Black Forest Labs' open-weights image generation model with frontier performance, available for non-commercial local deployment
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev]
24.5
arena score
#18 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]
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'small' sphere requirement
- + Superior lighting and texture on the wooden table
- + High-quality reflections and realistic glass thickness
- − The window lighting appears to come more from the top-left rather than purely the side
HiDream I1 Fast
- + Clear visibility of the green plant through the glass
- + Clean minimalist composition
- − The sphere is disproportionately large, ignoring the 'small' descriptor
- − The blue sphere appears to be floating rather than resting on the bottom of the cube
- − Artificial-looking glass edges that lack realistic depth
Verdict: FLUX.2 [dev] followed the spatial instructions much more accurately, correctly rendering a 'small' sphere resting on the base of the cube. HiDream I1 Fast failed on the scale of the sphere and its placement, making it look like it was hovering, while also producing a less realistic wood texture.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'motion blur from passing cars' instruction.
- + Highly realistic skin textures and wet surfaces.
- + Accurate 50mm lens look with natural shallow depth of field.
- − The hands have some slight anatomical structural issues common in AI.
HiDream I1 Fast
- + Good reflections on the wet pavement.
- + Clear subject focus and composition.
- − Failed to include motion blur on passing cars as requested.
- − The man's scale relative to the bicycle and the background car feels slightly off.
- − Image has a slightly more 'generated' and smoothed finish compared to the prompt's request for no stylization.
Verdict: FLUX.2 [dev] followed the complexity of the prompt much better, specifically capturing the motion blur of the traffic and the specific 50mm 'candid' feel. HiDream I1 Fast produced a clean image but ignored the motion blur requirement and looks less grounded in reality due to the lack of natural skin texture and imperfect framing.
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]
HiDream I1 Fast
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [dev]
- + Excellent photographic realism with realistic skin texture and subtle scars.
- + Lighting interaction is physics-accurate, especially the warmth on the metal and skin.
- + Fine details on the leather straps and metal engravings feel grounded and tactile.
- − The hair beads are a bit repetitive in pattern.
- − The battle-worn effect is slightly understated compared to the prompt's potential.
HiDream I1 Fast
- + Intricate armor engravings and very clear braiding in the hair.
- + Strong presence of the requested beads and colorful accents.
- + Dramatic lighting and composition.
- − Skin texture appears overly smooth and 'digital,' lacking lifelike pores.
- − The scar on the forehead looks like a red paint stroke rather than an actual healed or fresh wound.
- − The armor has some structural inconsistencies where the plates meet.
Verdict: FLUX.2 [dev] produces a significantly more lifelike and cohesive image that feels like a real photograph, with superior skin texture and natural lighting. HiDream I1 Fast has a more stylized, digital art aesthetic that makes the details feel artificial, particularly the skin and the scar rendering.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography with a clean, grid-based layout.
- + Successfully included all requested sections: Appetizers, Pizza, and Mains.
- + High visual quality and realistic food photography.
- − Nonsense text for item descriptions and some headings.
- − Some overlap between sections makes the categories a bit confusing.
HiDream I1 Fast
- + Strong bold headers that capture the requested casual dining feel.
- + Provides a clear grid of food photos.
- − Poor resolution and artifacting on the text and photos.
- − Mismatched content where the text says 'Appetizers' but the grid is almost entirely pizza.
- − Text rendering is distorted and messy compared to Model A.
Verdict: FLUX.2 [dev] significantly outperforms HiDream I1 Fast in terms of layout professionality, image resolution, and design coherence. While both models struggle with generating semantic text, FLUX.2 [dev] produces a much more realistic and usable menu design that adheres to the minimalist and grid-based requirements.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent text rendering with perfect spelling and glowing effects.
- + Superior photorealistic textures on the patty and bun.
- + Stronger 'exploded' effect with distinct separation of all layers.
- − The cheese looks somewhat flat and artificial compared to the other ingredients.
HiDream I1 Fast
- + Includes more toppings like pickles and onions for a denser looking burger.
- + Good use of glowing embers and fire at the base of the image.
- − Failed the 'exploded' instruction as the burger is mostly assembled.
- − Text rendering is messy with spelling errors like 'LIMITED TIMW' and distorted pricing.
- − Lighting on the burger is inconsistent with the fiery background.
Verdict: FLUX.2 [dev] followed every aspect of the prompt, delivering a truly exploded burger with clean, legible, and stylized text as requested. HiDream I1 Fast failed to properly separate the burger layers and struggled significantly with text rendering and spelling, resulting in a much less professional advertisement.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent text rendering with near-perfect spelling and legibility
- + Very realistic chalk texture with smudges and natural variations
- + Strong adherence to the requested menu items and formatting
- − Has a slight smudge overlap in the center of the 'Grilled Octopus' section
HiDream I1 Fast
- + Cozy café atmosphere with good depth of field
- + Charming cursive style for the title
- − Severe text rendering issues including overlapping letters and typos
- − Failed to correctly list the menu items, repeating prices and cluttering lines
- − Chalk texture looks more like a digital brush than physical chalk
Verdict: FLUX.2 [dev] significantly outperforms HiDream I1 Fast by delivering clear, legible, and accurately spelled text that follows every part of the prompt. While HiDream I1 Fast creates a nice background scene, the chalkboard text is garbled, contains several errors, and lacks the realistic chalk texture present in FLUX.2 [dev].
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [dev]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'in space' setting with detailed celestial backgrounds.
- + High tactile detail on both the space suit and the horse's fur.
- + Dynamic, surreal composition with the shadow cast on the atmosphere below.
- − The transition between the horse's hooves and the clouds is slightly muddy.
HiDream I1 Fast
- + Clean, well-defined character and animal subject.
- + Accurate anatomical depiction of both the horse and the astronaut's riding posture.
- − Failed the location prompt by showing a desert instead of space.
- − Lacks the 'surreal' quality requested in the prompt.
- − Low background detail and simpler lighting compared to the competitor.
Verdict: FLUX.2 [dev] followed all aspects of the prompt, including the specific 'in space' setting and the 'surreal' style. HiDream I1 Fast failed to place the subject in space, instead rendering an astronaut on a horse in a desert, which neglected the primary environmental instruction.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the 'both front paws on the steering wheel' prompt with realistic animal-like hands.
- + Features a much more authentic taxi interior with appropriate dashboard lighting and textures.
- + Characters are positioned correctly within the spatial logic of a car (capybara in front, woman in back).
- − The capybara's fur texture is slightly soft compared to the high-contrast background.
- − The composition is a bit tight, cutting off the top of the taxi.
HiDream I1 Fast
- + Strong bokeh effect in the background effectively captures the New York night atmosphere.
- + Detailed capybara facial hair and fur texture.
- − The passenger is sitting in the front passenger seat rather than the back seat as requested.
- − The capybara has distinct human hands holding the steering wheel, which is uncanny.
- − The perspective is physically impossible, as if looking through a side pillar that doesn't exist.
Verdict: FLUX.2 [dev] followed the spatial instructions much better, correctly placing the businesswoman in the back seat and giving the capybara animal paws. HiDream I1 Fast failed the prompt by placing the passenger in the front seat and using immersion-breaking human hands for the animal driver.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Perfect text rendering for all lines of the prompt
- + Excellent composition with a professional, cinematic aesthetic
- + Faithful adherence to the thorn and web border request
- − The jack-o-lantern is quite dark, though the glow is effective
HiDream I1 Fast
- + Vibrant colors that stand out
- + Includes the scroll banner as requested
- + Good use of negative space in the sky
- − Serious text rendering errors and repetition at the bottom
- − Border lacks the 'thorns' detail requested, opting for simpler flourishes
- − Graphic design looks like clip-art rather than polished cinematic art
Verdict: FLUX.2 [dev] significantly outperforms HiDream I1 Fast by following every instructional detail, including complex text and specific layout elements like the thorn border. While HiDream I1 Fast captures the general mood, its text is garbled and repetitive, and the composition lacks the polished 'cinematic' quality requested.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent text rendering and alignment.
- + High-quality PBR textures with realistic subsurface scattering on the fish.
- + Superior isometric composition with a clean diorama base.
- − The 'JAPAN' text is slightly off-center to the left compared to the Sushi text and flag.
HiDream I1 Fast
- + Successfully includes the requested flag icon and text.
- + Includes extra elements like chopsticks that fit the theme.
- + Bright, appealing cartoon colors.
- − Perspective and scale are inconsistent; the nigiri is massive compared to the maki rolls.
- − The text layout is cluttered with extra lines and artifacts.
- − The nigiri sushi has an illogical filling inside the rice block.
Verdict: FLUX.2 [dev] significantly outperforms HiDream I1 Fast in terms of visual polish, realistic material rendering, and logical consistency. While HiDream I1 Fast follows the prompt requirements, it suffers from poor scaling and strange anatomical choices in the food, whereas FLUX.2 [dev] delivers a professional, high-clarity 3D render look.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Perfectly includes all requested animals: retriever, kitten, fox, and bunny.
- + Superior rendering of lighting with realistic god rays and backlighting through fur.
- + Exceptional detail in the wildflower meadow and dew sparkles.
- − Includes an extra bunny not specifically mentioned in the count, though it fits the 'baby animals' theme.
- − The animals are posing more than 'tumbling' as requested.
HiDream I1 Fast
- + Captures a very warm, vibrant golden hour aesthetic.
- + Good expression on the fox kit's face.
- − Completely missed the 'baby bunny' requirement from the prompt.
- − Noticeable anatomical errors, such as the kitten on the left having a distorted body/paw structure.
- − Lower overall clarity and texture detail compared to Model A.
Verdict: FLUX.2 [dev] is the clear winner as it successfully included all four types of animals requested, whereas HiDream I1 Fast failed to include the bunny. FLUX.2 [dev] also provided much higher image fidelity, realistic fur textures, and a more sophisticated lighting setup that truly captured the 'masterpiece' quality requested.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography with perfect spelling of the name and establishment date.
- + Authentic vintage woodcut/vector style with appropriate subtle texture.
- + Strong composition and clean banner execution.
- − The steam element is a bit small and simplistic compared to the rest of the logo.
HiDream I1 Fast
- + Creative use of a circular frame to encompass the logo elements.
- + Good use of warm brown and cream tones as requested.
- − Significant spelling error in the date, rendering it as '17210'.
- − Confusing placement of text inside the cloche which breaks the vector emblem aesthetic.
- − Visual artifacts and messy lines in the steam and frame.
Verdict: FLUX.2 [dev] followed all instructions perfectly, creating a professional-grade vector logo with precise typography and a convincing vintage texture. HiDream I1 Fast failed on a fundamental level by hallucinating an extra digit in the establishment date and producing a less cohesive design. FLUX.2 is the clear winner for its functional and accurate execution of the design brief.
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]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [dev]
- + Excellent vector iconography with sharp, clean lines.
- + High quality text rendering for major labels and mission names.
- + Superior adherence to the specific mission sequence requested in the prompt.
- − Includes several extra icons not requested in the sequence.
- − Minor typos in smaller sub-text like 'Tranquility' and 'LUREST'.
HiDream I1 Fast
- + Strong adherence to the requested NASA-inspired color palette.
- + Good central composition of the Saturn V rocket.
- − Poor text rendering with numerous illegible characters.
- − Incorrect mission sequence mapping (icons do not match their labels).
- − Visual quality is blurry with artifacts, failing the 'crisp lines' requirement.
Verdict: FLUX.2 [dev] significantly outperforms HiDream I1 Fast by delivering a professional, clean vector aesthetic with readable text and accurate iconography that follows the requested 6-step sequence. While FLUX.2 includes additional icons, the overall composition and technical execution are vastly superior to the blurry and disorganized output of HiDream I1 Fast.
Next steps
Explore each model
Distilled version of HiDream AI's 17B parameter text-to-image model