo mission.

HiDream I1 Full

  • + Text is highly legible and correctly spells 'APOLLO 11'.
  • + Stronger 'NASA-inspired' graphic design feel with bold, blocky typography.
  • + Illustrates the Saturn V rocket with better anatomical accuracy for the launch step.
  • Fails to include all 6 requested steps, stopping after Translunar.
  • Included prompt instructions like '+ ICON' and 'UNLY' (likely for only) directly into the image text.
  • Uses a warmer orange instead of the requested 'muted red'.

Verdict: FLUX.1 [dev] followed the complex 6-step prompt instructions much better than HiDream I1 Full, though its text rendering remains unreadable. While HiDream I1 Full produced much cleaner text and a better Saturn V illustration, it failed to complete the requested mission sequence and accidentally printed prompt keywords like '+ ICON' into the graphic.

Next steps

Explore each model