Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 12 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
HiDream I1 Full
#60 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro]
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
FLUX1.1 [pro]
- + Exceptional photorealism with sharp textures on the book and glass edges.
- + Sophisticated light refraction that interacts convincingly with the sphere and background.
- + High-quality rendering of the green plant with a shallow depth of field.
- − The glass object is more of a rectangular prism than a cube.
- − The sphere appears to be levitating without a clear physical relationship to the bottom of the container.
HiDream I1 Full
- + Successfully captures a more accurate 'cube' shape for the glass container.
- + Warm, natural lighting that correctly follows the requested window light direction.
- + Good adherence to all spatial elements in the prompt.
- − The glass has a noticeable greenish tint that makes it look slightly less clear than requested.
- − The sphere has a somewhat flat, painted texture compared to the environment.
- − Reflections on the inner glass surfaces are slightly muddy.
Verdict: FLUX1.1 [pro] produces a more visually stunning, high-definition image with incredible material textures and realistic lighting, though it opted for a tall prism instead of a cube. HiDream I1 Full followed the geometric instruction of a 'cube' more accurately and captured the soft window light beautifully, but it lacks the crystalline clarity and sharpness found in FLUX1.1 [pro]. FLUX1.1 [pro] is the preferred choice for its superior artistic execution and realism.
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
FLUX1.1 [pro]
- + Excellent depiction of a wet pavement with realistic light reflections.
- + Strong photographic quality that matches the cinematic request.
- + Good implementation of the specified 50mm shallow depth of field.
- − The red bicycle is anatomically broken, missing a frame and rear half.
- − The man is holding the handlebars in a way that doesn't clearly suggest 'repairing'.
- − The cars in the background lack the requested motion blur.
HiDream I1 Full
- + Natural skin textures and realistic elderly features.
- + Better overall composition of a street scene that feels Japanese.
- + The bicycle is mostly complete and more recognizable as a vehicle.
- − Significant anatomical error where the man's leg appears to grow out of the bicycle seat.
- − Lack of visible rain or motion blur on passing cars.
- − Objects on the ground appear as illegible artifacts.
Verdict: FLUX1.1 [pro] produces a more atmospheric and cinematic lighting setup with superior reflections, but the bicycle is severely malformed. HiDream I1 Full captures the 'elderly Japanese man' subject more authentically and maintains a better street vibe, but suffers from a major anatomical glitch with the man's leg merging through the seat. FLUX1.1 [pro] is slightly preferred for adhering closer to the 'cinematic' and 'lighting' aspects of the prompt despite the broken bike.
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
FLUX1.1 [pro]
- + Exceptional photographic realism in skin texture and eyes
- + Natural-looking dirt and grime integration
- + Strong implementation of horizontal shallow depth of field
- − Missed the hair beads element of the prompt
- − Engraved armor is less prominent due to the framing
HiDream I1 Full
- + Excellent adherence to the 'braided hair with small beads' prompt
- + Very detailed ornate engraving on the plate armor
- + Clear depiction of multiple leather straps and layers
- − Scars look like drawn-on lines rather than healed skin
- − Face has a slightly 'plastic' or CGI aesthetic compared to Image A
- − The torch in the background is a bit distracting in the composition
Verdict: FLUX1.1 [pro] excels in photographic realism, capturing lifelike eyes and organic textures that make the character feel real, though it missed the hair beads. HiDream I1 Full followed the technical details of the prompt much more closely, including the beads and ornate engravings, but resulted in a more artificial, game-like render. FLUX1.1 [pro] is the winner for visual quality, while HiDream I1 Full is superior for prompt adherence.
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
FLUX1.1 [pro]
- + Excellent professional composition with a realistic mock-up presentation.
- + Strong adherence to the 'grid' request for food photos.
- + Includes the requested vibrant accents and complex sectioning.
- − Small body text is mostly illegible gibberish.
- − The food photos in the grid are quite small and lose some detail.
HiDream I1 Full
- + Features large, high-quality images of food with realistic textures.
- + Uses a clean sans-serif font that is very easy to read.
- + Accurately represents the requested sections like 'MAINS' and 'PIZZA'.
- − The layout is very basic and lacks the 'professional design' polish seen in mock-ups.
- − The price values are unrealistically high (e.g., 200, 500) and repetitive.
Verdict: FLUX1.1 [pro] provides a much more convincing professional design including a full brand presentation with cutlery and multiple menu cards, capturing the 'modern minimalist' aesthetic perfectly. While HiDream I1 Full has clearer food photography and readable headers, its layout is overly simplistic and less aligned with the professional 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
FLUX1.1 [pro]
- + Excellent text legibility and high adherence to the specific requested menu items.
- + Natural chalk texture and realistic handwriting variations.
- + Authentic cafe background with depth of field.
- − Split the Grilled Octopus into two lines with hallucinated prices ($228 and $98).
- − Minor spelling errors in the footer text like 'giluten' and 'iro'.
HiDream I1 Full
- + Strong composition with a nicely rendered coffee illustration.
- + Good date formatting and title layout.
- − Failed almost entirely on prompt adherence for specific menu items.
- − Text is largely gibberish/nonsensical.
- − Handwriting style looks more like a digital font than natural chalk.
Verdict: FLUX1.1 [pro] significantly outperforms HiDream I1 Full by correctly rendering the requested menu items with a realistic chalk texture. While HiDream I1 Full includes a nice illustration, the text is almost entirely gibberish, whereas FLUX1.1 [pro] captures the specific culinary details and handwriting style requested.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent texture on the horse's coat and mane
- + Cinematic lighting with a dramatic sky and planet textures
- + High level of detail in the astronaut suit and gear
- − Completely failed the negative constraint: the astronaut is riding the horse, not the other way around
- − The composition feels slightly cramped at the bottom edge
HiDream I1 Full
- + Strong cinematic composition with the planet's curve in the background
- + Clean, sharp image quality with good contrast
- + Accurate depiction of a white horse in a galloping space-pose
- − Completely failed the negative constraint: the astronaut is riding the horse
- − The anatomy of the horse's back legs is slightly warped
Verdict: Both models failed the complex spatial instruction to place the horse on top of the astronaut, instead providing the standard interpretation of an astronaut riding a horse. FLUX1.1 [pro] produced a more texturally rich and artistically detailed image, while HiDream I1 Full offered a cleaner, more traditional sci-fi composition with better use of negative space.
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
FLUX1.1 [pro]
- + Excellent atmospheric lighting and bokeh effect for a night scene
- + Very detailed fur texture on the capybara
- + High photographic realism in the woman's face and phone interaction
- − The capybara is not driving; it is positioned in the middle/passenger side looking toward the woman
- − The composition places the two characters side-by-side rather than front/back seat layout
HiDream I1 Full
- + Correctly follows the spatial composition with the capybara driving and woman in the back seat
- + Captures the requested 'bored' expression of the businesswoman very well
- + Clearly shows both paws on the steering wheel as requested
- − The woman's left hand has anatomical errors/strange finger merging
- − The text on the cap's logo is slightly distorted compared to Model A
- − The capybara's hands look more like primate hands than capybara paws
Verdict: Model B (HiDream I1 Full) is the winner because it successfully followed the complex spatial instructions of the prompt, placing the capybara in the driver's seat and the woman in the back. While FLUX1.1 [pro] produced a more aesthetically pleasing and high-fidelity image, it failed the core instruction of having the capybara driving the vehicle.
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
FLUX1.1 [pro]
- + Features a very atmospheric, cinematic background with high-quality lighting
- + Correctly captures the specific location and date requested
- + Beautifully intricate thorns and web border
- − Text layout is redundant, repeating the location and time multiple times
- − Contains a minor spelling error: 'You inivted to a n night'
HiDream I1 Full
- + Excellent typography for the 'Halloween Party' title
- + Perfectly renders the small scroll banner text exactly as requested
- + Clear layout that fits the square format well
- − Fails significantly on the specific event details, outputting 'Yootmber' and incorrect times
- − The background is less atmospheric compared to the competitor
Verdict: FLUX1.1 [pro] creates a much more cinematic and moody atmosphere with better adherence to the specific event details, though it struggles with text repetition. HiDream I1 Full has superior font choices and scroll banner rendering but fails to include the requested date and location. FLUX1.1 [pro] is the stronger choice for its visual quality and factual accuracy.
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
FLUX1.1 [pro]
- + Excellent soft-rendered 3D cartoon aesthetic with subtle subsurface scattering.
- + Precise text layout with high legibility.
- + Clean, minimalist composition that feels professional and balanced.
- − Missing the small flag icon requested in the prompt.
- − The 'sushi' subtext is slightly small and lacks the same weight as the main text.
HiDream I1 Full
- + Strong isometric adherence and high-clarity 3D modeling.
- + Follows the text layout instructions accurately with 'JAPAN' and 'SUSHI'.
- + Nice textural representation of the rice grains.
- − Missing the small flag icon requested in the prompt.
- − There is a slight blue chromatic aberration/artifacting on the left edge of the image.
- − The background has a subtle texture instead of being a perfectly solid light blue.
Verdict: FLUX1.1 [pro] produced a more aesthetically pleasing image with a soft, toy-like finish that perfectly matches the 'miniature 3D cartoon' request, although it failed to include the flag icon. HiDream I1 Full followed the text hierarchy well and had great detail on the rice, but it suffered from minor edge artifacts and a less refined background. FLUX1.1 [pro] is preferred for its superior lighting and cleaner overall presentation.
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
FLUX1.1 [pro]
- + Exquisite rim lighting that perfectly captures the golden sunrise glow.
- + Extremely realistic fur texture and soft focus depth-of-field.
- + Charming and expressive eye details with realistic reflections.
- − Failed to include the red fox kit from the prompt.
- − Missing the sense of 'tumbling' or active movement described.
HiDream I1 Full
- + Includes more of the requested animals, including a red fox kit.
- + Vibrant colors that lean heavily into the 'wholesome' vibe.
- + Features recognizable butterflies with distinct patterns.
- − Anatomy is slightly distorted, particularly on the kittens.
- − The 'god rays' are represented as harsh white streaks rather than atmospheric light.
- − The puppy has white 'teardrop' artifacts near the eyes.
Verdict: FLUX1.1 [pro] produced a much higher quality, photorealistic image with superior lighting and texture, but it completely missed the red fox kit. HiDream I1 Full followed the prompt's subject list more closely by including the fox, but suffered from lower technical quality, awkward animal anatomy, and less realistic lighting.
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
FLUX1.1 [pro]
- + Sophisticated vintage engraving style with high aesthetic appeal.
- + Excellent banner execution and border detailing.
- + Effective use of subtle textures that fulfill the vintage prompt perfectly.
- − Major spelling error where 'Florian' becomes 'FRATILIAN'.
- − Text rendering is cluttered and includes a stray 'e' with an accent.
HiDream I1 Full
- + Perfectly minimalist vector style that adheres to modern logo standards.
- + Accurate date text rendering in the banner.
- + Creative integration of the steaming coffee cup inside the cloche dome.
- − Completely failed to include the primary brand name 'Caffè Florian'.
- − Interpretation is perhaps too flat for the 'vintage' specific request compared to model A.
Verdict: FLUX1.1 [pro] produced a beautiful, high-quality engraving that captures the 'vintage' atmosphere, but it suffered from significant spelling errors and hallucinatory characters. HiDream I1 Full followed the 'minimalist' and 'vector' prompts much better with a clean execution, yet it entirely omitted the brand name required by the prompt. HiDream I1 Full is the winner for delivering a functional, professional logo design that is easier to fix, whereas the text errors in FLUX1.1 [pro] are quite messy.
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
FLUX1.1 [pro]
- + Excellent adherence to the NASA navy, white, and muted red color palette.
- + Includes a logical flow of steps with icons arranged in a sequence.
- + True flat-vector graphic design style that looks like a professional poster.
- − Text rendering is mostly gibberish despite the clear typography.
- − Numbering sequence is repetitive and confusing (1, 1, 2, 3, 5, 4).
HiDream I1 Full
- + Features a bold, impactful central Saturn V illustration.
- + Legible main headings for the specific steps requested.
- + Crisp vector aesthetic with clean geometric shapes.
- − Failed to include all six requested steps, stopping after step 3.
- − Included random prompt text like '+ ICON' and '+ UNG' inside the graphic.
- − Iconography is inconsistent, featuring a Saturn-like planet for Earth Orbit.
Verdict: FLUX1.1 [pro] followed the structural requirements of the infographic much better, providing a full sequence of steps and a cohesive visual layout that matches the NASA theme. While HiDream I1 Full had clearer text for a few labels, it failed to include half of the requested content and included literal prompt instructions as text within the image.
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