Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps
Settled by community votes across 12 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell]
#48 of 62 in Text-to-Image
HiDream I1 Full
#60 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [schnell]
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 [schnell]
- + Excellent clarity and sharpness of the green foliage
- + Vibrant colors and high-quality rendering of the glass cube
- + Follows most spatial requirements including directional lighting
- − Included a redundant second blue sphere on top of the book
- − The sphere inside is floating without clear physics
- − The book scale is quite small relative to the cube
HiDream I1 Full
- + Perfect adherence to all prompt elements with no extra objects
- + The blue sphere is properly scaled to appear 'small' as requested
- + Realistic lighting and shadow integration on the wooden table
- − Focus is slightly softer than the competitor
- − The back edge of the table feels a bit distorted against the background
Verdict: Both models handled the complex spatial reasoning well, but HiDream I1 Full followed the prompt more accurately by including only one blue sphere. FLUX.1 [schnell] produced a higher-fidelity image with better texture and sharpness, but failed on logic by adding a second sphere on top of the book.
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 [schnell]
- + Excellent handling of wet pavement reflections and light rain atmosphere.
- + Mechanical details of the bicycle like the chain and brake cables are relatively coherent.
- + Skin texture and facial features look very natural and age-appropriate.
- − The cars in the background are sharp rather than having the requested motion blur.
- − One of the man's hands is mangled/fused with the bicycle handlebars.
HiDream I1 Full
- + Successfully captured the 'imperfect framing' and 'shallow depth of field' requested.
- + Effective use of atmospheric perspective and rain effects in the background.
- + Face and hair texture are highly detailed and realistic.
- − Major anatomical and physics failure as the man appears to be sitting on or through the bicycle frame.
- − The bicycle is tiny and anatomically incorrect, looking more like a toy than a real bike.
- − The reflection on the ground does not match the positioning of the bicycle and man.
Verdict: FLUX.1 [schnell] creates a much more grounded and believable scene, despite failing the specific 'motion blur' request for the cars. While HiDream I1 Full captures the bokeh and framing style well, it suffers from severe spatial and anatomical errors, specifically the man appearing to phase through a miniature bicycle. FLUX is the preferred choice for its structural coherence and superior rendering of the requested red bicycle.
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 [schnell]
- + Extremely realistic skin texture and lifelike eye detail
- + Excellent subtle lighting that feels more natural to a torchlit scene
- + Highly detailed engraving on the dark plate armor
- − Misses the 'small beads' in the hair braids requested in the prompt
- − The composition is a bit too tightly cropped to see the full ornate nature of the armor
HiDream I1 Full
- + Perfect adherence to specific details like braided hair with beads and bokeh sparks
- + Excellent portrayal of the 'battle-worn' aspect with more prominent scars and dirt
- + Stronger sense of 'ornate' plate armor shown in the composition
- − The facial features have a slightly 'painterly' or artificial sharpness compared to Model A
- − The torch in the background is a bit distracting and less blurred than it should be for a shallow depth of field
Verdict: While FLUX.1 [schnell] offers a significantly more realistic and high-fidelity skin texture, HiDream I1 Full is the overall winner for its superior prompt adherence. HiDream I1 Full successfully included the beads in the hair, the prominent bokeh sparks, and better showcased the 'ornate' and 'battle-worn' elements of the paladin.
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 [schnell]
- + Strong minimalist aesthetic with a clean white border and modern layout.
- + Successfully included distinct sections for Appetizers, Pizza, and Mains (though one header is misspelled).
- + Includes a grid of food photography that feels professional and varied.
- − The placeholder text for menu items is garbled and illegible.
- − One section header is misspelled as 'ORFEFUS' instead of Mains.
HiDream I1 Full
- + High-quality food photography with realistic textures and lighting.
- + Better text rendering for prices and dish names, despite some minor character errors.
- + Clean, bold sans-serif typography that matches the prompt well.
- − The 'Appetizers / Pizza' section lacks visual separation, and only pizza photos are shown.
- − The layout is slightly cluttered compared to the minimalist request.
Verdict: FLUX.1 [schnell] captures the 'minimalist' and 'grid' aspects of the prompt more effectively with a professional graphic design layout, though it struggles with legible body text. HiDream I1 Full produces much better food photography and more readable text, but the design feels less like a multi-section menu and more like a simple flyer featuring only pizza. FLUX.1 [schnell] is the winner for better adhering to the structural design requirements of the prompt.
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 [schnell]
- + Closer adherence to the specific text provided in the prompt.
- + Superior chalk texture that looks authentically handwritten rather than digital.
- + Includes more accurate attempts at the specific menu items like 'Brown butter' and 'Octtoopus'.
- − Text contains several spelling errors and hallucinated words (e.g., 'Octtoopus', 'Pril').
- − Title is not in the requested 'elegant cursive' style.
HiDream I1 Full
- + Successfully applied an elegant cursive style to the title text.
- + Clean composition with a nice illustration of a coffee cup.
- − Completely ignored the specific menu items and prices requested in the prompt.
- − Text appears more like a digital font than actual chalk-on-board texture.
- − Text is largely nonsensical gibberish (e.g., 'Fart Sanl', 'Gnday sgreler').
Verdict: FLUX.1 [schnell] followed the prompt's content instructions much better, attempting to render the specific menu items and including the correct date, whereas HiDream I1 Full ignored the dinner items entirely. While HiDream I1 Full captured the requested cursive style for the header, FLUX.1 [schnell] produced a much more realistic chalk texture and legible (though misspelled) text.
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 [schnell]
- + Perfectly adheres to the reverse positioning prompt with the horse on top.
- + Creates a unique, surreal, and cinematic atmosphere.
- + High visual quality with realistic lighting and textures on the space suit.
- − The horse has two heads/necks merged into one body, which is a significant anatomical artifact.
HiDream I1 Full
- + Clean, sharp image quality with a classic cinematic sci-fi look.
- + Excellent anatomical accuracy for both the horse and the astronaut.
- − Completely fails the primary trick instruction: 'horse on top, not vice versa'.
- − Standard, literal interpretation lacking the requested 'surreal' quality.
Verdict: FLUX.1 [schnell] is the clear winner because it followed the difficult instruction to place the horse on top of the astronaut, whereas HiDream I1 Full provided a standard 'astronaut riding a horse' image. While FLUX.1 [schnell] suffered from a strange anatomical glitch where the horse has two heads, it captured the surreal intent of the prompt perfectly.
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 [schnell]
- + Excellent texture on the capybara's fur
- + Clean and readable text on the hat
- + Accurate expression on the human passenger
- − One paw is missing from the steering wheel
- − Lighting is a bit dark and muddy in the background
HiDream I1 Full
- + Successfully placed both paws on the steering wheel
- + Brighter and clearer color palette
- + Stronger overall composition with better lighting
- − The passenger's hands and phone are slightly distorted
- − The hat brim looks a bit artificial
Verdict: HiDream I1 Full followed the spatial prompt better by including both paws on the steering wheel and created a more vibrant, well-lit scene. FLUX.1 [schnell] had superior fur texture and more realistic text rendering, but failed the specific instruction regarding the paws and the passenger's seating depth feels less defined.
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 [schnell]
- + Strong composition with a balanced layout
- + Excellent cinematic lighting and atmosphere
- + Followed the date and location details mostly accurately
- − Included several lines of redundant and garbled text at the bottom
- − Title text is split and placed awkwardly over a banner
HiDream I1 Full
- + Perfectly legible scroll banner text
- + Captures the 'vintage parchment' texture better
- + Clearer gothic font for the title
- − Completely failed to include the specific date, time, and location details
- − Overall color palette is slightly washed out compared to the 'glowing' request
Verdict: FLUX.1 [schnell] captures the cinematic and moody atmosphere better, and it successfully included the specific event details like the date and location, even though it added some nonsensical text at the end. HiDream I1 Full has a better parchment texture and cleaner banner text, but it failed to follow the specific instructions for the event details, providing placeholder-style gibberish for the date and time.
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 [schnell]
- + Excellent 3D miniature diorama feel with high-quality soft textures.
- + Clean and professional typography for the word 'JAPAN'.
- + Perfectly includes the requested flag icon and solid light blue background.
- − Failed to include the word 'SUSHI' below 'JAPAN'.
- − The rice texture appears more like a solid piece of bread than distinct grains.
HiDream I1 Full
- + Successfully included all requested text ('JAPAN' and 'SUSHI').
- + Superior miniature 3D cartoon style with clear, distinct rice grains and variety.
- + Great isometric composition on the raised diorama base.
- − Failed to include the flag icon.
- − The top-down 45° angle is slightly less centered vertically compared to the other model.
Verdict: HiDream I1 Full is the winner because it followed more of the text-based instructions, including both 'JAPAN' and 'SUSHI', and offered a more vibrant 3D cartoon interpretation of the prompt. While FLUX.1 [schnell] included the flag icon and had a cleaner aesthetic, it missed a key text element and the sushi itself looked less like the traditional dish.
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 [schnell]
- + Excellent fur texture and lighting integration.
- + Better capture of 'god rays' and morning atmosphere.
- + Higher level of anatomical detail on the golden retriever and fox.
- − Failed to include a distinct baby bunny, instead showing an ambiguous kitten-like animal with larger ears.
- − Composition is a bit crowded at the bottom.
HiDream I1 Full
- + Includes more butterflies and captures the golden sunrise lighting well.
- + Centered, symmetrical composition feels very balanced.
- + Bright and vibrant colors match the joyful vibe.
- − Failed to include a bunny, instead generating two kittens.
- − The fox's eyes and face look slightly less realistic and more like an illustration.
- − Missing the 'dew sparkles' requested in the prompt.
Verdict: Both models failed to correctly include all four distinct animals, as both missed the baby bunny. FLUX.1 [schnell] is the winner because its rendering of fur and lighting is significantly more sophisticated and hyper-photorealistic compared to HiDream I1 Full, which has a slightly more artificial, doll-eyed look.
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 [schnell]
- + Clean vector-style execution
- + Strong composition with elegant framing elements
- + Good use of color and texture
- − Failed to render the correct restaurant name (wrote 'Café Framilan')
- − Incorrect year (wrote '7720' instead of '1720')
- − Missing the steam element requested in the prompt
HiDream I1 Full
- + Accurate rendering of the year '1720'
- + Includes the requested steam element inside the cloche
- + Crisp vector art style
- − Completely failed to include the brand name 'Caffè Florian'
- − The banner design is slightly disconnected from the main emblem
- − Interpretation is a bit literal with the coffee cup inside a cloche
Verdict: Both models struggled with full text adherence, though for different reasons. FLUX.1 [schnell] produced a more cohesive and professional-looking logo layout but suffered from significant spelling and date errors, whereas HiDream I1 Full captured more prompt elements like the steam and the correct date but forgot the primary brand name entirely.
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 [schnell]
- + Successfully follows the requested infographic layout with a sequential flow from Launch to Landing.
- + Captures the NASA-inspired color palette and flat vector style perfectly.
- + Contains all 6 requested steps in a logical, spatial arrangement.
- − The text is largely gibberish or nonsensical placeholder text.
- − The central rocket icon has some minor geometry glitches where the shapes overlap.
HiDream I1 Full
- + High-quality typography for the main title with legible text.
- + Clean, modern vector aesthetic that aligns well with the 'NASA-inspired' request.
- + The Saturn V icon is detailed and recognizable.
- − Fails the negative constraint by missing several requested steps (only shows 3) and includes a planet that looks like Saturn.
- − Misinterprets prompt instructions as literal text labels (e.g., 'EARTH V + ICON').
- − Lacks the sequential infographic structure requested in the prompt.
Verdict: FLUX.1 [schnell] is the winner because it successfully conceptualized the entire infographic journey from Earth to Moon, including all six specific steps requested. While HiDream I1 Full has cleaner text rendering, it failed the core task of creating a 6-step infographic and included irrelevant elements like a ringed planet.
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