Gemini 3.1 Flash Image (Nano Banana 2)

A comic page with a recurring character

Which image model keeps one character consistent across six panels, and which ones will draw a violent scene at all?

How: One character reference sheet, generated once and passed to every model, plus the same 6-panel page prompt. We ran the scene twice, once with violence (a knife fight) and once without.

• Qwen Image 3

  Only model to clear all four bars: drew the violence, held the character, got the mirrored-panel layout, drew the villains as written.

• GPT Image 2 (high)

  Best craft and atmosphere.

• Gemini 3.1 Flash Image, 4K

  Highest resolution (3392 by 5056). Got the mirrored-panel layout right.

• Muse Image

  Refused the violent version with an error. On the non-violent version it followed all six story beats in order.

• Seedream V4

  Only model to vary panel sizes like a real comic page. Weaker storytelling.

• Flux Kontext Pro

  Returned a fully black image on the violent prompt, with no error.

The test pages show graphic violence, so we describe them here instead of showing them.

Limits: One page, one art style, judged by our team. Violence handling can change when a provider updates its filters.

Cartoon cast to photoreal actors

Which cheap image model turns cartoon character designs into believable actors and stays on model?

How: Six cartoon character references from our show Pillbox, each converted to a photoreal actor by two models with the same prompt.

• Muse Image

  Stayed closer to each design and used the plain gray backdrop the prompt asked for, every time. $0.01 an image.

• Nano Banana 2

  Kept the pharmacy background on 2 of 5 characters even though the prompt asked for a plain gray backdrop, and changed one character's ethnicity. About $0.067 an image.

Limits: Both models added glasses that are not in some of the designs. One prompt, five characters shown here.