glu
Studio
Join the waitlist
All comparisons
By scene · 25 models

Best AI image generator for fast motion

25 models compared (November 2026)

Best for fast motion: Seedream 4.5 (8.3 out of 10), ahead of Nano Banana 2 and Muse Image, from our scores for prompt adherence, realism and film look.

We sent the same prompt, word for word, to the 25 best-ranked AI image models and put every result side by side. One image each, no retouching, no picking the best of several. Each card shows the model, its maker and its benchmark score.

The prompt

Medium wide shot from just outside the arena fence, slightly low, rider and bull centred with open dust on both sides. A rider in his late twenties in fringed tan leather chaps, a plaid snap-button shirt and a plain protective vest is thrown clear into the air, one gloved hand flung high, hat tumbling away, his face pure astonishment. Beneath him a heavy brindled bull twists mid-buck, hind legs kicked skyward, churned dirt bursting outward. A sparse row of middle-aged adult spectators stands behind the pipe fence, softly out of focus. The key is low evening sun at 3200K behind the bull, just outside frame on camera right, backlighting the dust into a golden cloud and rimming the bull's hair, the bright dust itself filling at 3:1. RED V-Raptor, Arri Signature Prime 125mm at T2.8, a 1/2000 shutter freezing every clod and bead of sweat, compressed background, honey and amber grade, soft highlight roll-off, gentle grain, a frame from a modern rodeo drama. True-to-life skin, sweat and grit, no CGI look. No text, no logos, no watermarks.

Shape
16:9, or the nearest a model offers
Made
Models
25, 19 finished
How we ran it and ranked it

Every model got the prompt exactly as written above. Where a model can rewrite or expand a prompt before it draws, that was switched off, so each one worked from the same words. We made one image per model at 16:9; a model that cannot make 16:9 made its nearest shape, and its picture is trimmed slightly at the edges to fill the frame. Where a model drew black cinema bars into its picture, the bars are cut off for display. Nothing was retouched or chosen from several tries. A model that failed was tried once more; if it failed again, its card says so and why.

The order is the models' benchmark rank, not our opinion: their score in the Artificial Analysis text-to-image arena (human preference Elo, checked 8 November 2026), or, for a model Artificial Analysis does not score, the Arena text-to-image leaderboard (checked 6 November 2026). The two boards use different scales, so each score is placed by the share of its own board it beats. A model sold under two names is one model, shown once under both.

A model whose content filter refused the prompt is shown as refused, with no picture. Only models whose pictures may be used commercially are included.

The answer at the top and the notes under What we noticed come from our own scores, not the benchmark. Each picture was scored 1 to 10 on prompt adherence, realism and film look, and the scores were checked by an independent cross-review.

The 25 results

Ranked by benchmark. Select a picture to see it full size, then use the arrows or your arrow keys to compare.

  1. #1

    Nano Banana 2

    · Google· AA Elo 1142
  2. #2

    Muse Image

    · Meta· AA Elo 1128
  3. #3

    Nano Banana Pro

    · Google· AA Elo 1119
  4. #4

    Qwen Image 3.0 Pro

    · Alibaba· AA Elo 1095
  5. #5

    Qwen Image 3.0

    · Alibaba· AA Elo 1073
  6. #6

    FLUX.3 Klein

    · Black Forest Labs· AA Elo 1043
  7. #7

    FIBO 2.0

    · Bria· AA Elo 1039
  8. #8

    Seedream 4.5

    · ByteDance· AA Elo 1030
  9. #9

    FLUX.2 [flex]

    · Black Forest Labs· AA Elo 1028
  10. #10

    Recraft V4.1 Utility

    · Recraft· AA Elo 1028
  11. #11

    Luma Uni-1 Max

    · Luma AI· AA Elo 1026
  12. #12

    Grok Imagine Image

    · xAI· AA Elo 1024
  13. #13

    FLUX.2 [max]

    · Black Forest Labs· AA Elo 1021
  14. #14

    Seedream 5.0 Lite

    · ByteDance· AA Elo 1019
  15. #15

    Recraft V4.1 Utility Pro

    · Recraft· AA Elo 1018
  16. #16

    Wan 2.6

    · Alibaba· AA Elo 1018
  17. #17

    FLUX.2 [pro]

    · Black Forest Labs· AA Elo 1003
  18. #18

    FLUX.2 [dev]

    · Black Forest Labs· AA Elo 1000
  19. #19

    FLUX.2 [dev] Turbo

    · Black Forest Labs· AA Elo 996
  20. #20

    Luma Uni-1

    · Luma AI· AA Elo 994
  21. #21

    Recraft V4.1 Pro

    · Recraft· Arena 1132
  22. #22

    FLUX.2 [dev] Flash

    · Black Forest Labs· AA Elo 989
  23. #23

    HunyuanImage 3.0 Instruct

    · Tencent· AA Elo 988
  24. #24

    Wan 2.7 Image

    · Alibaba· AA Elo 988
  25. #25

    Cosmos 3 Super

    · NVIDIA· AA Elo 987

What we noticed

Our read of these pictures. It's one image per model, so treat it as a snapshot, not a verdict.

  • Strongest: Nano Banana 2. Weakest: HunyuanImage 3.0 Instruct.

    Nano Banana 2 gets the whole frozen moment: the rider is fully clear of the bull, one gloved hand up, hat tumbling, mouth open in surprise, while a brindled bull twists with both hind legs kicked up and dirt flying. The fringed chaps, plaid shirt and vest are all there. HunyuanImage 3.0 Instruct leaves the rider upright over a planted bull, and adds a white board with green swooshes that reads like a logo.

  • Six models refused

    Luma Uni-1 Max, Wan 2.6, FLUX.2 [dev], FLUX.2 [dev] Turbo, Luma Uni-1 and FLUX.2 [dev] Flash made no picture: their content filters blocked a scene of danger or injury, on both tries. Their cards say so. The other 19 models drew the same prompt.

  • Thrown clear, or still in the saddle

    About half show the rider actually being thrown. Nano Banana 2, Muse Image, Seedream 4.5, Recraft V4.1 Utility and Recraft V4.1 Pro have him flying clear or pitching off sideways. Grok Imagine Image, FLUX.2 [flex], FLUX.2 [max] and Cosmos 3 Super keep him seated with an arm raised, which reads as riding rather than being thrown. Recraft V4.1 Pro has the clearest gap, but its bull barely twists.

  • The bull and the kicked hind legs

    The prompt wants the bull mid-buck with hind legs skyward. Nano Banana 2, Muse Image, Seedream 4.5 and Wan 2.7 Image show real kicks. Grok Imagine Image and HunyuanImage 3.0 Instruct have the bull walking or standing square. Cosmos 3 Super raises the hindquarters, but the hind legs are thin upright stalks, and it puts a hat on the rider's head and another in the air.

  • Dust, backlight and extras nobody asked for

    Seedream 4.5, Seedream 5.0 Lite and Recraft V4.1 Utility Pro get the low sun lighting the dust into a golden or pink cloud, with rim light on the bull. Recraft V4.1 Utility puts phones and cameras in the spectators' hands, and Seedream 5.0 Lite swaps the tan shirt for bright red plaid. Several pictures also show a bright sun disc in frame, though the prompt puts it outside the frame.

See how these models rank across all 10 scenes

Head to heads featuring these models

Two of the models above on the same film scenes, judged pair by pair.

Other scenes

The same 25 models on another film shot.

Join the waitlist

Sign in once. If you don't have an invite yet, that puts you on the waitlist, and we'll email you when your invite is ready. For people 18 or over.

Join the waitlist

Sold under more than one name, shown once: Nano Banana 2 (Nano Banana 2, Gemini 3.1 Flash Image Preview); Nano Banana Pro (Nano Banana Pro, Gemini 3 Pro Image Preview).