PinnedInGoogle Cloud - CommunitybyLaurent Picard·Feb 26Detecting and Editing Visual Objects with GeminiA practical guide to identifying, restoring, and transforming elements within your images
PinnedInGoogle Cloud - CommunitybyLaurent Picard·Sep 23, 2025Generating Consistent Imagery with Gemini Nano Banana 🍌A practical guide to building a prompt-based generation pipeline for your image library
PinnedInGoogle Cloud - CommunitybyLaurent Picard·Aug 29, 2025Unlocking Multimodal Video Transcription with Gemini — Part 1: 🔥 ChallengeExplore how to transcribe videos with detailed speaker identification in a single prompt
PinnedInGoogle Cloud - CommunitybyLaurent Picard·Jul 4, 2024Counting Gemini text tokens locally🧩 The Vertex AI SDK for Python now offers local tokenization to calculate the number of tokens in your text input.A response icon7A response icon7
PinnedInGoogle Cloud - CommunitybyLaurent Picard·Jun 16, 2023Moderating text with the Natural Language APIThe Natural Language API lets you extract information from text using Google machine learning and now also supports text moderation.
InGoogle Cloud - CommunitybyLaurent Picard·Nov 20, 2025🍌 Testing Gemini 3 Pro ImageNano Banana Pro is the new state-of-the-art image generation/editing model
InGoogle Cloud - CommunitybyLaurent Picard·Sep 6, 2025Unlocking Multimodal Video Transcription with Gemini — Part 8: 🏁 ConclusionExplore how to transcribe videos with detailed speaker identification in a single prompt
InGoogle Cloud - CommunitybyLaurent Picard·Sep 5, 2025Unlocking Multimodal Video Transcription with Gemini — Part 7: ⚖️ Analysis, Tips & OptimizationsExplore how to transcribe videos with detailed speaker identification in a single prompt
InGoogle Cloud - CommunitybyLaurent Picard·Sep 5, 2025Unlocking Multimodal Video Transcription with Gemini — Part 6: ✅ Challenge CompleteExplore how to transcribe videos with detailed speaker identification in a single prompt
InGoogle Cloud - CommunitybyLaurent Picard·Sep 5, 2025Unlocking Multimodal Video Transcription with Gemini — Part 5: 🚀 FinalizationExplore how to transcribe videos with detailed speaker identification in a single prompt