From 4553455c69ada023313a90f0e2372886cc188d61 Mon Sep 17 00:00:00 2001 From: Nikhileswar94 Date: Wed, 12 Nov 2025 14:04:44 +0530 Subject: [PATCH] Fix typo in video generation documentation. The input_reference parameter only supports images and not videos. Using video as an input_reference throws openai.BadRequestError: Error code: 400 - {'error': {'message': 'Video inpaint is not available for your organization.', 'type': 'invalid_request_error', 'param': None, 'code': None}} While OpenAI documentation clearly mentions Images https://platform.openai.com/docs/guides/video-generation#use-image-references the Azure OpenAI Documentation mentions that images/ videos can be used. --- articles/ai-foundry/openai/concepts/video-generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/articles/ai-foundry/openai/concepts/video-generation.md b/articles/ai-foundry/openai/concepts/video-generation.md index eae1be608b..2bf55bdea7 100644 --- a/articles/ai-foundry/openai/concepts/video-generation.md +++ b/articles/ai-foundry/openai/concepts/video-generation.md @@ -465,7 +465,7 @@ Saved video.mp4 ### Video generation from reference source -The `input_refernce` parameter allows you to transform existing images and videos using Sora 2. The resolution of the source image/video and final video must match. Supported values are `720x1280`, `1280x720`, `1024x1792`, and `1792x1024`. +The `input_refernce` parameter allows you to transform existing images using Sora 2. The resolution of the source image and final video must match. Supported values are `720x1280`, `1280x720`, `1024x1792`, and `1792x1024`. # [Microsoft Entra ID](#tab/python-entra)