Black Forest Labs' aesthetically-tuned 12-billion parameter flow transformer optimized for high-quality images with incredible aesthetics, suitable for personal and commercial use
Settled by community votes across 12 shared challenges, with an AI judge weighing in on each.
FLUX.1 Krea [dev]
#48 of 62 in Text-to-Image
HiDream I1 Full
#60 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Krea [dev]
0%
win rate
Ties
0%
HiDream I1 Full
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.1 Krea [dev]
- + Excellent photorealistic rendering of glass and reflections
- + Highly faithful to the lighting request with soft directional light
- + Realistic textures on the book and wooden table
- − The sphere inside appears to be resting on an internal base rather than the cube floor
- − The glass cube has very thick edges that slightly distort the interior view
HiDream I1 Full
- + Successfully shows the plant partially visible through the glass
- + Includes the window in the frame to justify the lighting source
- + Clean and simple composition
- − The blue sphere is floating inexplicably in the center of the cube
- − Ghosting artifacts/reflections of the sphere are logically inconsistent with the lighting
- − The book appears slightly flat and lacks texture detail
Verdict: FLUX.1 Krea [dev] produces a significantly more realistic and high-quality image with sophisticated light handling and material textures. While HiDream I1 Full attempts to include more background context like the window, it fails on basic physics by making the sphere float and exhibits odd visual artifacts in the 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.”
AI Judge Analysis
FLUX.1 Krea [dev]
- + Captures the motion blur from passing cars very effectively.
- + Excellent rendering of falling rain against the dark background.
- + Realistic skin texture and natural facial features.
- − The man appears to be standing with the bike rather than actively repairing it.
- − The proportions of the bicycle frame are slightly off near the handlebars.
HiDream I1 Full
- + The subject is actively engaged in 'repairing' the seat, better matching the prompt's action.
- + Beautiful reflections on the wet pavement.
- + Good shallow depth of field with a cinematic feel.
- − The cars in the background lack the specific motion blur requested.
- − The man is sitting on the bike while repairing it, which looks slightly unnatural.
- − The lighting on the man's head feels a bit too clean and studio-lit for a candid street shot.
Verdict: FLUX.1 Krea [dev] followed the technical instructions for motion blur and rain effects much better, resulting in a more authentic 'candid' feel. While HiDream I1 Full captured the action of repairing better, it missed the motion blur requirement and looks slightly more staged.
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.1 Krea [dev]
- + Excellent adherence to the 'faint scars' prompt with realistic skin texture
- + High-quality, coherent metal engravings that look believable
- + Strong cinematic lighting with subtle torchlight reflections
- − The 'braids with small beads' are very thin and less prominent than requested
HiDream I1 Full
- + Successfully captures the braided hair with beads more distinctly
- + High detail on the leather strap and metal studs
- + Vibrant colors and clear torch in the background
- − Scars look like digital paint strokes rather than realistic skin damage
- − Overall image has an over-sharpened, artificial look
- − Armor engravings are somewhat messy and lack the refinement of the competitor
Verdict: FLUX.1 Krea [dev] produces a significantly more realistic and cinematic portrait with believable textures and lighting, whereas HiDream I1 Full has an over-processed, 'CG' look with less realistic facial details. FLUX.1 Krea [dev] follows the 'faint' aspect of the scars better, while HiDream I1 over-exaggerates them.
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.1 Krea [dev]
- + Excellent professional alignment and grid structure.
- + Bold, vibrant typography that uses hierarchy effectively.
- + Comprehensive sectioning for appetizers and mains as requested.
- − Text consists of gibberish characters.
- − Repeats the 'Appetizers' heading twice.
HiDream I1 Full
- + Text is closer to readable English characters than the other model.
- + Good use of high-quality food photography.
- + Follows the minimalist aesthetic well.
- − Layout is somewhat sparse and poorly balanced.
- − Only features pizza photos despite having different sections.
- − Awkward cropping on the bottom left image.
Verdict: FLUX.1 Krea (Image A) produces a much more realistic and professional layout that looks like a finished graphic design piece, despite the illegible text. HiDream I1 Full (Image B) is a simpler design but fails to provide variety in the food photos (all pizzas) and has less sophisticated typography.
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.1 Krea [dev]
- + Excellent adherence to the specific menu text requested in the prompt.
- + Natural chalk textures and realistic smudge effects on the blackboard.
- + Clean and legible handwriting that maintains a cursive, consistent style.
- − Includes some hallucinations like 'Gruffle Mushroom' and 'Grilled Butter & Elvrcuations'.
- − The prices don't match the specific dollar amounts in the prompt for every item.
HiDream I1 Full
- + Captures a beautiful, elegant cursive style for the title text.
- + Includes a nice chalk illustration of a coffee cup.
- − Completely ignored the requested menu items (Truffle Mushroom Risotto, etc.).
- − Most text consists of gibberish words and nonsensical phrases.
- − The text style looks like a digital font overlay rather than organic chalk handwriting.
Verdict: FLUX.1 Krea [dev] is the clear winner as it attempted and largely succeeded in rendering the specific menu items requested, whereas HiDream I1 Full populated the board with illegible gibberish. FLUX.1 Krea [dev] also achieved a much more realistic chalk texture, while HiDream I1 Full's text appeared too clean and digital.
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.1 Krea [dev]
- + Excellent photorealistic texture and cinematic lighting.
- + Greater anatomical clarity in the astronaut's gear.
- + Higher resolution with less digital noise.
- − Fails the spatial reasoning requirement; the astronaut is riding the horse.
- − Confusing merging of mechanical parts with the horse's anatomy.
HiDream I1 Full
- + Dynamic composition and sense of movement.
- + Includes multiple planetary bodies for a more cosmic feel.
- − Fails the spatial reasoning requirement; the astronaut is riding the horse.
- − Significant anatomical issues with the horse's legs and the astronaut's right arm.
- − Noticeable digital artifacts and over-sharpening.
Verdict: Both models failed the complex spatial instruction to place the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX.1 Krea [dev] is the superior image due to much higher visual fidelity, realistic lighting, and cleaner textures compared to the distorted anatomy and artifacts found in the HiDream I1 Full output.
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.1 Krea [dev]
- + Excellent atmospheric lighting and realistic cinematic texture
- + Good interpretation of the taxi driver cap
- + High detail in the capybara's fur and expression
- − Includes an extra person in the front passenger seat which was not requested
- − The woman with the phone has a glowing artifact over her eye
HiDream I1 Full
- + Perfect adherence to the prompt characters and positions
- + Convincing 'bored' expression on the businesswoman
- + Accurate depiction of the capybara's paws on the steering wheel
- − Texture looks slightly more like a digital render than a photograph
- − The taxi cap text 'TAXI' is slightly distorted
Verdict: While FLUX.1 Krea [dev] has superior lighting and photographic realism, it failed the composition prompt by adding an unnecessary passenger in the front seat. HiDream I1 Full followed all instructions perfectly, including the specific character positions and the bored expression of the businesswoman, making it the more functional result.
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.1 Krea [dev]
- + Excellent atmospheric lighting and moody color palette
- + High-quality, intricate border design with webs and thorns
- + Accurately rendered central jack-o-lantern and silhouettes
- − Significant spelling errors including 'Pasty Halloween' as the title
- − Repetitive and garbled text in the invitation scroll at the bottom
HiDream I1 Full
- + Successfully captured the requested text 'You are invited to a night of frights' on the scroll banner
- + Clearer, more legible gothic font for the main title
- + Good layout with a distinct parchment layer
- − Illogical date and time information ('Yootmber' and '30 cm')
- − Visual style is slightly more cartoonish and less cinematic than requested
Verdict: FLUX.1 Krea [dev] produces a much more atmospheric and professional-looking graphic with superior lighting and borders, though it fails significantly on text legibility. HiDream I1 Full follows the text instructions more closely for the secondary banner, but the final result suffers from nonsensical event details and a flatter visual style. FLUX.1 Krea [dev] is the likely winner for its artistic quality despite the 'Pasty' typo.
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.1 Krea [dev]
- + Perfectly matches the 45-degree isometric projection requested.
- + Excellent text rendering and placement following the layout instructions.
- + Includes the requested flag icon and minimalist diorama base.
- − The fish texture appears a bit plastic-like rather than soft refined PBR.
- − Only features a single piece of sushi which feels very sparse.
HiDream I1 Full
- + Follows the diorama base instruction with a more traditional wooden platter feel.
- + Strong soft, cartoonish 3D texture style that fits the 'miniature' aesthetic.
- + Includes a variety of sushi types which fills the scene better.
- − Missed the flag icon requested in the prompt.
- − Perspective is slightly lower than the requested 45-degree isometric top-down view.
- − Text rendering is slightly thinner and less impactful than requested.
Verdict: FLUX.1 Krea (dev) adhered more closely to the technical layout requirements, specifically the 45-degree isometric angle and the inclusion of the flag icon. However, HiDream I1 Full captured the 'miniature cartoon' aesthetic much better with its soft textures and more visually interesting selection of sushi. FLUX.1 Krea (dev) is the likely winner for its precise adherence to every text and element instruction.
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.1 Krea [dev]
- + Excellent dynamic composition showing movement and playfulness
- + Superior realism in fur texture and lighting
- + Matches butterflies and sunrise lighting perfectly
- − Missed the baby bunny requirement, substituting it with a second kitten
HiDream I1 Full
- + Features a very vibrant and 'wholesome' color palette
- + Good rendering of 'big expressive eyes' on the animals
- − Missed the baby bunny requirement, substituting it with a second kitten
- − Anatomically awkward back leg on the fox kit
- − Less realistic, looking more like a digital illustration than a photograph
Verdict: Both models failed to include all four requested animals (both substituted the bunny for a second kitten). However, FLUX.1 Krea [dev] is the clear winner due to its much higher level of photorealism, superior fur textures, and a more dynamic composition that captures the requested 'tumbling' and 'chasing' action better than the static pose of HiDream I1 Full.
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.1 Krea [dev]
- + Excellent vintage engraving style with high artistic detail.
- + Includes both the request for 'Est. 1720' and a complex ribbon banner.
- + Superior texture application that matches the 'vintage parchment' look.
- − Failed to spell out 'Caffè Florian' correctly, resulting in 'Caffè FLANOR'IN'.
- − The cloche dome looks more like a jar or bottle due to the steam coming out of the top.
HiDream I1 Full
- + Perfectly captures the 'minimalist' and 'vector emblem' style requested.
- + Clearer representation of a cloche dome.
- + Very clean typography for the 'EST. 1720' text.
- − Completely missed the main brand name 'Caffè Florian' in the logo.
- − The design feels a bit generic compared to the intricate vintage request.
- − Texture is negligible, appearing as a flat color background.
Verdict: FLUX.1 Krea (dev) captures the 'vintage' and 'cloche dome with steam' brief much more effectively with beautiful detail, although it suffers from significant spelling errors in the brand name. HiDream I1 Full provides a cleaner minimalist vector, but it completely omitted the primary brand name text and lacks the requested texture. FLUX.1 Krea (dev) is the winner for better atmospheric adherence and a more sophisticated design language.
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.1 Krea [dev]
- + Successfully included all 6 numbered steps requested in the prompt.
- + Followed the dark navy and white color palette well.
- + Clean, minimalist vector aesthetic for the moon surface and main title.
- − Icons do not match the specific descriptions (e.g., includes a Saturn-like planet and astronauts instead of mission phases).
- − Text rendering for labels is garbled and incoherent.
- − The logical flow and numbering are visually confusing and scattered.
HiDream I1 Full
- + Closer iconography to the actual mission (Saturn V rocket, Earth, and capsule icons).
- + Text labels are legible and follow the requested step descriptions more accurately.
- + Better visual composition that feels like a cohesive poster.
- − Failed to include steps 4, 5, and 6 as requested in the prompt.
- − Included 'meta' text from the prompt (e.g., '+ ICON', 'UNLY') directly into the image labels.
- − The central rocket graphic overlaps other elements awkwardly.
Verdict: FLUX.1 Krea (dev) followed the instruction to provide six steps, but the content of those steps was largely irrelevant to the specific icons requested (showing astronauts and Saturn instead of trajectory arcs). HiDream I1 Full captured the infographic style and specific NASA mission iconography much better, though it failed to complete the full sequence of steps and hallucinated parts of the prompt text into the labels.
Explore each model
HiDream AI's 17B parameter text-to-image model using sparse diffusion transformer with mixture of experts, achieving state-of-the-art image generation quality with strong prompt following