Why Does Gemini Image Return IMAGE_OTHER?

Short answer

If the Gemini image API returns HTTP 200 with candidates[0].finishReason set to IMAGE_OTHER, and finishMessage says Unable to show the generated image, the model did generate an image, but the provider’s output check filtered it before it was returned.

It is probabilistic: the same request sometimes succeeds and sometimes fails, and the failure rate can be high
It is unrelated to negative prompts, parameters, or the gateway; the problem is what ends up in the picture
The most typical trigger we have measured: the prompt names a real person
The provider states in finishMessage that these requests are not charged

The approach is: find the part of the prompt that makes the picture look like a specific real person or other restricted content, and replace it with a description.

How to recognize it

A typical response:

{
  "candidates": [
    {
      "finishReason": "IMAGE_OTHER",
      "finishMessage": "Unable to show the generated image. The model could not generate the image based on the prompt provided. You will not be charged for this request. Try rephrasing the prompt. ..."
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 1430,
    "candidatesTokenCount": 274,
    "thoughtsTokenCount": 274
  },
  "modelVersion": "gemini-3-pro-image",
  "responseId": "..."
}

Note that candidatesTokenCount is not 0; it equals thoughtsTokenCount. The model finished thinking, but the final image was not delivered. Three ways an image can go missing:

Trait	IMAGE_OTHER	NO_IMAGE	blockReason: OTHER
Field carrying the failure	`candidates[0].finishReason`	`candidates[0].finishReason`	`promptFeedback.blockReason`
Where it happens	Image generated, filtered on output	The model never drew an image	Before generation, input blocked
`finishMessage`	`Unable to show the generated image`	Usually none	No `candidates` at all
Output tokens	Thinking tokens only	0 or text only	0
Reproducible every time?	Probabilistic	Probabilistic	Usually yes
Common cause	Picture resembles a specific real person or other restricted content	The prompt asks for written output	A reference image is blocked
What to do	Rewrite the person or restricted part of the prompt	See NO_IMAGE troubleshooting	See blockReason: OTHER troubleshooting

In the official API reference, IMAGE_OTHER belongs to the same group as IMAGE_SAFETY, IMAGE_PROHIBITED_CONTENT, and IMAGE_RECITATION, all meaning “image generation was stopped”. IMAGE_OTHER covers reasons outside the other categories, and the provider does not disclose the specific criteria.

A tested case

In September 2026 (UTC+8), a customer reported that a pure text-to-image player-card request failed to return an image about 63% of the time on gemini-3-pro-image. The prompt was about 5,500 characters:

An opening sentence naming a real athlete and asking for a “1:1 replica” of their facial features
Detailed pose, framing, uniform colors, art style, and white-background instructions
Two long negative-prompt (NEGATIVE) blocks listing many brand names

Every failure we reproduced was IMAGE_OTHER, returned in about 20 seconds. We then removed one element at a time, 6 calls per group:

Change	No image
Original prompt	5/6
Only the sentence naming the real person removed, everything else verbatim	0/6
Name kept, only the “1:1 replica” wording removed	4/6
Both negative-prompt blocks removed	3/6

The conclusion is clear: the real person’s name itself is the trigger. The model recognizes the name and draws toward that person’s likeness; the closer the likeness, the more likely the output is filtered. The attempts that came out less similar got through, which is why it looked random. Neither the “1:1 replica” wording nor the long negative prompts were the cause. With the name removed, the hair, face-shape, and eye descriptions already in the prompt were enough to produce a player card in the same style.

Six calls per group is enough for this kind of bisection: when the original fails 5/6, the chance that the right fix passes 6 in a row by luck is about 2 in 100,000. The whole investigation took 24 calls.

How to locate the trigger

Step 1: Confirm the failure type

Resend the same request 5 to 6 times, confirm that failures carry finishReason: IMAGE_OTHER, and note the failure rate. If you see NO_IMAGE or blockReason instead, use the matching troubleshooting page.

Step 2: Check names and specific subjects first

Look for names of real people in the prompt (celebrities, athletes, influencers, politicians, and so on), or instructions to look “exactly like” someone. Remove them and run another group.

Step 3: Remove sections by halves

If it is not a name, remove half the prompt at a time, 6 calls per group, and keep narrowing down only in the half whose failure rate drops clearly.

Step 4: Rewrite instead of just deleting

Once you find the trigger, replace the named reference with a description of appearance, clothing, and style, keeping the visual requirements you actually need.

Recommendations

Do not put real people’s names in the prompt: describe their appearance instead, for example “straight blonde hair with an off-center part, almond-shaped eyes, oval face”. This was the only effective fix in our case.
Trimming negative prompts is fine, but they are not the cause: Gemini image models have no separate negative-prompt parameter, so a long NEGATIVE list is read as ordinary text. Trimming it makes the prompt clearer but does not lower the IMAGE_OTHER rate.
Do not rely on retries: with a failure rate above 60%, retrying is a gamble and adds latency. Your client can retry once on IMAGE_OTHER as a fallback, but the real fix is the prompt.
Fix templates before batch generation: if you generate from a roster (for example, one card per player), do not insert the names into the prompt. Use them only for your own file names or later layout.
Use a reference image when a consistent likeness is required: if you truly need to depict a specific person, provide a reference image authorized by that person, and keep in mind the real-person and minor restrictions listed in Nano Banana image generation failures.

Distinguishing the three forms in code:

def classify_no_image(resp: dict) -> str:
    if resp.get("promptFeedback", {}).get("blockReason"):
        return "input_blocked"        # see blockReason: OTHER troubleshooting
    cand = (resp.get("candidates") or [{}])[0]
    reason = cand.get("finishReason")
    if reason == "IMAGE_OTHER":
        return "output_filtered"      # rewrite names / restricted descriptions
    if reason == "NO_IMAGE":
        return "no_image_intent"      # see NO_IMAGE troubleshooting
    if reason in ("IMAGE_SAFETY", "IMAGE_PROHIBITED_CONTENT"):
        return "safety"               # explicit safety block, do not retry
    return "ok" if any("inlineData" in p for p in (cand.get("content") or {}).get("parts") or []) else "unknown"

FAQ

Does it trigger if the prompt only mentions the name, without asking for a likeness?

Yes. In our tests, with the “1:1 replica” wording removed and only the name kept, the failure rate was still 4/6. The model recognizes the name and draws toward that person.

Why does the same request succeed sometimes and fail other times?

The filter runs after the image is generated, so the outcome depends on what was drawn that time. Every generation is different, so the same request can pass or be filtered.

Why did it work after I switched groups or channels?

The strictness of the output check can differ between groups, so the same prompt may fail at different rates. Group routing changes over time, though, so that difference is not stable. Fixing the prompt is the reliable approach.

Do negative prompts (NEGATIVE) help?

Gemini image models have no separate negative-prompt parameter; a NEGATIVE list in the prompt is read as ordinary text. It has no effect on IMAGE_OTHER, but a very long list can dilute the main description. Keep only the few items that matter and phrase them positively (for example, “plain white background” instead of a long list of “no stadium, no grass…”).

Am I charged for IMAGE_OTHER?

The provider states in finishMessage that these requests are not charged. To confirm whether a request was billed, check the call logs in the APIYI console.

Still stuck? Contact support

Please include the following so we can help:

Model name and token group;
The complete response (at least finishReason, finishMessage, and responseId) and the request ID;
Time of occurrence (with time zone);
The redacted prompt, and the failure rate you observed.

Never send a complete API key. Redact the key before sharing screenshots or logs.

WeCom Support

Scan the QR code, or click this card to contact support directly.

Email Support

Support: [email protected]We recommend including “IMAGE_OTHER” and the model name in the subject.

Why Does the Gemini Image API Return NO_IMAGE?

Missing images caused by unclear prompt intent, and how to fix them

Why Does Gemini Image Return blockReason: OTHER?

Locating a reference image blocked before generation, and preprocessing advice

Nano Banana image generation failures

Common causes including safety, watermark removal, well-known IP, and minors

Gemini Image API Error Handling

The full response-checking order and user-friendly error messages

Basics

Basic API

Image API (Official)

Video API (Official)

Multimodal Understanding API

Text Generation

Audio API (Official)

Retrieval & Safety

Why Does Gemini Image Return IMAGE_OTHER?

Short answer

How to recognize it

A tested case

How to locate the trigger

Recommendations

FAQ

Still stuck? Contact support

WeCom Support

Email Support

Why Does the Gemini Image API Return NO_IMAGE?

Why Does Gemini Image Return blockReason: OTHER?

Nano Banana image generation failures

Gemini Image API Error Handling

​Short answer

​How to recognize it

​A tested case

​How to locate the trigger

​Recommendations

​FAQ

​Still stuck? Contact support

WeCom Support

Email Support

​Related documentation

Why Does the Gemini Image API Return NO_IMAGE?

Why Does Gemini Image Return blockReason: OTHER?

Nano Banana image generation failures

Gemini Image API Error Handling

Short answer

How to recognize it

A tested case

How to locate the trigger

Recommendations

FAQ

Still stuck? Contact support

Related documentation