Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [klein] 9B 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 [klein] 9B

20.6 arena score

#13 of 32 in Image Editing

Skill signature · Image Editing

HiDream I1 Full

13.7 arena score

#60 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [klein] 9B

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent depiction of the glass cube with realistic thickness and refraction.
  • + High detail on the wooden table texture and the grains of the book pages.
  • + Perfect lighting consistency from the left side.
  • The glass cube is slightly more rectangular/tall than a perfect cube.
  • The blue sphere appears to be floating without a clear reason, though this matches the prompt literally.

HiDream I1 Full

  • + Successfully includes the blue sphere inside a sharp glass cube.
  • + Good placement of the green plant in the background as requested.
  • + The lighting on the table surface is warm and atmospheric.
  • The glass cube has strange internal reflections that look like duplicate spheres.
  • The red book has a slightly unnatural texture on its cover.
  • The cube's edges look a bit thin and less like solid glass compared to Model A.

Verdict: Both models followed the prompt instructions very well. FLUX.2 [klein] 9B is the winner due to its superior rendering of glass physics, material textures, and more realistic soft lighting. HiDream I1 Full is a strong competitor but suffers from slightly distracting artifacts in the glass reflections.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent skin texture and realistic age-related details on the man's hands and face.
  • + Superior mechanical accuracy of the bicycle components and tools.
  • + Stronger adherence to the 'candid' and 'imperfect framing' prompt with a believable composition.
  • Minimal motion blur on the passing cars despite the prompt's request.

HiDream I1 Full

  • + Effective captures the mood of light rain and wet pavement reflections.
  • + Follows the shallow depth of field instruction well with a blurry background.
  • The man is oddly sitting on/straddling a tiny bicycle, which makes the scale feel incorrect.
  • The bicycle's anatomy is nonsensical, particularly the handlebars and lack of a front wheel fork.
  • Face and skin textures look smoother and more 'AI-restored' compared to the other model.

Verdict: FLUX.2 [klein] 9B is the clear winner as it provides a highly realistic, gritty, and mechanically sound image that looks like actual street photography. HiDream I1 Full fails on basic anatomy and scale, with the elderly man appearing to float or sit awkwardly on a bicycle that is missing key parts and is far too small for him.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Exquisite detail on the engraved armor and weathered leather straps.
  • + Highly realistic skin texture with authentic-looking scars and dirt.
  • + Perfectly executed bokeh and lighting that feels integrated into the scene.
  • The hair braids are a bit simplistic compared to the rest of the high-fidelity detail.

HiDream I1 Full

  • + Great lighting on the face creating a dramatic, intense expression.
  • + Captured the 'battle-worn' aesthetic well with noticeable scarring.
  • + Good use of depth of field with the torchlight in the background.
  • Texture on the armor and straps is significantly less detailed and more blurry than the other model.
  • The braid beads look more like biological growth than intentional jewelry.
  • Lower overall sharpness and technical clarity.

Verdict: FLUX.2 [klein] 9B is the clear winner due to its superior rendering of textures, particularly on the leather straps and the intricate engravings of the armor. While HiDream I1 Full captures the mood well, it lacks the fine detail and realism found in the skin and metal of the FLUX image.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent professional graphic design layout
  • + Includes all three requested category sections (Appetizers, Pizza, Mains)
  • + High-quality, realistic food photography photography
  • Text rendering is mostly gibberish despite the professional look
  • Section headers overlap logically (showing pizza under appetizers)

HiDream I1 Full

  • + Legible 'RESTAURANT MENU' main header
  • + Clean white background with minimal distractions
  • + Good alignment of text and images
  • Every single photo is a pizza, failing the variety requested in 'colorful food photos'
  • Layout is less sophisticated and looks like a generic template
  • Pricing and text details are nonsensical (e.g., '200' for a main)

Verdict: FLUX.2 [klein] 9B produces a much more realistic and professional menu design that captures the 'casual dining' vibe perfectly, despite the garbled text. HiDream I1 Full fails significantly on variety, providing only pizza images when the prompt requested different food sections, making it less useful as a design mockup.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent adherence to the specific text requested in the prompt.
  • + Realistic chalk texture with visible smudges and erased marks on the board.
  • + Consistent and authentic-looking handwriting style throughout the entire board.
  • Small spelling error in the bottom footer ('fress' instead of 'fresh').

HiDream I1 Full

  • + Includes a charming coffee cup illustration that fits the café theme.
  • + Clean layout with a high-contrast wood frame.
  • Completely ignored the specific menu items requested in the prompt.
  • The text is largely gibberish with repeated prices.
  • The font looks too digital and uniform, lacking the authentic chalk variation requested.

Verdict: FLUX.2 [klein] 9B is the clear winner as it followed the complex text instructions almost perfectly, creating an authentic-looking chalkboard with realistic textures. In contrast, HiDream I1 Full failed to include the requested menu items, providing a board filled with nonsensical text and a font that looks synthetic rather than handwritten.

The Reversed Rodeo

Text-to-Image

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

FLUX.2 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + High level of detail in the astronaut's suit and the horse's anatomy
  • + Vibrant and complex space background with various textures
  • + Sharp rendering of facial features inside the helmet
  • Completely failed the negative constraint to put the horse on top
  • Includes nonsensical AI-generated text at the bottom
  • The composition feels a bit cluttered with too many planets

HiDream I1 Full

  • + Strong cinematic lighting with a clear horizon line
  • + Dynamic sense of motion with the horse's pose
  • + Cleaner composition compared to the other model
  • Failed the negative constraint to put the horse on top of the astronaut
  • Anatomy issues with the horse's front legs and hooves
  • Low texture detail on the astronaut suit

Verdict: Both models failed the specific spatial instruction to place the horse on top of the astronaut, instead defaulting to the common 'astronaut riding a horse' trope. FLUX.2 [klein] 9B provides a much more detailed and polished image, despite the hallucinated text, whereas HiDream I1 Full appears more generic with noticeable anatomical flaws 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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent photorealistic texture on the capybara fur and the car interior.
  • + The perspective through the windshield accurately depicts a night street in Manhattan.
  • + Perfectly captures the 'bored' expression of the passenger as requested.
  • The passenger is sitting in the front passenger seat instead of the 'back seat' specified in the prompt.
  • The text on the cap is slightly distorted ('NEIV TALA').

HiDream I1 Full

  • + Successfully places the passenger in the back seat as requested.
  • + The capybara's pose on the steering wheel is dynamic and natural.
  • + Good lighting on the car frame and character subjects.
  • The passenger's hands and phone are blurry and poorly rendered.
  • The framing of the taxi is slightly illogical, showing an open window perspective that cuts off the roof.
  • Noticeable digital smoothing makes the capybara look less realistic than Image A.

Verdict: FLUX.2 [klein] 9B produces a significantly more realistic and detailed image with superior lighting and textures, though it fails the spatial instruction to put the passenger in the back seat. HiDream I1 Full follows the backseat instruction correctly but suffers from lower image quality, particularly regarding the passenger's distorted hands and the overall 'AI-generated' look of the hair and fur.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Perfect text rendering, including the specific date, time, and location.
  • + Strong cinematic lighting with a glowing jack-o-lantern and a moody, atmospheric background.
  • + Excellent adherence to all visual elements like thorns, webs, and a small scroll banner.
  • The central Jack-o-lantern is quite large, pushing the event details to the bottom edge.

HiDream I1 Full

  • + Effective use of negative space in the layout, making text easier to read.
  • + Good inclusion of stylized gothic bats and trees.
  • Failed significantly on text accuracy, hallucinating words like 'Yootmber' and missing the location.
  • Missing the specific 'thorn' element requested for the border.
  • The aesthetic is more clip-art style rather than the 'cinematic' and 'polished' look requested.

Verdict: FLUX.2 [klein] 9B followed the prompt with near-perfect accuracy, particularly regarding the specific text details for the event and the cinematic lighting request. HiDream I1 Full struggled with text generation and failed to include the specific date and location requested, resulting in a less professional final product.

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 [klein] 9B
Before After
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent source preservation, keeping the face, glasses, clothing, and background nearly identical to the original.
  • + High-density hair with realistic texture and a convincing hairline.
  • Small stray hairs slightly overlap the frame of the glasses in an unnatural way.

HiDream I1 Full

  • + Successfully adds hair to the back of the head.
  • Fails significant source preservation by changing the background environment entirely.
  • Adds bizarre artifacts like a black strap or device across the person's face.
  • Changes facial features significantly and removes the glasses.

Verdict: FLUX.2 [klein] 9B followed the edit instructions perfectly, adding a realistic head of hair while keeping the person and environment consistent with the source. In contrast, HiDream I1 Full failed on almost every metric, altering the face, removing the glasses, changing the background, and adding nonsensical artifacts.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent 3D miniature aesthetic with soft, refined 3D textures
  • + Clear and legible typography for both text elements
  • + Clean isometric composition on a realistic wood-textured diorama base
  • The flag icon is incorrect, resembling the flag of Yemen rather than Japan
  • The sushi shapes are slightly odd, specifically the nori wrap around the nigiri

HiDream I1 Full

  • + Strong 3D cartoon style with vibrant colors
  • + Good variety of sushi types within the miniature scene
  • + Correct isometric perspective and square framing
  • Completely failed to include the requested flag icon
  • The typography is less refined and lacks the 'bold' contrast requested
  • Background shows minor texture artifacts rather than being a solid flat color

Verdict: FLUX.2 [klein] 9B is the preferred output because it followed the complex layout instructions more closely, including both tiers of text and the flag icon (though the flag colors were incorrect). HiDream I1 Full produced a generic 3D scene that ignored the flag icon and had less precise 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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Expertly incorporates all requested elements: TV anchor desk, hockey arena setting, and numerous dogs in the crowd.
  • + Strong caricature style with exaggerated proportions that still maintain facial recognition of the source subject.
  • + Excellent storytelling, showing the subject in a professional suit vs. the source denim, fitting the 'job' prompt.
  • The right hand (thumbs up) has anatomical issues with finger count and positioning.
  • Text on the screens and banner is garbled and nonsensical.

HiDream I1 Full

  • + Maintains the denim jacket from the source image, providing higher source preservation.
  • + Includes a cute, well-rendered dog caricature perched on the shoulder.
  • + High visual clarity and clean line work.
  • Fails to incorporate the 'hockey' aspect of the prompt in any meaningful way.
  • The 'TV show anchor' aspect is very weak, represented only by a blurred TV in the background rather than active involvement.
  • The caricature exaggeration is very subtle compared to Model A.

Verdict: FLUX.2 [klein] 9B is the clear winner as it fully realized the complex prompt, successfully merging a TV studio setting with a hockey arena and dogs. While HiDream I1 Full produced a clean image, it ignored the hockey requirement and provided a much less creative interpretation of the 'tv anchor' role.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent fur texture and fine detail rendering
  • + Dynamic and playful composition with active posing
  • + Successfully includes multiple colorful butterflies and flowers
  • Failed to include the baby bunny requested in the prompt
  • The kitten has an anatomically awkward middle leg-like limb emerging from its chest

HiDream I1 Full

  • + Warm and vibrant color palette with strong lighting
  • + Cute animal characters with expressive, large eyes
  • + Good preservation of the 'wholesome' vibe
  • Failed to include the baby bunny requested in the prompt
  • Included two kittens instead of one kitten and one bunny
  • Lower resolution/clarity in fine details like fur and flowers compared to the competitor

Verdict: Both models failed to include the requested baby bunny, with HiDream I1 Full substituting it for a second kitten. FLUX.2 [klein] 9B is the winner due to its significantly higher image clarity, realistic fur textures, and dynamic composition, whereas HiDream I1 Full looks more illustrative and less photorealistic.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent preservation of the original poses and character composition.
  • + Perfect execution of the soft pastel 'hand-painted' watercolor aesthetic typical of Ghibli concept art.
  • + Maintains the distinct plaid pattern of the man's shirt from the source image.
  • Lacks the 'unhappy' facial expression of the partner on the right, making her look pleasant instead of jealous.
  • The background is significantly altered from an urban street to a rural mountain village.

HiDream I1 Full

  • + Strong 'modern anime' character designs with expressive blush.
  • + Includes thematic Ghibli-esque background elements like Japanese signage.
  • Completely loses the original character poses, especially the distinct head turn of the man.
  • Alters character appearances too much, replacing the plaid shirt with a floral one and adding a beard and hat.
  • The character on the right is looking away from the man, losing the narrative's core 'distracted boyfriend' dynamic.

Verdict: FLUX.2 [klein] 9B is the superior edit because it retains the essential structure and poses of the iconic meme while perfectly capturing the requested watercolor art style. HiDream I1 Full fails as an edit by completely reimagining the character designs and poses, losing the identifiable narrative of the source image.

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 [klein] 9B
Before After
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent source preservation, maintaining the identity of the woman and the dog perfectly.
  • + Successfully added wind-blown hair and fallen leaves without distorting the background.
  • + Clean integration of new elements into the existing lighting/shadow profile.
  • The wind effect on the hair is slightly symmetrical and looks a bit digital/artificial.

HiDream I1 Full

  • + Successfully captures a high sense of energy and motion.
  • + Good leaf distribution throughout the scene.
  • Poor source preservation; completely removed the dog from the image.
  • Significantly changed the woman's appearance, clothing details, and pose.
  • Low fidelity with noticeable blurring/artifacts in the background and hands.

Verdict: FLUX.2 [klein] 9B is the clear winner as it successfully applied the requested edits while keeping the original image intact. HiDream I1 Full failed the image editing task by hallucinating a new person and completely removing the golden retriever present in the source image.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Excellent typography including the specific name 'Caffè Florian' with correct accents.
  • + Clean vector emblem style with high-quality line work.
  • + Perfect adherence to color and texture requirements.
  • The steam effect is a bit singular and thick compared to natural steam.

HiDream I1 Full

  • + Elegant cloche silhouette with a nice internal coffee cup graphic.
  • + Good use of the 'Est. 1720' banner.
  • + Appropriate warm color palette.
  • Failed to include the primary business name 'Caffè Florian' from the prompt.
  • The banner is disconnected from the main emblem, hurting the composition.
  • Lacks the requested subtle texture on the background.

Verdict: FLUX.2 [klein] 9B followed the prompt instructions perfectly, including the specific name and the requested vintage texture. HiDream I1 Full produced a generic icon but missed the actual name of the restaurant, making it unusable as a logo for the requested brand.

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 [klein] 9B
HiDream I1 Full

AI Judge Analysis

FLUX.2 [klein] 9B

  • + Successfully includes all 6 requested steps of the mission.
  • + Excellent adherence to the color palette and vector style.
  • + Clear, clean layout that functions well as an infographic.
  • Several spelling errors in the labels (e.g., 'EARDHT', 'TRANSLURAL', 'ARMSTROMG').
  • Flow of arrows is somewhat disorganized and non-linear.

HiDream I1 Full

  • + Superior text rendering for the main title with no spelling errors in the word 'APOLLO'.
  • + Clean, balanced composition with high visual appeal.
  • + Effective use of negative space and navy blue NASA-inspired background.
  • Failed to include all 6 steps requested, stopping after step 3.
  • Literal interpretation of prompt text in labels (e.g., '+ ICON', '+ UNG').
  • Includes a planet with rings that is not relevant to the Apollo 11 moon mission.

Verdict: FLUX.2 [klein] 9B followed the complex multi-step instructions much better, providing a complete infographic from launch to landing, despite significant spelling issues. HiDream I1 Full has much cleaner graphic design and better title text, but it failed to follow the logical sequence of the prompt and included irrelevant imagery like a ringed planet. FLUX.2 is the better choice for content accuracy, while HiDream is better for pure aesthetic quality.

Next steps

Explore each model