NightCafe AI Art
Create

AI text-to-video model comparison

Compare AI text-to-video models side-by-side with benchmark prompts, credit costs, latency, and clip lengths.

Prompt
Kling 4.0
šŸŖ™ 59 cr720p⚔ 191.9s avgPRO
Kling 4.0 Flash
šŸŖ™ 38 cr720p⚔ 90.7s avgPRO
MiniMax H3 Max
šŸŖ™ 40 cr720p⚔ 34.3s avgPRO
MiniMax H3 Max Turbo
šŸŖ™ 20 cr720p⚔ 29.3s avgPRO
MiniMax H3 Fast
šŸŖ™ 25 cr480p⚔ 35.4s avgPRO
Gemini Omni Flash 1.2
šŸŖ™ 27 cr720p⚔ 64.5s avgPRO
Wan 3.0
šŸŖ™ 50 cr720p⚔ 220.2s avgPRO
Wan 3.0 Prime
šŸŖ™ 70 cr720p⚔ 125.7s avgPRO
MiniMax H3
šŸŖ™ 70 crModel default⚔ 264.2s avgPRO
Seedance 2.5
šŸŖ™ 125 cr720p⚔ 175.9s avgPRO
P-Video-2 Fast
šŸŖ™ 8 cr720p⚔ 40.4s avgPRO
P-Video-2
šŸŖ™ 13 cr720p⚔ 43.4s avgPRO
P-Video-2 Pro Fast
šŸŖ™ 14 cr768p⚔ 37.3s avgPRO
P-Video-2 Pro
šŸŖ™ 29 cr768p⚔ 50.4s avgPRO
Seedance 2.0 Mini
šŸŖ™ 42.5 cr720p⚔ 125.8s avgPRO
Seedance 2.0
šŸŖ™ 80 cr720p⚔ 209.0s avgPRO
Seedance 2.0 Fast
šŸŖ™ 65 cr720p⚔ 159.8s avgPRO
Happy Horse 1.0
šŸŖ™ 56 cr720p⚔ 103.6s avgPRO
Grok Imagine Video
šŸŖ™ 42 cr720p⚔ 110.7s avgPRO
Google Veo 3.1 Lite
šŸŖ™ 20 cr720p⚔ 54.6s avgPRO
Kling 3.0 Turbo
šŸŖ™ 56 cr720p⚔ 105.6s avgPRO
PixVerse V6
šŸŖ™ 30 cr720p⚔ 88.6s avgPRO
Art & Animations
ā€œA whimsical stop-motion claymation animation of a small blue robot planting a tiny glowing flower in a cracked ceramic pot, soft studio lighting, tactile clay texture.ā€
Kling 4.0
šŸŖ™ 59 crā± 5s⚔ 191.0s1280Ɨ720PRO
Try in Studio
Kling 4.0 Flash
šŸŖ™ 38 crā± 5s⚔ 85.7s1280Ɨ720PRO
MiniMax H3 Max
šŸŖ™ 40 crā± 5s⚔ 30.3s1344Ɨ768PRO
MiniMax H3 Max Turbo
šŸŖ™ 20 crā± 5s⚔ 25.4s1344Ɨ768PRO
MiniMax H3 Fast
šŸŖ™ 25 crā± 5s⚔ 35.6s864Ɨ480PRO
Gemini Omni Flash 1.2
šŸŖ™ 27 crā± 5s⚔ 60.6s1280Ɨ720PRO
Wan 3.0
šŸŖ™ 50 crā± 5s⚔ 151.1s1280Ɨ720PRO
Wan 3.0 Prime
šŸŖ™ 70 crā± 5s⚔ 106.0s1280Ɨ720PRO
MiniMax H3
šŸŖ™ 70 crā± 5s⚔ 191.1s2560Ɨ1440PRO
Seedance 2.5
šŸŖ™ 125 crā± 5s⚔ 161.2s1280Ɨ720PRO
P-Video-2 Fast
šŸŖ™ 8 crā± 5s⚔ 35.5s1280Ɨ704PRO
P-Video-2
šŸŖ™ 13 crā± 5s⚔ 45.5s1280Ɨ704PRO
P-Video-2 Pro Fast
šŸŖ™ 14 crā± 5s⚔ 40.4s1344Ɨ768PRO
P-Video-2 Pro
šŸŖ™ 29 crā± 5s⚔ 45.5s1344Ɨ768PRO
Seedance 2.0 Mini
šŸŖ™ 42.5 crā± 5s⚔ 100.8s1280Ɨ720PRO
Seedance 2.0
šŸŖ™ 80 crā± 5s⚔ 196.0s1280Ɨ720PRO
Seedance 2.0 Fast
šŸŖ™ 65 crā± 5s⚔ 145.9s1280Ɨ720PRO
Happy Horse 1.0
šŸŖ™ 56 crā± 4s⚔ 100.6s1280Ɨ720PRO
Grok Imagine Video
šŸŖ™ 42 crā± 6s⚔ 90.8s1280Ɨ720PRO
Google Veo 3.1 Lite
šŸŖ™ 20 crā± 4s⚔ 55.7s1280Ɨ720PRO
Kling 3.0 Turbo
šŸŖ™ 56 crā± 5s⚔ 216.1s1280Ɨ720PRO
PixVerse V6
šŸŖ™ 30 crā± 5s⚔ 70.7s1280Ɨ720PRO
Prompt
Kling 4.0
šŸŖ™ 59 cr720p⚔ 191.9s avgPRO
Kling 4.0 Flash
šŸŖ™ 38 cr720p⚔ 90.7s avgPRO
MiniMax H3 Max
šŸŖ™ 40 cr720p⚔ 34.3s avgPRO
MiniMax H3 Max Turbo
šŸŖ™ 20 cr720p⚔ 29.3s avgPRO
MiniMax H3 Fast
šŸŖ™ 25 cr480p⚔ 35.4s avgPRO
Gemini Omni Flash 1.2
šŸŖ™ 27 cr720p⚔ 64.5s avgPRO
Wan 3.0
šŸŖ™ 50 cr720p⚔ 220.2s avgPRO
Wan 3.0 Prime
šŸŖ™ 70 cr720p⚔ 125.7s avgPRO
MiniMax H3
šŸŖ™ 70 crModel default⚔ 264.2s avgPRO
Seedance 2.5
šŸŖ™ 125 cr720p⚔ 175.9s avgPRO
P-Video-2 Fast
šŸŖ™ 8 cr720p⚔ 40.4s avgPRO
P-Video-2
šŸŖ™ 13 cr720p⚔ 43.4s avgPRO
P-Video-2 Pro Fast
šŸŖ™ 14 cr768p⚔ 37.3s avgPRO
P-Video-2 Pro
šŸŖ™ 29 cr768p⚔ 50.4s avgPRO
Seedance 2.0 Mini
šŸŖ™ 42.5 cr720p⚔ 125.8s avgPRO
Seedance 2.0
šŸŖ™ 80 cr720p⚔ 209.0s avgPRO
Seedance 2.0 Fast
šŸŖ™ 65 cr720p⚔ 159.8s avgPRO
Happy Horse 1.0
šŸŖ™ 56 cr720p⚔ 103.6s avgPRO
Grok Imagine Video
šŸŖ™ 42 cr720p⚔ 110.7s avgPRO
Google Veo 3.1 Lite
šŸŖ™ 20 cr720p⚔ 54.6s avgPRO
Kling 3.0 Turbo
šŸŖ™ 56 cr720p⚔ 105.6s avgPRO
PixVerse V6
šŸŖ™ 30 cr720p⚔ 88.6s avgPRO
Realism
ā€œA slow steady dolly toward a cafe window sign reading exactly "NightCafe - OPEN 7 DAYS - EST. 2019". The text stays sharp, correctly spelled and unchanged for the whole clip as the camera approaches. No other text in the frame.ā€
Kling 4.0
šŸŖ™ 59 crā± 5s⚔ 155.6s1280Ɨ720PRO
Kling 4.0 Flash
šŸŖ™ 38 crā± 5s⚔ 65.4s1280Ɨ720PRO
MiniMax H3 Max
šŸŖ™ 40 crā± 5s⚔ 25.3s1344Ɨ768PRO
MiniMax H3 Max Turbo
šŸŖ™ 20 crā± 5s⚔ 25.3s1344Ɨ768PRO
MiniMax H3 Fast
šŸŖ™ 25 crā± 5s⚔ 35.3s864Ɨ480PRO
Gemini Omni Flash 1.2
šŸŖ™ 27 crā± 5s⚔ 55.4s1280Ɨ720PRO
Wan 3.0
šŸŖ™ 50 crā± 5s⚔ 205.8s1280Ɨ720PRO
Wan 3.0 Prime
šŸŖ™ 70 crā± 5s⚔ 95.5s1280Ɨ720PRO
MiniMax H3
šŸŖ™ 70 crā± 5s⚔ 195.9s2560Ɨ1440PRO
Seedance 2.5
šŸŖ™ 125 crā± 5s⚔ 170.8s1280Ɨ720PRO
P-Video-2 Fast
šŸŖ™ 8 crā± 5s⚔ 25.2s1280Ɨ704PRO
P-Video-2
šŸŖ™ 13 crā± 5s⚔ 30.3s1280Ɨ704PRO
P-Video-2 Pro Fast
šŸŖ™ 14 crā± 5s⚔ 35.3s1344Ɨ768PRO
P-Video-2 Pro
šŸŖ™ 29 crā± 5s⚔ 45.3s1344Ɨ768PRO
Seedance 2.0 Mini
šŸŖ™ 42.5 crā± 5s⚔ 110.8s1280Ɨ720PRO
Seedance 2.0
šŸŖ™ 80 crā± 5s⚔ 150.6s1280Ɨ720PRO
Seedance 2.0 Fast
šŸŖ™ 65 crā± 5s⚔ 175.9s1280Ɨ720PRO
Happy Horse 1.0
šŸŖ™ 56 crā± 4s⚔ 105.7s1280Ɨ720PRO
Grok Imagine Video
šŸŖ™ 42 crā± 6s⚔ 85.6s1280Ɨ720PRO
Google Veo 3.1 Lite
šŸŖ™ 20 crā± 4s⚔ 35.4s1280Ɨ720PRO
Kling 3.0 Turbo
šŸŖ™ 56 crā± 5s⚔ 65.5s1280Ɨ720PRO
PixVerse V6
šŸŖ™ 30 crā± 5s⚔ 55.3s1280Ɨ720PRO
Realism
ā€œA low tracking shot running alongside the subject at knee height, commercial sportswear cinematography, crisp and high-contrast, cold blue pre-dawn light with the first warm sun breaking along the horizon, an empty city waterfront promenade, wet concrete from overnight rain, the skyline across the water still lit, a female runner in a charcoal training top pushes through the last stretch of a session, her shoes striking through shallow puddlesā€
Kling 4.0
šŸŖ™ 59 crā± 5s⚔ 170.9s1280Ɨ720PRO
Kling 4.0 Flash
šŸŖ™ 38 crā± 5s⚔ 86.3s1280Ɨ720PRO
MiniMax H3 Max
šŸŖ™ 40 crā± 5s⚔ 40.3s1344Ɨ768PRO
MiniMax H3 Max Turbo
šŸŖ™ 20 crā± 5s⚔ 30.3s1344Ɨ768PRO
MiniMax H3 Fast
šŸŖ™ 25 crā± 5s⚔ 40.4s864Ɨ480PRO
Gemini Omni Flash 1.2
šŸŖ™ 27 crā± 5s⚔ 65.7s1280Ɨ720PRO
Wan 3.0
šŸŖ™ 50 crā± 5s⚔ 161.1s1280Ɨ720PRO
Wan 3.0 Prime
šŸŖ™ 70 crā± 5s⚔ 145.9s1280Ɨ720PRO
MiniMax H3
šŸŖ™ 70 crā± 5s⚔ 211.1s2560Ɨ1440PRO
Seedance 2.5
šŸŖ™ 125 crā± 5s⚔ 165.8s1280Ɨ720PRO
P-Video-2 Fast
šŸŖ™ 8 crā± 5s⚔ 30.4s1280Ɨ704PRO
P-Video-2
šŸŖ™ 13 crā± 5s⚔ 40.4s1280Ɨ704PRO
P-Video-2 Pro Fast
šŸŖ™ 14 crā± 5s⚔ 40.4s1344Ɨ768PRO
P-Video-2 Pro
šŸŖ™ 29 crā± 5s⚔ 45.4s1344Ɨ768PRO
Seedance 2.0 Mini
šŸŖ™ 42.5 crā± 5s⚔ 130.9s1280Ɨ720PRO
Seedance 2.0
šŸŖ™ 80 crā± 5s⚔ 155.9s1280Ɨ720PRO
Seedance 2.0 Fast
šŸŖ™ 65 crā± 5s⚔ 120.8s1280Ɨ720PRO
Happy Horse 1.0
šŸŖ™ 56 crā± 4s⚔ 95.6s1280Ɨ720PRO
Grok Imagine Video
šŸŖ™ 42 crā± 6s⚔ 75.6s1280Ɨ720PRO
Google Veo 3.1 Lite
šŸŖ™ 20 crā± 4s⚔ 50.5s1280Ɨ720PRO
Kling 3.0 Turbo
šŸŖ™ 56 crā± 5s⚔ 60.4s1280Ɨ720PRO
PixVerse V6
šŸŖ™ 30 crā± 5s⚔ 65.6s1280Ɨ720PRO
Prompt
Kling 4.0
šŸŖ™ 59 cr720p⚔ 191.9s avgPRO
Kling 4.0 Flash
šŸŖ™ 38 cr720p⚔ 90.7s avgPRO
MiniMax H3 Max
šŸŖ™ 40 cr720p⚔ 34.3s avgPRO
MiniMax H3 Max Turbo
šŸŖ™ 20 cr720p⚔ 29.3s avgPRO
MiniMax H3 Fast
šŸŖ™ 25 cr480p⚔ 35.4s avgPRO
Gemini Omni Flash 1.2
šŸŖ™ 27 cr720p⚔ 64.5s avgPRO
Wan 3.0
šŸŖ™ 50 cr720p⚔ 220.2s avgPRO
Wan 3.0 Prime
šŸŖ™ 70 cr720p⚔ 125.7s avgPRO
MiniMax H3
šŸŖ™ 70 crModel default⚔ 264.2s avgPRO
Seedance 2.5
šŸŖ™ 125 cr720p⚔ 175.9s avgPRO
P-Video-2 Fast
šŸŖ™ 8 cr720p⚔ 40.4s avgPRO
P-Video-2
šŸŖ™ 13 cr720p⚔ 43.4s avgPRO
P-Video-2 Pro Fast
šŸŖ™ 14 cr768p⚔ 37.3s avgPRO
P-Video-2 Pro
šŸŖ™ 29 cr768p⚔ 50.4s avgPRO
Seedance 2.0 Mini
šŸŖ™ 42.5 cr720p⚔ 125.8s avgPRO
Seedance 2.0
šŸŖ™ 80 cr720p⚔ 209.0s avgPRO
Seedance 2.0 Fast
šŸŖ™ 65 cr720p⚔ 159.8s avgPRO
Happy Horse 1.0
šŸŖ™ 56 cr720p⚔ 103.6s avgPRO
Grok Imagine Video
šŸŖ™ 42 cr720p⚔ 110.7s avgPRO
Google Veo 3.1 Lite
šŸŖ™ 20 cr720p⚔ 54.6s avgPRO
Kling 3.0 Turbo
šŸŖ™ 56 cr720p⚔ 105.6s avgPRO
PixVerse V6
šŸŖ™ 30 cr720p⚔ 88.6s avgPRO
Tricky Prompts
ā€œA fixed close shot of a full glass of beer on a wooden table. A rolling red cricket ball into the glass. The glass tips over away from the camera, beer spills across the table and spreads outward, and the empty glass rolls slightly and comes to rest. No hands, no cuts.ā€
Kling 4.0
šŸŖ™ 59 crā± 5s⚔ 150.8s1280Ɨ720PRO
Kling 4.0 Flash
šŸŖ™ 38 crā± 5s⚔ 70.4s1280Ɨ720PRO
MiniMax H3 Max
šŸŖ™ 40 crā± 5s⚔ 25.2s1344Ɨ768PRO
MiniMax H3 Max Turbo
šŸŖ™ 20 crā± 5s⚔ 25.3s1344Ɨ768PRO
MiniMax H3 Fast
šŸŖ™ 25 crā± 5s⚔ 30.3s864Ɨ480PRO
Gemini Omni Flash 1.2
šŸŖ™ 27 crā± 5s⚔ 55.4s1280Ɨ720PRO
Wan 3.0
šŸŖ™ 50 crā± 5s⚔ 220.8s1280Ɨ720PRO
Wan 3.0 Prime
šŸŖ™ 70 crā± 5s⚔ 115.5s1280Ɨ720PRO
MiniMax H3
šŸŖ™ 70 crā± 5s⚔ 195.8s2560Ɨ1440PRO
Seedance 2.5
šŸŖ™ 125 crā± 5s⚔ 150.6s1280Ɨ720PRO
P-Video-2 Fast
šŸŖ™ 8 crā± 5s⚔ 45.3s1280Ɨ704PRO
P-Video-2
šŸŖ™ 13 crā± 5s⚔ 30.2s1280Ɨ704PRO
P-Video-2 Pro Fast
šŸŖ™ 14 crā± 5s⚔ 25.3s1344Ɨ768PRO
P-Video-2 Pro
šŸŖ™ 29 crā± 5s⚔ 35.3s1344Ɨ768PRO
Seedance 2.0 Mini
šŸŖ™ 42.5 crā± 5s⚔ 115.7s1280Ɨ720PRO
Seedance 2.0
šŸŖ™ 80 crā± 5s⚔ 180.8s1280Ɨ720PRO
Seedance 2.0 Fast
šŸŖ™ 65 crā± 5s⚔ 150.7s1280Ɨ720PRO
Happy Horse 1.0
šŸŖ™ 56 crā± 4s⚔ 90.5s1280Ɨ720PRO
Grok Imagine Video
šŸŖ™ 42 crā± 6s⚔ 145.8s1280Ɨ720PRO
Google Veo 3.1 Lite
šŸŖ™ 20 crā± 4s⚔ 40.9s1280Ɨ720PRO
Kling 3.0 Turbo
šŸŖ™ 56 crā± 5s⚔ 70.5s1280Ɨ720PRO
PixVerse V6
šŸŖ™ 30 crā± 5s⚔ 60.5s1280Ɨ720PRO
Tricky Prompts
ā€œ15-second multi-shot cinematic sequence in true pure black-and-white only, absolutely no colour, no sepia, no warm tint, no cool tint, no colour contamination of any kind. Hard-contrast monochrome film look with deep crushed blacks, bright clean whites, strong silver highlights and minimal midtones. Inspired by classic high-contrast large-format black-and-white photography in the spirit of Ansel Adams. Weathered 1800s New England lighthouse at sunset, rendered entirely in grayscale values only. Natural film grain, dramatic chiaroscuro, stark shadows, bright lantern light, no modern objects, no text. Shot 1, 0:00-0:02: Extreme macro close-up of the elderly lighthouse keeper’s weathered hands gripping a chipped ceramic coffee mug. Steam rises into the lantern light. Camera slowly tracks across the wrinkles, rough skin and mug texture. Shot 2, 0:02-0:04: Tight close-up of the keeper’s lined face, thick grey beard and tired eyes. He slowly takes a sip of coffee. The lighthouse beam sweeps across his face, leaving one side in brilliant white light and the other in deep shadow. Shot 3, 0:04-0:06: Extreme close-up of the rotating Fresnel lens and aged brass mechanism. Bright white beams refract through the glass. Hard reflections play across corroded metal, bolts and ironwork. Shot 4, 0:06-0:08: Low-angle close-up of the keeper’s worn boots near the balcony railing. Camera glides along peeling paint, rust, rivets and salt-worn metal. Far below, dark Atlantic waves crash against pale rocks. Shot 5, 0:08-0:10: Medium rear three-quarter shot of the keeper leaning on the circular railing around the lantern room, coffee in hand. The wind stirs his coat. The revolving beacon creates strong moving shadows across his body and the balcony. Shot 6, 0:10-0:12: Smooth pullback begins, moving away from the keeper and balcony to reveal more of the lighthouse tower. Cracked stonework, narrow windows and decades of weathering come into view. Shot 7, 0:12-0:15: Continue the uninterrupted pullback into a dramatic extreme wide shot. The full 19th-century lighthouse stands on a rugged New England coastal outcrop. Huge dark waves, bright foam, distant rocky islands and dramatic cloud formations fill the scene. The keeper remains visible as a tiny figure near the glowing lantern. Important visual instructions: true monochrome black-and-white only, no colour at all, no sepia, no tinting, no muted colour, no golden sunset hues. The sunset must be expressed only through grayscale brightness and contrast. Use a hard-contrast film aesthetic, stark tonal separation, silver-gelatin look, crisp whites, dense blacks, dramatic shadow structure. Every shot lasts no more than 3 seconds. Smooth elegant cuts. No slow motion, no static hold, no freeze frame, no painterly look, no soft modern grading. It must look like a proper classic black-and-white hard-contrast film.ā€
Kling 4.0
šŸŖ™ 177 crā± 15s⚔ 291.2s1280Ɨ720PRO
Kling 4.0 Flash
šŸŖ™ 113 crā± 15s⚔ 145.6s1280Ɨ720PRO
MiniMax H3 Max
šŸŖ™ 120 crā± 15s⚔ 50.3s1344Ɨ768PRO
MiniMax H3 Max Turbo
šŸŖ™ 60 crā± 15s⚔ 40.3s1344Ɨ768PRO
MiniMax H3 Fast
šŸŖ™ 75 crā± 15s⚔ 35.3s864Ɨ480PRO
Gemini Omni Flash 1.2
šŸŖ™ 79 crā± 15s⚔ 85.6s1280Ɨ720PRO
Wan 3.0
šŸŖ™ 150 crā± 15s⚔ 362.1s1280Ɨ720PRO
Wan 3.0 Prime
šŸŖ™ 210 crā± 15s⚔ 165.7s1280Ɨ720PRO
MiniMax H3
šŸŖ™ 210 crā± 15s⚔ 527.1s2560Ɨ1440PRO
Seedance 2.5
šŸŖ™ 375 crā± 15s⚔ 231.0s1280Ɨ720PRO
P-Video-2 Fast
šŸŖ™ 23 crā± 15s⚔ 65.5s1280Ɨ704PRO
P-Video-2
šŸŖ™ 38 crā± 15s⚔ 70.5s1280Ɨ704PRO
P-Video-2 Pro Fast
šŸŖ™ 40 crā± 15s⚔ 45.3s1344Ɨ768PRO
P-Video-2 Pro
šŸŖ™ 85 crā± 15s⚔ 80.4s1344Ɨ768PRO
Seedance 2.0 Mini
šŸŖ™ 127.5 crā± 15s⚔ 170.8s1280Ɨ720PRO
Seedance 2.0
šŸŖ™ 240 crā± 15s⚔ 361.5s1280Ɨ720PRO
Seedance 2.0 Fast
šŸŖ™ 195 crā± 15s⚔ 205.9s1280Ɨ720PRO
Happy Horse 1.0
šŸŖ™ 168 crā± 12s⚔ 125.7s1280Ɨ720PRO
Grok Imagine Video
šŸŖ™ 84 crā± 12s⚔ 155.9s1280Ɨ720PRO
Google Veo 3.1 Lite
šŸŖ™ 40 crā± 8s⚔ 90.7s1280Ɨ720PRO
Kling 3.0 Turbo
šŸŖ™ 168 crā± 15s⚔ 115.6s1280Ɨ720PRO
PixVerse V6
šŸŖ™ 90 crā± 15s⚔ 190.8s1280Ɨ720PRO