Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [flex]
#14 of 62 in Text-to-Image
HiDream I1 Fast
#51 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [flex]
0%
win rate
Ties
0%
HiDream I1 Fast
0%
win rate
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent photorealistic rendering of materials and lighting.
- + The plant is clearly visible through the glass cube as requested.
- + The soft window light is realistically directional and matches the shadows.
- − The sphere is quite large relative to the cube, rather than 'small' as requested.
HiDream I1 Fast
- + Strong composition with a clear focus on the subject.
- + Good textures on the book and table surface.
- − The glass refractive logic is slightly flawed, making the plant behind it appear disconnected or absent.
- − The sphere appears to be floating rather than resting on the bottom of the cube.
- − The light source feels less clearly directional than Model A.
Verdict: FLUX.2 [flex] produced a more coherent and realistic image, particularly in how the plant is refracted through the glass and how the lighting interacts with the scene. While the sphere in FLUX.2 [flex] is a bit larger than described, HiDream I1 Fast struggles with the physics of the scene, showing a floating sphere and a less convincing glass effect.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to the 'repairing' aspect of the prompt, with a realistic kneeling posture.
- + Very high-quality textures on the man's skin and the wet asphalt.
- + Effective lighting with realistic bokeh and reflections on the pavement.
- − The bicycle's physical geometry is slightly nonsensical, particularly where the frame connects to the pedals.
- − The framing, while intentionally 'imperfect', feels a bit cropped on the right side.
HiDream I1 Fast
- + Captures the rainy atmosphere and reflections well.
- + Good character design for an elderly Japanese man.
- − Fails the primary action of the prompt; the man is sitting on the bike rather than repairing it.
- − The scale of the man relative to the bicycle is awkward, making the bike look like a toy.
- − The white car on the right lacks the requested motion blur, appearing static.
Verdict: FLUX.2 [flex] is the clear winner as it accurately depicts the specific action of repairing the bicycle, whereas HiDream I1 Fast shows the man simply sitting on it. FLUX.2 also provides much more realistic skin textures and a more authentic cinematic feel, while HiDream suffers from strange scaling issues between the subject and the vehicle.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent detail on the engraved plate armor and leather textures.
- + Very realistic, lifelike skin texture with appropriate grime and faint scars.
- + Accurate braided hair with small beads as requested.
- − The torch in the background has a slightly artificial blue glow at its base.
HiDream I1 Fast
- + Strong cinematic contrast and lighting.
- + Good representation of the braided hair and beads.
- + Effective use of warm torchlight on the character's face.
- − The facial features and skin texture look overly smooth and 'AI-generated' compared to Model A.
- − The scar on the forehead looks like a red paint stroke rather than a realistic healed or fresh wound.
- − The armor engraving is less precise and busy.
Verdict: FLUX.2 [flex] is the clear winner due to its superior realism and adherence to detail, particularly in the skin textures and the intricate engravings on the armor. HiDream I1 Fast delivers a more stylized, almost video-game-like aesthetic that lacks the lifelike quality and fine material detail seen in the first 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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography and layout that resembles a real menu.
- + Clean grid alignment with professional food photography.
- + Accurate adherence to the section requirements (Appetizers, Pizza, Mains).
- − Nonsense filler text in the descriptions.
- − Misalignment between the header 'Pizza' and the items listed under it (which include a chicken bowl and appetizer).
HiDream I1 Fast
- + High contrast header that stands out.
- + Follows the request for a grid of food photos.
- − Poor typography with significant artifacts and illegible characters.
- − Does not separate sections properly, grouping 'Appetizers' and 'Pizza' into one messy line.
- − Low quality visual coherence in the food images compared to the competitor.
Verdict: FLUX.2 [flex] produced a professional, believable menu design with a clean layout and high-quality imagery that perfectly fits the 'modern minimalist' prompt. In contrast, HiDream I1 Fast struggled with text rendering, font clarity, and overall composition, resulting in a cluttered and unusable graphic. FLUX.2 [flex] is the clear winner for its realistic structure and aesthetic appeal.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography with a realistic fiery texture.
- + Photorealistic texture on the bun and patty.
- + Perfect adherence to all prompt elements including price alignment.
- − The 'exploded' effect is slightly more controlled than dynamic.
HiDream I1 Fast
- + Creative use of glowing embers and fire at the base of the image.
- + Satisfactory rendering of the price in a starburst.
- − Text rendering for 'LIMITED TIME ONLY' is garbled and redundant.
- − The burger is largely stacked rather than 'exploded' or suspended in components.
- − Inconsistent lighting on floating elements like the onion rings.
Verdict: FLUX.2 [flex] significantly outperforms HiDream I1 Fast in terms of textual accuracy and visual fidelity. While FLUX.2 followed every instruction for the advertisement layout and text, HiDream I1 Fast struggled with the smaller text and failed to create the requested 'exploded' burger effect, presenting a mostly intact sandwich instead.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent text rendering with perfect spelling and grammar.
- + Highly realistic chalk texture, including smudges and varying stroke opacity.
- + Consistent handwriting style across all menu items.
- − The font, while handwritten-style, appears slightly too uniform to be fully organic.
HiDream I1 Fast
- + Natural composition with café elements like a coffee cup and window light.
- + Reasonable rendering of the main header text.
- − Significant text artifacts and overlapping characters in the menu body.
- − Spelling errors such as 'Buter' and garbled pricing symbols.
- − Poor text alignment and messy chalk strokes that look like digital glitches.
Verdict: FLUX.2 [flex] successfully rendered all the requested text with perfect accuracy and a very convincing chalk texture. HiDream I1 Fast struggled significantly with the complex text, resulting in numerous spelling errors, overlapping characters, and nonsensical layout choices. FLUX.2 [flex] is the clear winner for its superior prompt adherence and legibility.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [flex]
- + Successfully followed the difficult spatial reasoning prompt of a horse riding an astronaut.
- + Excellent cinematic lighting and high-detail textures in both the horse's coat and the space suit.
- + Dynamic composition with a sense of surrealism and motion.
- − The anatomy where the horse meets the astronaut's shoulders is slightly merged and physically impossible.
HiDream I1 Fast
- + Natural lighting on the subject.
- + High clarity in the textures of the sand and horse.
- − Failed the primary prompt instruction to put the horse on top of the astronaut.
- − Failed the environmental prompt by setting the scene in a desert instead of space.
- − The horse is missing a leg in the background/foreground intersection.
Verdict: FLUX.2 [flex] successfully interpreted the complex and non-standard request for a 'horse riding an astronaut' while maintaining a beautiful cinematic space theme. HiDream I1 Fast completely ignored the core logic of the prompt, providing a standard astronaut riding a horse in a desert, and also featured significant anatomical errors with 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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to the capybara's physical interaction with the steering wheel
- + Realistic lighting and texture on the capybara's fur and the taxi interior
- + Accurately places the passenger in the back seat as requested
- − The hands on the steering wheel look more like human hands than capybara paws
- − Slightly crowded composition with the car door frame cutting through the view
HiDream I1 Fast
- + High contrast lighting creates a punchy, cinematic night atmosphere
- + The capybara's face is very clear and well-rendered
- − The passenger is incorrectly placed in the front passenger seat instead of the back seat
- − The driver's arms and hands are clearly human, failing the requested anatomy for the capybara
- − The taxi cap is a simple baseball cap rather than a professional driver's cap
Verdict: FLUX.2 [flex] is the superior model because it correctly followed the spatial instructions, placing the passenger in the back seat and showing the capybara actually driving. HiDream I1 Fast failed on multiple prompt details, specifically the passenger's location and the requirement for capybara paws on the wheel, instead generating human arms and hands.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Perfect text rendering for all requested details and slogans.
- + High-quality cinematic lighting with a moody, professional atmosphere.
- + Excellent composition using the parchment aesthetic with a detailed thorny border.
- − The parchment background is slightly less 'dark' than might be expected, appearing more tan/sepia.
HiDream I1 Fast
- + Stronger color contrast with the blue night sky and orange pumpkin.
- + Captures the 'twisted trees' prompt element with high stylization.
- − Text is poorly rendered with multiple typos and overlapping characters.
- − Lacks the specific 'gothic' typeface requested for the title.
- − The 'small scroll banner' is poorly integrated with cut-off text.
Verdict: FLUX.2 [flex] is the clear winner as it followed every instruction, including specific text strings, which were rendered with perfect accuracy and elegant typography. HiDream I1 Fast failed significantly on the text rendering and logical layout, resulting in a cluttered design with illegible details.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent text rendering and placement of the Japan flag icon.
- + Strong adherence to the 'diorama base' prompt with a clean isometric platform.
- + Very high clarity and consistent PBR material textures for the sushi.
- − The sushi toppings appear slightly more like plastic than realistic food models.
HiDream I1 Fast
- + Good interpretation of the miniature cartoon aesthetic.
- + Includes extra elements like chopsticks that fit the theme.
- + Soft, pleasing lighting and shadow work.
- − Text layout is cluttered and contains a nonsensical artifact next to the word 'SUSHI'.
- − The nigiri sushi has an illogical cross-section of fish/vegetable inside the rice base.
- − The flag icon is stylized in a way that makes it look slightly off-center.
Verdict: FLUX.2 [flex] followed the prompt instructions near perfectly, delivering ultra-clean typography and a professional diorama composition. While HiDream I1 Fast captured a nice miniature feel, it failed on the logical consistency of the sushi anatomy and the cleanliness of the text arrangement.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Successfully includes all four requested animals: puppy, kitten, bunny, and fox kit.
- + Captures the 'playfully chasing' and 'tumbling' motion described in the prompt.
- + Excellent execution of god rays and morning dew details.
- − The fox kit has a slightly awkward extra-long tail.
- − The puppy's front paw looks slightly distorted due to the motion blur.
HiDream I1 Fast
- + Soft, appealing lighting and cute facial expressions.
- + Clean fur textures and vibrant butterfly colors.
- − Failed to include the baby bunny, a core requirement of the prompt.
- − Included two kittens instead of one, deviating from the specified list.
- − The scene is static rather than showing the animals 'chasing and tumbling'.
Verdict: FLUX.2 [flex] is the clear winner as it followed every part of the prompt, including all four specific animals and captured the energetic action of chasing. HiDream I1 Fast failed to include the bunny, doubled the kitten count, and produced a static portrait rather than the dynamic scene 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.”
AI Judge Analysis
FLUX.2 [flex]
- + Perfect text rendering for all elements including the Italian accent.
- + Clean vector emblem style with excellent visual balance.
- + Accurate prompt adherence to all components including the banner and steam.
- − The steam is very subtle, almost blending into the background.
HiDream I1 Fast
- + Nice use of gold-toned highlights to create dimension on the cloche.
- + Strong vintage aesthetic with the circular frame.
- − Significant typo in the year, rendering as 'EST. 17210'.
- − The text placement inside the cloche feels cramped and poorly integrated.
- − Visible artifacts and messy line work on the right side of the dome.
Verdict: FLUX.2 [flex] produced a professional, production-ready logo with perfect typography and a clean minimalist aesthetic. In contrast, HiDream I1 Fast failed the primary requirement of numerical accuracy by adding an extra digit to the year and struggled with clean vector lines.
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.”
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography with perfect spelling and professional layout.
- + Highly accurate flat-vector style that perfectly matches the 'modern infographic' request.
- + Logical progression of phases with clean, crisp iconography.
- − Missed the final 'Landing' step, stopping after 'Lunar Orbit' and 'Descent'.
- − The 'Translunar' icon is slightly abstract compared to the others.
HiDream I1 Fast
- + Successfully included a landing/flag element at the end of the sequence.
- + Followed the color palette requirements reasonably well.
- − Severe spelling errors in almost every label (e.g., 'EAKH OPBIT', 'DESCENG').
- − Cluttered and confusing layout with random lines connecting icons to nothing.
- − Poor icon quality with blurry edges and nonsensical shapes for the lunar module.
Verdict: FLUX.2 [flex] produced a professional, high-quality infographic with perfect text rendering and a sophisticated minimalist aesthetic. While it missed the very last step of the sequence, HiDream I1 Fast failed significantly on basic execution, producing garbled text and a messy composition that does not meet the 'clean, crisp' requirements of the prompt.
Explore each model
Distilled version of HiDream AI's 17B parameter text-to-image model