Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [max]
25.9
arena score
#10 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 [max]
0%
win rate
Ties
0%
HiDream I1 Fast
0%
win rate
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 [max]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to lighting instructions, showing clear window light from the left.
- + Highly realistic textures on the book cover and wooden table.
- + Superior glass rendering with accurate reflections and refractions of the blue sphere.
- − The sphere reflection on the right side of the glass appears slightly disconnected from physics.
HiDream I1 Fast
- + Follows all prompt object placements correctly.
- + Clean composition with a minimalist aesthetic.
- − The sphere is disproportionately large for the description of a 'small sphere'.
- − The lighting is flat and lacks the specific 'from the left' directional quality requested.
- − The glass cube lacks thickness and realistic edge refraction compared to Model A.
Verdict: FLUX.2 [max] is the clear winner as it perfectly captures the specific lighting request and provides a significantly higher level of photorealism. While both models followed the spatial instructions, HiDream I1 Fast produced a much simpler image with less detail in the textures and less convincing glass effects.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the 'repairing' action with realistic hand placement and tools.
- + Strong implementation of motion blur on passing vehicles while maintaining subject clarity.
- + Very realistic skin textures and wet surfaces that look like a genuine 50mm photograph.
- − The framing feels slightly more calculated than 'imperfect' though it captures the street vibe well.
HiDream I1 Fast
- + Good reflections on the wet pavement.
- + Captures the 'light rain' atmosphere with a moody, cool-toned color palette.
- − The man is sitting on the bike rather than repairing it, missing the primary action of the prompt.
- − The anatomy of the man's hands and the bike's frame is distorted.
- − Missing the motion blur for passing cars; the background car is static.
Verdict: FLUX.2 [max] significantly out-performs HiDream I1 Fast by accurately depicting the man repairing the bicycle with realistic detail and motion-blurred traffic. While HiDream I1 Fast captures a moody atmosphere, it fails on the specific action requested and contains several anatomical and structural errors.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Exceptional photographic realism in skin texture and eyes
- + Highly detailed and realistic engraving on the plate armor
- + Subtle and believable application of dirt and scars
- − The lighting feels a bit flat compared to the dramatic 'torchlight' expectation
HiDream I1 Fast
- + Strong adherence to the 'hair braided with small beads' requirement
- + Warm, dramatic lighting that feels more like a torchlight source
- + Clearer inclusion of the leather straps mentioned in the prompt
- − Slightly over-saturated, 'digital art' look compared to Model A
- − The scars look like red paint rather than skin tissue
- − Armor engravings are less intricate and look slightly generic
Verdict: FLUX.2 [max] wins on pure technical execution, providing a lifelike portrait with incredible detail in the skin pores, eyes, and metal textures. While HiDream I1 Fast better incorporated the specific request for colorful beads and more dramatic torchlight, its overall image quality feels more like a video game render than a realistic photograph.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with distinct, readable sections for Appetizers, Pizza, and Mains.
- + High-quality, professional food photography organized in a clean grid.
- + Strong adherence to the minimalist aesthetic with appropriate use of white space and color accents.
- − Nonsense filler text for descriptions and social media handles.
- − One pizza item is incorrectly listed under the 'Mains' category header.
HiDream I1 Fast
- + Features a bold header which was requested in the prompt.
- + Follows the grid layout requested for food photos.
- − Extremely poor text rendering with severe distortions and gibberish.
- − Low visual quality and resolution in the food images, which appear muddy.
- − Fails to clearly separate sections for Pizza and Mains as requested.
Verdict: FLUX.2 [max] produced a professional-grade menu design that looks ready for a real restaurant, despite some meaningless text. HiDream I1 Fast struggled significantly with text legibility and image clarity, resulting in an unpolished and messy layout that does not meet the minimalist or professional criteria of the prompt.
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 [max]
HiDream I1 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent text rendering with clean, readable fonts
- + Highly detailed and realistic food textures
- + Dynamic 'exploded' composition that follows the prompt accurately
- − The starburst for the price is slightly more graphic/illustrative than the rest of the realism
- − Missing the physical fire at the bottom requested in the 'fiery background' description
HiDream I1 Fast
- + Good use of glowing fire effects on the title
- + Nice inclusion of actual burning coals at the base to ground the fiery theme
- − Significant text errors and duplication of price/messages
- − The 'exploded' effect is less pronounced with components overlapping closely
- − Lower overall image resolution and texture clarity
Verdict: FLUX.2 [max] is the clear winner as it successfully rendered all required text perfectly and followed the 'exploded' layout prompt with high-fidelity detail. HiDream I1 Fast struggled with the secondary text, resulting in garbled words and repetitive layout elements, and lacked the crispness found in the FLUX image.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Perfect text rendering with zero spelling errors across all menu items.
- + Highly realistic chalk texture, including smudges and authentic variation in stroke pressure.
- + Excellent adherence to the date and price requirements specified in the prompt.
HiDream I1 Fast
- + Includes a nice environmental context with a cozy café setting in the background.
- + Generally captures the 'cursive cursive' request for the title better than Model A.
- − Extreme text rendering errors including overlapping letters and nonsensical characters.
- − Fails to correctly render the requested menu prices and item names.
- − The layout is cluttered and messy, lacking the professional look of a real café board.
Verdict: FLUX.2 [max] significantly outperforms HiDream I1 Fast by delivering perfectly legible text and a highly realistic chalk texture that matches every requirement of the prompt. While HiDream I1 Fast attempts a more complex background, the actual content of the chalkboard is garbled and contains numerous spelling and formatting errors.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the 'in space' setting with a cinematic galaxy background.
- + High level of detail on the space suit and horse textures.
- + Good lighting and composition that creates a surreal atmosphere.
- − Failed the specific spatial instruction 'horse on top, not vice versa' by placing the astronaut on the horse.
HiDream I1 Fast
- + Clean visual style with good lighting on the subject.
- + Relatively realistic horse anatomy and movement.
- − Completely ignored the 'in space' setting, placing the scene in a desert instead.
- − Failed the specific spatial instruction 'horse on top, not vice versa'.
- − Lower resolution and visible artifacts around the horse's legs.
Verdict: Both models failed the 'trick' prompt instruction to place the horse on top of the astronaut. However, FLUX.2 [max] significantly outperformed HiDream I1 Fast by correctly identifying the space setting and providing much higher visual detail. HiDream I1 Fast ignored the space environment entirely, rendering a standard desert scene.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent interior taxi lighting that creates a realistic atmosphere
- + Strong prompt adherence by placing the human in the back seat as requested
- + Detailed capybara head texture and appropriate driver attire
- − The driver hands are clearly human hands rather than capybara paws
- − The capybara's head is not anatomically connected well to the human-like torso
HiDream I1 Fast
- + High contrast lighting and vibrant night city colors through the window
- + Clear text 'TAXI' on the driver's cap
- + Detailed rendering of the businesswoman's facial features
- − Failed the spatial prompt instruction by placing the woman in the front passenger seat
- − Like Model A, the hands on the steering wheel are human rather than capybara paws
- − Composition feels cramped with both characters in the front row
Verdict: FLUX.2 [max] followed the complex spatial instructions of the prompt much better, correctly placing the woman in the back seat to create the requested 'bored passenger' narrative. While both models struggled to render actual capybara paws on the steering wheel (using human hands instead), FLUX.2 [max] produced a more convincing and atmospheric interior scene.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Perfect text rendering for all requested details, including the scroll and date.
- + Highly realistic, cinematic lighting with a polished gothic aesthetic.
- + Excellent composition that feels like a professional movie poster or high-end invitation.
- − The border is a bit dark, making it slightly harder to distinguish the thorns and webs against the background.
HiDream I1 Fast
- + Good use of the 'dark parchment' texture as a central focus.
- + Strong silhouettes for the twisted trees and bats.
- − Text rendering is poor, with garbled words on the banner and repeated location info.
- − The illustration style is more cartoonish and lack the 'cinematic' polish requested.
- − Failed to include the full title 'Halloween Party Invitation', truncating it to 'Halloween Party'.
Verdict: FLUX.2 [max] is the clear winner as it flawlessly rendered all requested text and maintained a high-quality, cinematic atmosphere. HiDream I1 Fast struggled significantly with the text on the scroll and the event details, resulting in an unpolished and cluttered layout.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the 45-degree isometric perspective.
- + Clean and professional typography that follows the layout instructions perfectly.
- + Sophisticated lighting and soft, refined textures create a cohesive 3D cartoon aesthetic.
- − The sushi and props are quite small within the frame relative to the diorama base.
HiDream I1 Fast
- + Strong '3D cartoon' character design with chunky, appealing shapes.
- + Good use of color and high-quality rice texture rendering.
- + Bold and clear text rendering.
- − Perspective is more eye-level/cinematic than the requested 45-degree isometric top-down view.
- − The typography layout includes extra decorative lines and icons not requested in the prompt.
- − The sushi roll in the front has a confusing internal texture that looks like a sticker.
Verdict: FLUX.2 followed the technical constraints much more accurately, specifically regarding the isometric 45-degree angle and the exact layout of the text elements. While HiDream I1 Fast produced a very charming character-style sushi, it failed to capture the requested diorama perspective and added unnecessary graphical elements to the header.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the prompt by including all four distinct animals: puppy, kitten, bunny, and fox kit.
- + Realistic scale and interaction between the animals with dynamic poses.
- + High-quality lighting including subtle god rays and realistic dew sparkles in the grass.
- − The fox's front paws are slightly stylized/blackened in a way that looks a bit like socks rather than natural fur transition.
HiDream I1 Fast
- + Warm, vibrant color palette that captures the 'joyful' vibe well.
- + Good texture on the puppy and fox fur.
- − Fails to include the bunny, instead providing two kittens.
- − The composition is static and the animals are not 'playfully chasing' or 'tumbling' as requested.
- − Lower overall clarity and detail in the background compared to Model A.
Verdict: FLUX.2 [max] significantly outperformed HiDream I1 Fast by following the complex list of subjects perfectly, whereas HiDream I1 Fast missed the bunny and provided a static pose. FLUX.2 [max] also captured the requested dynamic actions of chasing and tumbling with much higher fidelity and atmospheric detail.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography including the requested accent mark on 'Caffè'.
- + Perfect adherence to all prompt elements including the 'Est. 1720' banner.
- + Clean, professional vector aesthetic with subtle background texture.
- − The steam is a bit simplistic compared to the rest of the illustration.
HiDream I1 Fast
- + Strong contrast with bold brown and cream tones.
- + Creative use of the cloche dome as a frame for the main text.
- − Typographical error in the date, displaying '17210' instead of '1720'.
- − The steam effect looks more like abstract swirls or decorative marks.
- − Line work is slightly less clean and appears more like a painting than a vector emblem.
Verdict: FLUX.2 [max] significantly outperformed HiDream I1 Fast by following every detail of the prompt, most notably the specific date. While HiDream I1 Fast had a bolder color palette, its failure to render '1720' correctly and its less refined vector lines make it the weaker choice for a logo design.
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 Fast
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with very high legibility for technical terms.
- + Sophisticated flat-vector style that adheres perfectly to the requested NASA-inspired palette.
- + Logical layout that follows the chronological steps of the mission across panels.
- − Repeats the label 'Earth Orbit' across multiple panels unnecessarily.
- − The Saturn V icon looks more like a modern shuttle/capsule hybrid than the historical rocket.
HiDream I1 Fast
- + Features a bold, clear central 'APOLLO 11' title.
- + Uses an iconic Saturn V silhouette that reflects the historical rocket shape better than the competitor.
- − Text rendering is poor with several misspellings like 'DESCENG' and 'EARH OPBIT'.
- − Composition is cluttered and the icons do not logically correspond to the labels provided.
- − The vector style is messy with jagged edges and artifacts.
Verdict: FLUX.2 [max] produced a professional, high-quality infographic with clean lines and mostly accurate text, successfully capturing the 'modern vector' aesthetic. In contrast, HiDream I1 Fast struggled with text legibility and logical grouping, resulting in a cluttered layout with several artifacts. Although FLUX.2 [max] had some labeling redundancies, its overall visual polish makes it the clear winner.
Next steps
Explore each model
Distilled version of HiDream AI's 17B parameter text-to-image model