Google Flow Automation
Stop clicking Generate 50 times in Google Flow.
What it does
Stop clicking through Google Flow one prompt at a time. This extension batch-runs your prompts — paste a list or import a file, choose Text-to-Image, Image-to-Image, Text-to-Video, or Frames-to-Video, and it queues the batch, tracks progress, and auto-downloads every result with clean filenames. Built for creators and editors generating at volume, no API keys or code needed. Runs inside your own signed-in Google Flow session, working directly on the page you already have open.
Flow Automation is a no-code browser extension for non-technical creators to batch-run Google Flow video prompts: import spreadsheets, queue Text to Video, Frames to Video, and Ingredients to Video jobs, retry failures, and auto-download results in your own browser session.
Paste your shot list, pick a workflow, and the extension queues, paces, retries, and downloads every generation — inside the Flow session you already have open. No API keys, no scripts, no setup. Every Flow creation mode that benefits from batching, driven from the same queue. Queue written prompts and let Flow render each one while you keep editing. Animate between a start and end frame. Upload frame sets once; the extension pairs them per row. Feed reference images — characters, locations, styles — and batch prompts against them. Pacing, retries, naming, and filing are where batches eat your evening. That is what the extension takes over. Bring prompts from Sheets…from deepakthapa.dev
Does the same job
all alternatives →
Higgsfield Automation12d ago · deepakthapa.dev · ▲5Stop clicking Generate 50 times. Batch it instead.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com