Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • I make motorcycle travel videos for YouTube, and the bulk of where my time goes in the preparation of a timeline: chronologically cutting the highlights, synchronising dual camera footage. If Claude + Davinci Resolve will enable me to cut this time slightly, even if it's 10%, it's a welcome change. Ever since I made the jump from Premiere Pro, I've been positively surprised with how good Resolve is. Excited to try this out!
  • I thought DaVinci Resolve could automatically sync camera footage for a few years now. I did it about 4 years ago.
  • As an anecdote, I recently needed to colour-grade some short footage for personal purposes. My workflow at the time was to essentially ask an LLM for guidance on how to use DaVinci Resolve to perform the task, step by step. I would make an adjustment, take a screenshot of the controls and the result, and repeat that process a handful of times, eventually ending up with a pretty nice result.

    I can definitely see the utility of something like this for cases where a media budget just wouldn't have existed in the first place.

  • Have anyone tried using this as a substitute for CaptureOne/Lightroom? Any experiences? I'm aware it's a quite new feature added to the suite, but would love to one day stop paying the pricey subscriptions the other two alternatives demand
  • I spent a little while trying. My knowledge of lightroom didn't really carry over. I couldn't work out how to do things like masks. I'm sure if i spent longer and watched some tutorials I'd get further but I decided to just let the photo mode cook a little longer before I try to switch over.
  • I tried and as a individual (single/one at a time) image editor is it fantastic, beats Lightroom by a mile and the node editor gives me the ability to "emulate" panels from CaptureOne (and OFX plugin support means I can just LLM my own if I need).

    Library management is where Lightroom (and honestly CaptureOne) still wins, I couldn't find a good way to manage a 100k photo library.

    I created one project and tried importing the whole library, but it took more than 8 hours and didn't make meaningful progress (~10%?) so I stopped (compared to 15hr for the whole thing in Lightroom).

    I also did a project for about 1K photos and while the import worked, the library management itself was lacking. I could not find ways to do image stacks for bursts, group by metadata, etc. The obvious filters are there, but I think it needs more work.

  • As a free user for several years, the MCP integration was exactly something I was looking forward to for getting a rough cut!

    Sadly, things are not quite as straightforward for non-Studio. For one, you need to be a paying customer to get access to the new feature. Moreover, a community-based solution [1], which previously worked for all users, have now artificial limitation in implementing automation for Free users.

    Quite a shame really but maybe it will trickle down over time (like expanding export resolution support). Regardless, a much more open implementation than Adobe, who'd like you to pay for yet another chat window.

    [1] https://github.com/samuelgursky/davinci-resolve-mcp#free-edi...

  • I'm all for AI features here. The software is so feature packed and conplex, that after years of usage I still need to search and look up tutorial videos every single time I edit something.

    How to ease key frames, how to fix my HDR captured footage for SDR, how to export the best quality video, how to burn in subtitles with word highlights, how to fix my audio aaand so on.

    Either the AI will show me the particular feature and setting or a YouTube tutorial will. I think the AI might be faster and easier in this scenario.

  •   pacman -S davinci-resolve-free
    
    Would be SO sick! I feel like there is such a big appetite for it and people would do the free labor to support it. I wonder what keeps it in this horrible purgatory of install hell.
  • That's the experience on CachyOS. They package it up for their users and updates just work.

        pacman -S davinci-resolve
  • This is a good place to share that MakeResolveDeb makes installing Davinci Resolve very easy on Ubuntu/Mint/Debian

    Way more people should know about this solution.

    https://www.danieltufvesson.com/makeresolvedeb

  • This aur package [1] works well for me. Unfortunately the new maintainer removed the automatic download and you need to manually download the zip via the form on Blackmagic's website (however not even the email is validated).

    1: https://aur.archlinux.org/packages/davinci-resolve

  • I install, run and update via this container script [1] on Arch. It works very well.

    [1] https://github.com/zelikos/davincibox

    by dtf
  • The Claude connector is a nice idea, but there are lots of Python APIs missing in Resolve. Even simple interactions like moving a clip 3 seconds in the timeline will not work with the MCP. I just tried it, and got only the message: "Resolve's scripting API also has no way to reposition an existing timeline item".
  • I've had Claude Code drive DaVinci Resolve before in three ways: - Generate .otio files that are imported. Unfortunately, .otio doesn't fully support everything Resolve can do. - Resolve has a scripting engine. Claude can write Lua scripts, then execute the script (through UI Automation) - Computer Use. It's quite token intense, but it works.

    I didn't try it, but for the paid version, someone also built a MCP server based on the scripting engine.

    I'm programmatically adding analysis to sim racing lap guides, therefore my flow is probably different from the usual editing flow, but I have to say I found Claude Code + Opus to be quite capable of making edits with computer use.

    by cnj
  • > I'm programmatically adding analysis to sim racing lap guides

    Yosh is that you?

  • I used IntelliScript a lot. I give Claude a subtitle export, ask it to cut it and import the cut subtitle track with IntelliScript. Resolve then creates a video version that’s cut based on the subtitle changes

    Works pretty well!

  • I spent a few tokens last year trying to create a Python lib for native (undocumented) Resolve files. I was making progress, but it was slow (I ended up scripting Resolve in different ways). I imagine that current models could reverse-engineer the native file format relatively quickly.
  • I helped my girlfriend use the MCP server as she had a project where all the media files had been moved to a new source location, and using Codex, it managed to hunt down all the files and stitch it all back together. Ended up saving quite a lot of manual boring labour, and was quite cool to see it work in real time:)
  • I had AI write a program to edit with resolve. It does transcription, looks at the transcript and decides where to make cuts. If does a decent job and saves me a bunch of time.
  • I really wish the Linux version supported h264 video and AAC audio. These are extremely disk space efficient codecs and even on 12 year old hardware you can edit 1080p videos without any CPU bound lag. Having to re-encode your source material and re-encode your exports is too tedious to do in practice.

    On Windows I edited 100+ podcasts with Resolve and it's so good. Video editing on Linux for the last 9 months with Kdenlive has been killing me (vs Camtasia or Resolve on Windows).

  • H.264 isn't efficient though. AV1 (and even H.265) are anywhere from 20-50% more space efficient for the same visual quality.

    AAC vs Opus is a little bit more debated, but on average should outperform AAC.

  • H.264 is supported on Linux in DR Studio, it’s just not in the free version.
  • A few weeks ago I used claude to reverse engineer the linux version of resolve to add support for AAC media. The patch is here, and it works great:

    https://github.com/josephg/resolve-aacfix

    AAC streams are decoded and sent to ffmpeg.

  • Not even BMD is safe from the agent apocalypse:

    > DaVinci Resolve 21.1 now supports integration with AI assistants such as Claude, Claude Code and ChatGPT Codex, allowing customers to analyze projects, organize media, adjust settings and batch render using everyday conversational language. Customers can ask their AI assistant to create highlight edits from long form video, remove unwanted clips and render deliverables, so they can spend more time being creative rather than getting bogged down in repetitive tasks.

  • They'd rather add agentic AI support instead of adding proper codec support on the free Linux version (which is already supported on Windows).

    smh

  • Furthermore, can one use custom API endpoint or is it forced use of corpo AI?
  • LOVE this. Game changer in capability and it'd kill Resolve if they didn't do it.
  • They've added it as people are opting for stuff like Palmier Pro, FableCut, and likes, which can edit videos using AI.
  • No no, if you've ever spent serious time editing, it's a big deal -- if they pull this off correctly, it will be a game changer. Editing has so much grunt work, where you just have to spending time organizing, collecting files, renaming things, finding missing files... Just tedious project management stuff that is excellent for an AI to do.
    by aizk