Troubleshooting of Google Gemini: Difference between revisions

Jump to navigation Jump to search

Troubleshooting of Google Gemini (edit)

Revision as of 18:15, 23 September 2025

5,954 bytes added ,  23 September 2025
m
→‎How to resolve: Gemini Text-to-Image: 16:9 Aspect Ratio Not Working, Always Generates 1:1 Images
(Created page with " {{Draft}} == Troubleshooting of Google Gemini API == === How to fix "Request contains an invalid argument" === Error message <pre> 無法提交提示 錯誤訊息：「Request contains an invalid argument.」 狀態：400 錯誤代碼：3 要求 ID：xxx </pre> Workaround solution: * If you upload a video file for API analysis, you might consider shortening the video duration, for example, using ffmpeg to reduce an hour-long video to half its length. This will help...")
 
 
(16 intermediate revisions by the same user not shown)
Line 2: Line 2:
{{Draft}}
{{Draft}}


== Troubleshooting of Google Gemini API ==
== Troubleshooting of Google Gemini ==
=== How to fix "Request contains an invalid argument" ===
=== How to fix "Request contains an invalid argument" ===
Error message
'''Error message'''
<pre>
<pre>
無法提交提示
無法提交提示
Line 14: Line 14:
</pre>
</pre>


Workaround solution:  
'''Model Affected''': gemini-1.5-pro-preview-0409 or gemini-1.5-flash-preview-0514
 
'''Workaround solution:'''
* If you upload a video file for API analysis, you might consider shortening the video duration, for example, using ffmpeg to reduce an hour-long video to half its length. This will help reduce the input token length.
* If you upload a video file for API analysis, you might consider shortening the video duration, for example, using ffmpeg to reduce an hour-long video to half its length. This will help reduce the input token length.
=== How to fix: The File XXX is not in an ACTIVE state and usage is not allowed ===
After upload the video to  Gemini API
'''Error message'''
<pre>
Processing video...
$response is: Array
(
    [error] => Array
        (
            [code] => 400
            [message] => The File XXX is not in an ACTIVE state and usage is not allowed.
            [status] => FAILED_PRECONDITION
        )
)
</pre>
Solution
* "You need to check its status and wait until it becomes ACTIVE" [https://stackoverflow.com/questions/79033795/google-generativeai-unable-to-load-video-files python - Google GenerativeAI unable to load video files - Stack Overflow]
=== How to fix: Invalid or unsupported file uri ===
After upload the video, when I tried to analysis the video by the Gemini API
'''Error message'''
<pre>
Uncaught Exception: API request failed with HTTP code 400
Response: {
  "error": {
    "code": 400,
    "message": "Invalid or unsupported file uri: ZGFkYjY0Njg0MDIyYmM3ZDc2YmIwY2Q5YzI4ZTllYzBhN2E1OGMzNDk2YWVkMmVlZWY0NDhlY2FhZGVjZTM1Ng==",
    "status": "INVALID_ARGUMENT"
  }
}
</pre>
Solution
* Please verify the format of your file URL. It should follow this pattern:
`https://generativelanguage.googleapis.com/v1beta/files/XXXXX`
=== How to fix: Invalid JSON payload received. Unknown name "responseSchema" at 'generation_config' ===
After upload the video, when I tried to analysis the video by the Gemini API
'''Error message'''
<pre>
{
  "error": {
    "code": 400,
    "message": "Invalid JSON payload received. Unknown name \"responseSchema\" at 'generation_config': Proto field is not repeating, cannot start list.",
    "status": "INVALID_ARGUMENT",
    "details": [
      {
        "@type": "type.googleapis.com/google.rpc.BadRequest",
        "fieldViolations": [
          {
            "field": "generation_config",
            "description": "Invalid JSON payload received. Unknown name \"responseSchema\" at 'generation_config': Proto field is not repeating, cannot start list."
          }
        ]
      }
    ]
  }
}
</pre>
Solution
* The parameter "responseSchema" could not be an empty array
=== Resolving "Model not found for API version v1beta" Error with Gemini API ===
'''Error Details'''
<pre>
{
  "error" : {
    "code" : 404,
    "message" : "models/gemini-2.0-flash-exp-image is not found for API version v1beta, or is not supported for generateContent. Call ListModels to see the list of available models and their supported methods.",
    "status" : "NOT_FOUND"
  }
}
</pre>
'''Problematic Command'''
<pre>
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp-image:generateContent" \
  -H 'Content-Type: application/json' \
  -H 'X-goog-api-key: GEMINI_API_KEY' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Generate an image of a cute baby turtle in a 3d digital art style"
          }
        ]
      }
    ]
  }'
</pre>
'''Affected Model:''' gemini-2.0-flash-exp-image-generation
'''Troubleshooting Steps:'''
<pre>
# Set your API key
API_KEY="YOUR_API_KEY_HERE"
echo "Retrieving available Gemini models..."
curl -s "https://generativelanguage.googleapis.com/v1beta/models" \
  -H "X-goog-api-key: $API_KEY" | jq -r '.models[] | select(.name | contains("gemini")) | {name: .name, supportedGenerationMethods: .supportedGenerationMethods}'
</pre>
Expected Output
<pre>
{
  "name": "models/gemini-2.0-flash-exp-image-generation",
  "supportedGenerationMethods": [
    "generateContent",
    "countTokens",
    "bidiGenerateContent"
  ]
}
</pre>
Issue Identified: Incorrect model name used. The valid model name is "models/gemini-2.0-flash-exp-image-generation", not "models/gemini-2.0-flash-exp-image"
Fixed Command
<pre>
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp-image-generation:generateContent" \
  -H 'Content-Type: application/json' \
  -H 'X-goog-api-key: GEMINI_API_KEY' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Generate an image of a cute baby turtle in a 3d digital art style"
          }
        ]
      }
    ]
  }'
</pre>
=== How to resolve: Gemini Text-to-Image: 16:9 Aspect Ratio Not Working, Always Generates 1:1 Images ===
'''Question:'''
Has anyone experienced issues with Gemini's text-to-image function where you specify 16:9 aspect ratio but keep getting 1:1 square images?
'''Problematic prompt''' for Models: 2.5 Pro & 2.5 Flash
<pre>
Generate a cute young turtle, 3D style
Image size 16:9
</pre>
<pre>
Generate a cute young turtle, 3D style
landscape orientation, wide format
</pre>
'''Answer:'''
A Google Product Expert acknowledged this issue in official forums, describing it as a "known limitation." However, no timeline has been provided for when the functionality might be restored.<ref>Gemini Nano Banana users report 1:1 aspect ratio lock on image generation https://piunikaweb.com/2025/09/11/gemini-image-generator-aspect-ratio-problems/</ref><ref>What happened to imagegen quality?? - Gemini Apps Community https://support.google.com/gemini/thread/372012804?hl=en&msgid=372013964</ref>
I've actually tested both Gemini 2.5 Pro and 2.5 Flash models, specifying image dimensions in the prompt (Image size: 16:9) or generating landscape orientation (landscape orientation, wide format), and both have the same problem. If you can make API calls, you might try using the API to call other models.
If you want an online solution that works, you can try Google Whisk directly: https://labs.google/fx/tools/whisk/
The interface allows you to directly set three aspect ratios: square 1:1, portrait 9:16, and landscape 16:9.
== Further reading ==
* [https://ai.google.dev/gemini-api/docs/troubleshooting?hl=zh-tw 疑難排解指南  |  Google AI for Developers  |  Google for Developers]


[[Category:Tools]] [[Category:Google]]
[[Category:Tools]] [[Category:Google]]
[[Category:Generative AI]]
[[Category:Generative AI]]
Retrieved from "https://wiki.planetoid.info/index.php/Special:MobileDiff/24816...26023"

Navigation menu