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 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell]
#48 of 62 in Text-to-Image
HiDream I1 Fast
#51 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [schnell]
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.1 [schnell]
- + Excellent photographic quality and leaf textures.
- + Accurate lighting direction from the left window.
- + Complex glass reflections and refraction.
- − Included an extra blue sphere on top of the book.
HiDream I1 Fast
- + Perfect adherence to the object count and description.
- + Clean and simple composition.
- + The plant is clearly visible through the glass as requested.
- − Slightly lower resolution and softer textures compared to Model A.
- − Object physics feel a bit detached from the table surface.
Verdict: HiDream I1 Fast followed the prompt's instructions perfectly in terms of spatial arrangement and object counts, whereas FLUX.1 [schnell] hallucinated an additional sphere on top of the book. However, FLUX.1 [schnell] produced a significantly more realistic and aesthetically pleasing image with better lighting and material physics.
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 realism in skin texture and textile details
- + Effective use of wet pavement reflections and rainy atmosphere
- + High physical coherence in the bicycle frame and components
- − The cars in the background are frozen rather than having the requested motion blur
- − The framing feels a bit too balanced for 'imperfect framing'
HiDream I1 Fast
- + Stronger sense of cinematic atmosphere and color grading
- + Good capture of rain droplets on the wet asphalt
- + Better adherence to the 'imperfect framing' request with a wider, busier scene
- − Anatomical issues with the man's hands merging into the bike frame
- − Structural errors in the bicycle, such as the disappearing seat and messy spokes
- − The man appears to be sitting on a non-existent seat rather than repairing the bike
Verdict: FLUX.1 [schnell] is the winner due to its superior anatomical and mechanical coherence, providing realistic skin textures and a believable bicycle structure. HiDream I1 Fast captures a more cinematic mood but fails significantly on the details, with the man's hands mangled into the frame and the bicycle missing key parts like a seat.
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]
- + Extreme facial skin texture detail and realistic iris patterns
- + Intense, cinematic lighting and expression
- + Strong adherence to the 'close portrait' instruction
- − Missed the request for small beads in the hair braids
- − The plate armor is barely visible in the crop
- − Lacks the bokeh sparks requested in the background
HiDream I1 Fast
- + Perfectly executed hair braids with small colorful beads
- + Excellent rendering of ornate engraved plate armor as requested
- + Includes clear bokeh effects and warm torchlight ambiance
- − Skin texture and scars look slightly painted or artificial compared to Model A
- − The sword hilt in the background is slightly incoherent physically
- − Composition is a bit wider than a 'close portrait'
Verdict: Model B (HiDream I1 Fast) followed the specific prompt details much better, including the braids with beads and the ornate engravings on the armor. While Model A (FLUX.1 [schnell]) has superior skin realism and a more striking expression, it failed to include several key decorative elements requested in the prompt.
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 adherence to the minimalist aesthetic with a clean white background.
- + Excellent layout organization that clearly separates the sections as requested.
- + Clean typography that looks professional and fits the modern theme.
- − The placeholder text for descriptions is nonsensical gibberish.
- − The 'ORFEFUS' header seems unrelated to the prompt categories.
HiDream I1 Fast
- + Successfully incorporates vibrant accents with the red header bars.
- + Food photos have good color saturation and appetizing appearance.
- − Failed the 'white background' requirement by including a large black header.
- − Text rendering is poor with significant artifacts and spelling errors like 'NOEPINEINIALIST'.
- − Composition feels cluttered compared to the minimalist request.
Verdict: FLUX.1 [schnell] is the clear winner as it perfectly captured the 'modern minimalist' and 'white background' requirements, resulting in a layout that looks like a real professional menu. While HiDream I1 Fast used vibrant colors, it failed on the background color and suffered from severe text corruption and layout clutter.
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.1 [schnell]
- + Excellent photorealistic texture on the burger bun and meat patty
- + High-quality rendering of embers and background lighting
- + Clean, professional composition similar to a commercial ad
- − Text rendering is broken, missing the 'M' in MAGIC and providing conflicting prices
- − Failed the 'exploded' instruction as the main burger is fully assembled
HiDream I1 Fast
- + Successful rendering of the main 'MAGIC BURGER' text with the requested glowing effect
- + Good adherence to the starburst and price requirements
- + Effective fiery background color palette
- − Image quality is significantly lower with a soft, slightly blurry finish
- − Secondary text 'LIMITED TIME' is distorted and messy
- − The 'exploded' burger effect is weak, with only a few ring-like objects floating
Verdict: FLUX.1 [schnell] produces a much higher quality image with superior photorealism, though it failed significantly on text accuracy and the specific 'exploded' layout. HiDream I1 Fast followed the text styling and layout instructions more closely but suffered from poor resolution, distorted secondary text, and a less professional aesthetic. FLUX.1 [schnell] is likely the winner for users prioritizing visual fidelity, but HiDream I1 Fast is closer to the requested prompt structure.
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]
- + The handwriting style is consistent and realistically messy.
- + The chalkboard surface and frame look very authentic.
- − The text is largely nonsensical with frequent spelling errors.
- − The handwriting is blocky rather than the requested elegant cursive.
HiDream I1 Fast
- + Captures the requested cursive style for the title.
- + The 'cozy café' atmosphere is better rendered in the background.
- − Text legibility suffers from overlapping characters and messy smudges.
- − Several menu items contain spelling errors and awkward character spacing.
Verdict: Both models struggled significantly with the spelling and legibility requirements of the prompt. HiDream I1 Fast followed the stylistic request for cursive elements and atmospheric background more effectively, while FLUX.1 [schnell] produced more believable chalk textures but failed to output coherent English words.
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]
- + Perfect adherence to the difficult constraint of the horse being on top
- + Stunning cinematic lighting and composition with the planetary backdrop
- + High level of detail on the space suit and saddle
- − The horse has two heads appearing to merge, which is an anatomical artifact
HiDream I1 Fast
- + Realistic lighting and textures
- + Clear, high-resolution rendering of the subject
- − Completely failed the primary prompt instruction by putting the astronaut on top
- − Failed the environment prompt by placing the subjects in a desert instead of space
Verdict: FLUX.1 [schnell] followed a complex and non-standard prompt perfectly, successfully placing the horse on top of the astronaut in a space setting. HiDream I1 Fast failed almost every specific instruction, providing a generic image of an astronaut riding a horse in a desert. despite the anatomical error of the two-headed horse in FLUX.1 [schnell], it is the clear winner for its prompt adherence and surreal creativity.
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 fur texture and lighting on the capybara.
- + Logical camera placement that views both the front and back seats effectively.
- + Detailed rendering of the passenger and her interaction with the phone.
- − The capybara's hands are anatomically strange and not properly gripping the steering wheel.
- − The capybara is looking at the camera rather than the road.
HiDream I1 Fast
- + Successfully shows two hands on the steering wheel.
- + Good depiction of the Manhattan street lights through the window.
- + Clear 'TAXI' text on the cap.
- − Significant anatomical error with human hands growing out of the capybara's chest/shoulders to reach the wheel.
- − The passenger appears to be in the front seat or middle console area rather than the back seat.
- − The capybara's head is not naturally attached to the body.
Verdict: FLUX.1 [schnell] creates a much more convincing and coherent image, despite the capybara looking at the camera; it manages the complicated interior space well. HiDream I1 Fast fails significantly on anatomy, rendering human hands protruding from the capybara's neck area and placing the passenger in an ambiguous central position rather than the back seat.
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]
- + Excellent typography style that matches the gothic theme.
- + Clearer, more cinematic lighting effects with a nice glow from the pumpkin.
- + Better overall aesthetic coherence for a digital invitation.
- − Several spelling errors and repetitions in the small text and event details.
- − The 'dark parchment' looks more like a modern graphic background than a vintage poster.
HiDream I1 Fast
- + Successfully captures the 'dark parchment' and 'torn poster' aesthetic requested.
- + Border design with webs is more prominent and detailed.
- + Good layout with the central pumpkin and trees framing the composition.
- − Significant text corruption and overlapping characters in the banner and details.
- − Lower resolution/clarity with more visible compression artifacts.
- − Missed some specific text elements like 'Invitation' in the main heading.
Verdict: Both models struggled with the complex task of rendering five distinct lines of specific text correctly. FLUX.1 [schnell] is the winner because its typography is much more legible and its lighting is significantly more polished and 'cinematic' as requested, whereas HiDream I1 Fast suffered from severe text artifacts and lower image quality.
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 high-clarity 3D rendering with smooth PBR-style textures
- + Perfectly followed the 45-degree isometric perspective request
- + Ultra-clean composition that fits the 'miniature' aesthetic
- − Failed to include the requested word 'SUSHI' in text
- − The white text 'JAPAN' lacks contrast against the light blue background
HiDream I1 Fast
- + Successfully included all requested text elements: 'JAPAN', 'SUSHI', and flag
- + Included variety in sushi types which adds visual interest
- + Good readability of typography and bold icons
- − Perspective is more of a front-view than the requested 45-degree top-down isometric
- − Noticeable artifacts and poor texture on the 'sushi' lettering and icons
- − Lower visual quality with some blurring on the edges of the 3D models
Verdict: FLUX.1 [schnell] produced a far superior 3D render with clean textures and a perfect isometric perspective, though it failed to include all the requested text. HiDream I1 Fast adhered more closely to the prompt's specific text requirements but struggled with perspective and overall image clarity. FLUX.1 [schnell] is the winner for its professional polish and adherence to the miniature diorama style.
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]
- + Exhibits clearer sunrise 'god rays' as requested in the prompt.
- + Vibrant color palette with high-quality rendering of the flower meadow.
- + Excellent focus on the puppy's face and fur texture.
- − Failed to include a rabbit, instead generating two cat-like hybrids.
- − The animal in the middle has anatomically confusing ears that look like a cat-fennec fox mix.
HiDream I1 Fast
- + Successfully captured a more photorealistic fur texture on the golden retriever.
- + Includes a good variety of butterflies and captures the golden hour lighting effectively.
- + The facial expressions are very soft and wholesome.
- − Failed to include a bunny, instead providing two kittens and a fox.
- − The spatial composition feels a bit crowded at the bottom edge.
- − The kitten on the far left has slightly unnatural eye placement.
Verdict: Both models failed to include all four specific animals requested, as neither image includes a baby bunny. However, FLUX.1 [schnell] followed the lighting and atmosphere instructions much better, providing distinct god rays and a more 'masterpiece' feel, whereas HiDream I1 Fast feels slightly more generic in its composition.
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]
- + Excellent vector aesthetic with clean, professional lines
- + Balanced composition that follows traditional logo architecture
- + High visual clarity and sharp rendering
- − Significant spelling errors in the brand name ('CAFEÉ FRAMILAN')
- − Incorrect date provided ('EST. 7720')
- − Missing the steam element requested in the prompt
HiDream I1 Fast
- + Accurately spells the requested name 'CAFFÉ FLORIAN'
- + Includes the requested steam and banner elements
- + Better adherence to the specific '1720' date requirement despite a slight typo
- − Typography within the cloche is poorly integrated and lacks symmetry
- − The date banner has a rendering error ('17210')
- − Vector lines are less crisp and show some messy overlaps
Verdict: HiDream I1 Fast is the winner primarily because it managed to spell 'Caffè Florian' correctly, which is the most critical part of a logo request, whereas FLUX.1 [schnell] hallucinated an entirely different name. While FLUX.1 [schnell] produced a much cleaner and more professional-looking vector emblem, its total failure on text accuracy and the established date makes it unusable for the prompt.
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]
- + Excellent vector aesthetic with clean, professional lines and a sophisticated layout.
- + Strong adherence to the requested color palette.
- + Captures the infographic feel with consistent iconography and concentric orbital paths.
- − The text is largely gibberish and significantly non-functional.
- − Fails to clearly delineate the 6 distinct steps requested, merging them into a single diagram.
HiDream I1 Fast
- + Attempts to label the specific steps as requested in the prompt.
- + Features clear, legible heading text for 'APOLLO 11'.
- + Categorizes the information into a more traditional infographic step-by-step layout.
- − Visual quality is poor with messy, jagged lines and blurry edges.
- − Icons are nonsensical (e.g., a generic orange planet for Translunar) and do not follow the 'NASA-inspired' style well.
- − Included a Saturn-like ringed planet for Earth/Lunar icons which is factually incorrect.
Verdict: FLUX.1 [schnell] creates a much more visually appealing and professionally designed vector poster that perfectly matches the requested aesthetic, though its text and sequential logic are weak. HiDream I1 Fast attempts to follow the step-by-step instructions more literally with labels, but the artistic execution is very low quality with significant artifacts and poor icon design. FLUX.1 [schnell] is the preferred choice for a 'clean, modern vector infographic' despite the illegible body text.
Explore each model
Distilled version of HiDream AI's 17B parameter text-to-image model