# Image to z-depth **URL:** \ **Category:** Flame Questions\ **Tags:** action, batch\ **Created:** [June 4, 2023, 10:02am UTC](https://forum.logik.tv/t/image-to-z-depth/8517 "2023-06-04T10:02:55Z")\ **Posts on this page:** 16\ **Page:** 1
**Author:** ![yola](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/yola/32/64_2.png) [@yola](https://forum.logik.tv/u/yola)\ **Post date:** [June 4, 2023, 10:02am UTC](https://forum.logik.tv/t/image-to-z-depth/8517/1 "2023-06-04T10:02:55Z")
hello. if i wanted to use a camera depth oh field but i don’t have a z layer. how could i transform a normal rampe into z information? i have a feeling there was something like that in nuke, but in Flame? (old flame 2016) without all funcy AI additions. Or maybe an outside solution to creat a fake zdepth ? ---
**Author:** ![RufusBlackwell](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/rufusblackwell/32/422_2.png) [@RufusBlackwell](https://forum.logik.tv/u/RufusBlackwell)\ **Post date:** [June 4, 2023, 12:21pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/2 "2023-06-04T12:21:22Z")
You can use Runway ML to create a z-depth pass from a live action clip. I actually haven’t used that particular tool, but all the other tools are v good. If you don’t have a Runway account I’ll happily run it through for you and do a test, (if you’re able to share the clip). ---
**Author:** ![Sinan](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/sinan/32/155_2.png) [@Sinan](https://forum.logik.tv/u/Sinan)\ **Post date:** [June 4, 2023, 12:51pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/3 "2023-06-04T12:51:55Z")
If you have a normal map, you might be able get a depth map out of it using action together with the depth map normalizer matchbox. ---
**Author:** ![randy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/randy/32/6122_2.png) [@randy](https://forum.logik.tv/u/randy)\ **Post date:** [June 4, 2023, 1:21pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/4 "2023-06-04T13:21:21Z")
How many shots? Want me to run a couple through a new version of Flame’s ML Depth Extract for ya? ---
**Author:** ![paul\_round](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/paul_round/32/389_2.png) [@paul\_round](https://forum.logik.tv/u/paul_round)\ **Post date:** [June 5, 2023, 2:02pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/10 "2023-06-05T14:02:58Z")
> [@randy](#): > > How many shots? Want me to run a couple through a new version of Flame’s ML Depth Extract for ya? Flames ML depth map really helped me on House of the Dragon. ---
**Author:** ![allklier](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/allklier/32/4309_2.png) [@allklier](https://forum.logik.tv/u/allklier)\ **Post date:** [June 5, 2023, 3:19pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/11 "2023-06-05T15:19:39Z")
I just used Flame’s ML depth on a project and it worked reasonably well. Have to mind the parameters a bit, and watch the matte. I had to roto an area where the matte was weak, so I could keep the parameters in the sweet spot for the rest. But definitely solid tool in the right situation. ---
**Author:** ![andy\_dill](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/andy_dill/32/15475_2.png) [@andy\_dill](https://forum.logik.tv/u/andy_dill)\ **Post date:** [June 5, 2023, 4:47pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/12 "2023-06-05T16:47:35Z")
Blue channel on a normal map is the facing ratio, which could be used as a hacky depth map. ---
**Author:** ![randy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/randy/32/6122_2.png) [@randy](https://forum.logik.tv/u/randy)\ **Post date:** [June 5, 2023, 7:54pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/13 "2023-06-05T19:54:09Z")
Facing Ratio. Sounds like dope band name. ---
**Author:** ![yola](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/yola/32/64_2.png) [@yola](https://forum.logik.tv/u/yola)\ **Post date:** [June 5, 2023, 9:06pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/14 "2023-06-05T21:06:13Z")
I have 2 shots. I’ve tryed Runway ML in free mode, but its not precise enough. Do you think I could send you those shots @randy for a quick test please? ---
**Author:** ![yola](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/yola/32/64_2.png) [@yola](https://forum.logik.tv/u/yola)\ **Post date:** [June 5, 2023, 9:08pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/15 "2023-06-05T21:08:00Z")
it’s not a 3D shot. it’s a dron shot where I would like to loose a real life look and push it to a tilt shift mockup look ---
**Author:** ![randy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/randy/32/6122_2.png) [@randy](https://forum.logik.tv/u/randy)\ **Post date:** [June 5, 2023, 9:12pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/16 "2023-06-05T21:12:23Z")
Sure. Send me a link ---
**Author:** ![yola](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/yola/32/64_2.png) [@yola](https://forum.logik.tv/u/yola)\ **Post date:** [June 6, 2023, 4:54pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/17 "2023-06-06T16:54:21Z")
thank you so much @randy 1 shot is here [Frame.io](https://f.io/M6a9zcAR) 2 shot is here [Frame.io](https://f.io/0uYAB6Wi) - I’m not sure how it can work for this little ladder 3 - if there is a problem with the shot 2. maybe this one would be better ? - [Frame.io](https://f.io/BVWbsWj_) ---
**Author:** ![yola](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/yola/32/64_2.png) [@yola](https://forum.logik.tv/u/yola)\ **Post date:** [June 8, 2023, 9:56am UTC](https://forum.logik.tv/t/image-to-z-depth/8517/18 "2023-06-08T09:56:01Z")
i’ve tested it with [depth scanner](https://aescripts.com/depth-scanner/?aff=35) and I have a feeling it’s not possible to have a clear z from shot 2 and 3 - the difference between BG and the chimney is too big. I should clean the chimney, do the z, add the chimney 🤢 🤕 ---
**Author:** ![Ally\_Burnett](https://avatars.discourse-cdn.com/v4/letter/a/ba8739/32.png) [@Ally\_Burnett](https://forum.logik.tv/u/Ally_Burnett)\ **Post date:** [June 8, 2023, 10:01am UTC](https://forum.logik.tv/t/image-to-z-depth/8517/19 "2023-06-08T10:01:56Z")
I had a similar issue recently where I was adding fog to a city. ML got me tantalisingly close but in the end I had to create the depth map manually using lots of roto. I’d imagine for a DoF effect the map would have to be even more accurate. ---
**Author:** ![allklier](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/allklier/32/4309_2.png) [@allklier](https://forum.logik.tv/u/allklier)\ **Post date:** [June 8, 2023, 12:03pm UTC](https://forum.logik.tv/t/image-to-z-depth/8517/20 "2023-06-08T12:03:59Z")
Out of curiousity… Realizing you’re looking for a Flame solution, but are possibly considering Runway ML to process this externally - are some of those situations a case where CopyCat could help? Manually do a few frames and train a data set. Seems like a good use case where the fully automated tools have failed. Also, if you had multiple z-depth tools, any use to averaging their mattes rather than picking just one? Or combining them by zones where each one does better? ---
**Author:** ![julioleon](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.logik.tv/julioleon/32/14482_2.png) [@julioleon](https://forum.logik.tv/u/julioleon)\ **Post date:** [June 9, 2023, 4:20am UTC](https://forum.logik.tv/t/image-to-z-depth/8517/21 "2023-06-09T04:20:16Z")
> [@randy](#): > > Facing Ratio. Sounds like dope band name. Ratiohead