adishj

no worries at all. compared to some other comments in this thread, I didn't find your tone snarky at all. I appreciate your engaging with the conversation and the thread :)

Hey there, this is just the output from the Rough Cut tile. Right now each tile in Mosaic represents a modular and functional edit to the video. So after you've got your Rough Cut, given all your footage, there are other tiles which you can then use to add transitions, motion graphics, background music, etc.

That being said, the coolest part with this Rough Cut was that it decided to stand in the footage of the kite to creatively imply the freefall portion of the skydive (because we aren't able to record while we're jumping out of a plane). This ability for it to creatively decided to imply the jump because of the limited footage is what I wanted to get across here.

curious how does this compare to something like Memories.ai when it comes to video in particular?

Hey there! We already support XML exports to DaVinci Resolve, Final Cut Pro, and Premiere Pro!

We also do transcoding of all uploaded files to lower-res proxies, which can be re-linked when brought back into a more traditional NLE.

good point — we could enable these more granular-level knobs for users if it seems to be something people want

since we're building on top of LLMs which are by nature probabilistic, you won't produce the exact same frame-level cut each time, but of course there is still determinism in the expected outputs

for example, if you have a workflow setup to create 5 clips from a podcast and add b-rolls and captions and reframe to a few different aspect ratios, any time you invoke this workflow (regardless of which podcast episode you're providing as input), you'll get 5 clips back that have b-rolls, captions, and are reframed to a few different aspect ratios

however, which clips are selected, what b-rolls are generated, where they're placed — this is all non-deterministic

you can guide the agent via prompting the tiles individually, but that's still just an input into a non-deterministic machine

what I mean here is that processing / analyzing a beefy file format like video will take longer than processing text input

same with returning that back to the user as manipulated output (text / code generation is much more rapid than rendering a video)

thanks dan

thanks for the kind word and for being an early supporter!

thanks for the kind word and for being an early supporter!

Haven't chatted with them but their platform looks interesting!

Video is hard, but it's also a fun modality which presents some interesting challenges. And is where content is converging towards.

next dropbox? lets go!

loom is focused on screen recordings / demos

great to hear — I'd recommend using the clips tile to create clips, but you can also use the rough cut tile to help edit down the raw footage for the long-form

hey, thanks for sharing about your documentary series. would love to check it out if you don't mind linking it!

we don't yet support that volume of footage (1TB), however if you'd like to try this at a smaller scale, you can already do this today with the Rough Cut tile — simply prompt it for the moments that you're interested in (it can take visual cues, auditory cues, timestamp cues, script cues) and it will create an initial rough cut or assembly edit for you.

I'd also recommend checking out the new Motion Graphics tile we added for animations. You can also single-point generate motion graphics using the utility on the bottom right of the timeline. Let me know if you have any questions on that.

yes! you can upload as many videos as you want (file limits currently are at 20GB and 90 minutes, per file). then I'd recommend using either the Rough Cut tile or the Montage tile to stitch them all together. In those tiles, you can prompt particular visual cues in terms of how you want the videos to be combined. Let me know if any questions.

looks like I got a network error

i agree, things are a bit too kind. give me some more feedback.

there is some friction even in downloading a new app

if our goal is to bring more people into the fold, minimizing the steps for them to start editing is something we want to optimize for

that being said, being on the browser presents its own set of challenges, many of which are rightfully mentioned in this thread

we've done a ton of work to optimize the uploads / downloads / transcoding of videos to handle beefy files using proxies, and also allow you to XML export back to traditional editing tools that can link back to your "heavy" media, but I hear you and I think anything running locally on device is just going to feel faster

it does present its own set of challenges, but something we've thought about

thank you so much for the kind word!

if you have an example you could share i'd be very curious on what you mean.

hey, thanks for the comment!

we've actually found that multimodal models are surprisingly good at maintaining temporal context as well

that being said, there's also a bunch of additional processing using more traditional CV / audio analysis we do to extract this information out as well (both frame-level and temporal) in your video understanding

for example, with the mean-motion analysis — you can see how subjects move over a period of time, which can help determine where important things are happening in the video, which ultimately can lead to better placements of edits.

thank you! let us know if you have any feedback!

thank you! let us know if you have any feedback!

that's super interesting — what kind of things have you done with remotion and Claude Code?

they're very powerful, when you put them together, it almost feels like Cursor for Video Editing

naming is hard

our original name was Frame, only to realize that frame.io existed already.

we brainstormed names for a while and had several notes full of possible names

mosaic is one which stood out to us because it not only represents artwork, but also the tiles (nodes) in the canvas come together to form your mosaic — we thought that was a fitting name

thanks for the comment, thats exactly right

we're using a mix of out-of-the-box multimodal AI capability + traditional audio / video analysis techniques as part of our video understanding pipeline, all of which become context for the agent to use during its editing process

thank you! chatoctopus looks pretty cool, I'm trying it out right now!

how did you find the chat-first interface to work out for video? what we found is that the response times can be so long that the chat UX breaks down a bit. how are you thinking about this?

thank you! if you get a chance to try it, let me know if you have any feedback