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

Best AI image generator for drama scenes

25 models compared (November 2026)

Best for drama scenes: Luma Uni-1 Max (7.7 out of 10), ahead of Qwen Image 3.0 Pro and Nano Banana 2, 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 close-up from the jury box at seated eye level, the witness centred, a tall arched window glowing behind her and dark panelling on both sides. A woman in her sixties sits very straight in a worn wooden witness stand, navy wool coat buttoned to the throat, both hands folded tightly over a handkerchief, knuckles pale. She has just been asked the question: her chin lifts a fraction and her eyes, wet but steady, hold on the person asking. A 1970s municipal courtroom: varnished oak with nicks and water rings, a brass rail, a sweating water jug. Dust motes drift through broad shafts of late-morning sun from the window, the 5600K key, across her shoulder and half her face, with soft bounce from pale plaster at 4:1. 35mm Kodak Vision3 250D, Cooke S4/i 75mm at T2, amber and walnut palette with soft green shadows, visible grain, a frame from a 1970s courtroom drama. True-to-life skin, fine wrinkles and face powder, no CGI look. No text, no logos, no watermarks.

Shape
16:9, or the nearest a model offers
Made
Models
25
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.

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: Qwen Image 3.0 Pro. Weakest: Wan 2.6.

    Qwen Image 3.0 Pro gets the most of the brief: the witness centred, wet red-rimmed eyes, a sweating jug, the brass rail, a handkerchief and natural skin. The light falls short: a soft backlight only, with no sun across her face and no visible shafts. Wan 2.6 went theatrical: white lace gloves, rouged cheeks, a frayed collar and a cloud of dust, none of which were asked for.

  • Light: shafts and dust motes

    The brief asked for broad shafts of sun with dust in them. FLUX.3 Klein, Seedream 5.0 Lite and Muse Image drew clear beams with floating motes. Nano Banana 2, Qwen Image 3.0 and Wan 2.7 Image kept the window glowing but gave flat, even room light, so the sun never crosses her face. Recraft V4.1 Pro and Utility Pro pushed cold teal beams, which fights the amber and walnut palette.

  • Framing: centred, from the jury box

    Nano Banana 2, Qwen Image 3.0, FLUX.2 [dev] and Wan 2.7 Image give the straight-on, centred medium close-up the prompt describes. Muse Image turns her three-quarters away, Luma Uni-1 shoots from low and off to one side, and Grok Imagine Image makes her small and left of frame. FLUX.2 [pro] puts a blurred figure in the foreground that nobody asked for.

  • The story beat: wet but steady eyes

    The moment is a lifted chin and steady, wet eyes. Qwen Image 3.0 Pro and Nano Banana 2 get closest, with a quiet, damp-eyed look. Seedream 4.5 overshoots into visible tears, and both it and FLUX.2 [flex] look more anxious than composed. Luma Uni-1 Max has her mouth slightly open, as if speaking, which reads as the wrong beat.

  • Props and wardrobe: coat, handkerchief, jug

    Nearly every model delivered the navy coat, the handkerchief and a water jug. Extras crept in: FLUX.2 [flex] piles papers on the stand, Seedream 4.5 adds bright painted nails, and FLUX.2 [dev] Turbo puts a ring on her hand. Buttoned to the throat is the harder ask: Seedream 4.5 and Seedream 5.0 Lite close the collar high, while Nano Banana 2 and Qwen Image 3.0 leave it open.

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).