Loading...
> >

Remixing your art with AI

1…1314161819…22

Comments

  • ArtiniArtini Posts: 9,513
    edited November 2023

    Diomede said:

    Stable Diffusion with ControlNet has a menu for loading rigged FBX, JSON, and similar models.  But my custom toon Marx brothers do not appear to transfer correctly from Carrara FBX to Stable Diffusion.  crying

     

    Have you tried to transfer your Carrara FBX to Blender

    and then export from Blender as FBX or any other format, that ControlNet accepts.

    I am going via Blender when I need to export FBX models from Shape-E to Daz Studio, for example.

    Awesome work and your thoughts about you experiments with Stable Diffusion.

    I am also doing my experiments with AI for the same reasons.

     

    Post edited by Artini on
  • ArtiniArtini Posts: 9,513

    WendyLuvsCatz said:

    A video using my trained Textual Inversion Embedding

    a recent pic of me for comparisson

    I added my embedding to try, the words to trigger it are myself, AND wendyvain,

    beginning and end of prompt

    it will sometimes work with just wendyvain in the prompt but for specific use something like "myself, a woman doing such and such or wearing such and such etc, wendyvain" should trigger it

    it was trained on Dreamshaper7 specifically but I think any SD v1.5 model should work

    Nice work, Wendy.

    I have not tried to make my own Textual Inversion Embedding, yet.

     

  • DiomedeDiomede Posts: 15,188

    WendyLuvsCatz said:

    A video using my trained Textual Inversion Embedding

    a recent pic of me for comparisson

    I added my embedding to try, the words to trigger it are myself, AND wendyvain,

    beginning and end of prompt

    it will sometimes work with just wendyvain in the prompt but for specific use something like "myself, a woman doing such and such or wearing such and such etc, wendyvain" should trigger it

    it was trained on Dreamshaper7 specifically but I think any SD v1.5 model should work

    That is awe-inspiring!  Well done.  I just did my first masking in image2image, and my first upscale.  So I am still just taking my first steps.  Unfortunately, I continue to get conflicts among extensions related to animation.  The most recent conflict was with deforum.  

  • DiomedeDiomede Posts: 15,188

    Artini said:

    Diomede said:

    Stable Diffusion with ControlNet has a menu for loading rigged FBX, JSON, and similar models.  But my custom toon Marx brothers do not appear to transfer correctly from Carrara FBX to Stable Diffusion.  crying

     

    Have you tried to transfer your Carrara FBX to Blender

    and then export from Blender as FBX or any other format, that ControlNet accepts.

    I am going via Blender when I need to export FBX models from Shape-E to Daz Studio, for example.

    Awesome work and your thoughts about you experiments with Stable Diffusion.

    I am also doing my experiments with AI for the same reasons.

    Thanks for the suggestion.  I tried for a similar model some time ago but have forgotten the details.  I think I had to look up FBX versions on the web and use a conversion, but I don't remember for sure.  Given how crude my toon figures are (intentionally), I would probably be better off just transferring the mesh to Blender and rigging there.  I have successfully done something similar with Mixamo.

  • WendyLuvsCatzWendyLuvsCatz Posts: 38,312
    edited November 2023

    well I have yet to try FBX with ControlNet, Deforum is fussier about ControlNet too, a few that work fine with Image2Image won't work for me in Deforum

    my build being in a VOC container is different from before when I use A1111 standalone so again I am not much help

    I have serious conflicts due to my hardware set up with my iGPU

    Fooocus has now decided to stop working too surprise

     

    a Video of my AI likeness

    Post edited by WendyLuvsCatz on
  • ArtiniArtini Posts: 9,513

    The details in the video are amazing, Wendy.

    I have found tutorials for making animations in ComfyUI.

    Just need to find some time for make it.

     

  • WendyLuvsCatzWendyLuvsCatz Posts: 38,312

    Artini said:

    The details in the video are amazing, Wendy.

    I have found tutorials for making animations in ComfyUI.

    Just need to find some time for make it.

     

    thx

    Nodes terrify me so nothing comfy about that UI surprise 

  • Cris PalominoCris Palomino Posts: 11,507

    WendyLuvsCatz said:

    A video using my trained Textual Inversion Embedding

    a recent pic of me for comparisson

    I added my embedding to try, the words to trigger it are myself, AND wendyvain,

    beginning and end of prompt

    it will sometimes work with just wendyvain in the prompt but for specific use something like "myself, a woman doing such and such or wearing such and such etc, wendyvain" should trigger it

    it was trained on Dreamshaper7 specifically but I think any SD v1.5 model should work

    this was fun to watch and listen to, Wendy. Well-done! 

  • WendyLuvsCatzWendyLuvsCatz Posts: 38,312

    thx Cris

  • ArtiniArtini Posts: 9,513
    edited November 2023

    Trying to figure out, how to recreate in Daz Studio something, like this...

    image

    cows06.jpg
    1024 x 1024 - 172K
    Post edited by Artini on
  • ArtiniArtini Posts: 9,513
    edited November 2023

    ... and of course The Pigs

    image

    pigs04.jpg
    1024 x 1024 - 262K
    Post edited by Artini on
  • ArtiniArtini Posts: 9,513
    edited November 2023

    Could not forget about The Cats...

    image

    cats05.jpg
    1024 x 1024 - 242K
    Post edited by Artini on
  • WendyLuvsCatzWendyLuvsCatz Posts: 38,312
    edited November 2023

    DAZ Filament Render reimagined with Stable Diffusion

    Music is also AI created using Sumo Chirp

    you can see the 2 Filament renders used as shorts on my Madcatlady channel if curious 

    https://youtube.com/shorts/V5uZb9URi0g?si=H1R3YVWXcq8SldAC

    https://youtube.com/shorts/GxhYCojnLhQ?si=5xxDyUfEdzkPCfXA

    Post edited by WendyLuvsCatz on
  • DiomedeDiomede Posts: 15,188
    edited November 2023

    Great work, Artini.  Daz Studio can probably render anything, but needs Blender or ZBrush or.... to do the sculpting or modeling.  I did some more playing around.  Here is yet another interpretation of the myth of George vs the Dragon, perhaps suitable for cover art.  I started with decades old Poser figures in Carrara, and rendered a depth pass.  Poser 7 Sydney and Simon.  Maybe 10 - 15 minutes to throw together the Carrara scene, including customzing with the built in terrain modeler and plant modeler.  I used the depth pass in Controlnet to help direct the way in which Stable Diffusion manipulated the image.  I will attach the original Carrara render and its Carrara depth pass in addition to the Stable Diffusion output.  Pretty sure Daz Studio could do the same as Carrara's depth pass.  Canvasses I think is the term.

    upscaled output of stable diffusion.png
    1024 x 1536 - 2M
    Goerge Dragon Carrara Output 01.png
    512 x 768 - 747K
    Goerge Dragon Carrara Output 01_Depth.png
    512 x 768 - 72K
    Post edited by Diomede on
  • ArtiniArtini Posts: 9,513

    Another great creation, Diomede.

    Looks like I need to learn much more...

     

  • WendyLuvsCatzWendyLuvsCatz Posts: 38,312
    edited November 2023

    A Stonemason ruin in Twinmotion, Zombie Diffused

    Video1000000000.jpg
    1920 x 1080 - 581K
    20231120174454_000000000.png
    1920 x 1080 - 3M
    Post edited by WendyLuvsCatz on
  • DiomedeDiomede Posts: 15,188

    WendyLuvsCatz said:

    Artini said:

    Thanks for the explanation, Wendy.

    Hope to try it at some point. It seems unavoidable...

     

    more or less my reasoning

    I don't do commercial work, 3D is just a hobby for me so feel less guilty

    I understand the artists point of view but I am not on one side or the other and resent being called a thief because I am exploring and educating myself on new technology

    the minute I deprive someone of some income by my actions I will accept the thief label

    I haven't 

    it's not black and white for me, it's a spectrum and I am in the middle or grey area on my feelings

    I am sad DAZ PAs who I have even recently like in the last week bought products from are so angry about it

    for them it seems a black and white issue but they created their models, I am just a user/customer and IMO not an artist either (me personally that is) I am a hobbyist that uses premade models by others

    I don't steal 3D models, I don't upload other people's art

    I have Greg Rutkowski's Witcher art in my desktop rotation (it came with my bought Witcher games and he was paid by them) wink

    I have looked at it and my DAZ stuff and considered doing a render based on it, shoot me!

    I am in a similar boat.  yes

  • DiomedeDiomede Posts: 15,188

    Artini said:

    Another great creation, Diomede.

    Looks like I need to learn much more...

    Thanks for the kind words.  You are lightyears ahead of me, making the kind words even more kind.  yes

  • DiomedeDiomede Posts: 15,188
    edited November 2023

    Custom Figures for Comic Strip

    Years ago, I modeled and rigged some custom figures intending to make a comic strip or animation.  Never finished the Brash Lonergan and Moxie Espinoza comic strip, but I still trot out the figures now and again.  It is amazing what the AI programs can do.  Here is an example.  I posed my figures in Carrara, along with simple primitives, and rendered out a base render and a depth pass.  In Stable Diffusion's Controlnet extension, I used the base render for the 'canny' function and the depth pass for the 'depth' function, setting each to half strength.  I then entered some simple verbal prompts describing the scene.  Here is my base render and the result.  Going for the look of a 1940s newspaper comic strip, so this has too much modern anime influence despite my putting anime among the negative prompts, but still amazing to me.  Find the base render and the depth pass attached.

    I prompted for doing in comic style of the Flash Gordon creator.  I would have to touch this up.  For example, you can see from my base render (attached) that the colors of the uniform are reversed.  Here is the verbal prompt for the man in the foreground.  (1 boy) man blonde hair in foreground wearing uniform (red shirt, gold trim, blue pants) standing, pressing right hand against pillar, holding box of tools with left hand.  

    Result from AI

    Carrara Renders.png
    517 x 768 - 168K
    SD output hi 2.png
    1024 x 1024 - 966K
    Carrara Renders_Depth.png
    517 x 768 - 37K
    Post edited by Diomede on
  • DiomedeDiomede Posts: 15,188
    edited November 2023

    Using a different model makes a huge difference.  Here is the result of using the same verbal prompts and the same input images but using a different model.  The result for the figures is much closer to the 1940s style, but the sets and props are not as good.  And where did that moon come from?

     

    different model.png
    512 x 768 - 564K
    Post edited by Diomede on
  • ArtiniArtini Posts: 9,513

    Nice experiments with depth pass.

    Yes, different models, seeds values, LORAs gives different results.

    Just trying to figure out the best workflow for me.

     

  • ArtiniArtini Posts: 9,513
    edited November 2023

    Making comics is another idea to try...

    image

    Comic06.jpg
    1024 x 1024 - 413K
    Post edited by Artini on
  • ArtiniArtini Posts: 9,513
    edited November 2023

    Two Lions...

    image

    Ancient22.jpg
    1024 x 1024 - 221K
    Post edited by Artini on
  • ArtiniArtini Posts: 9,513
    edited November 2023

    Meerkats...

    image

    Ancient52.jpg
    1024 x 1024 - 268K
    Post edited by Artini on
  • DiomedeDiomede Posts: 15,188

    Wow!  Very cool, @Artini

  • ArtiniArtini Posts: 9,513

    Thanks, Diomede.

    Wish, I could create similar images from scratch using Daz Studio.

     

  • ArtiniArtini Posts: 9,513
    edited November 2023

    There is available https://www.daz3d.com/space-bash

    so here is the image to inspire some possible creations with it, I think.

    image

    SciFi01.jpg
    1024 x 1024 - 187K
    Post edited by Artini on
  • ArtiniArtini Posts: 9,513
    edited November 2023

    The other one would be cool to recreate in Daz Studio

    image

    SciFi02.jpg
    1024 x 1024 - 185K
    Post edited by Artini on
  • ArtiniArtini Posts: 9,513
    edited November 2023

    Just one more...

    image

    SpaceShips03.jpg
    1024 x 1024 - 213K
    Post edited by Artini on
  • DiomedeDiomede Posts: 15,188

    @Artini.  All three are very cool.  yes

Sign In or Register to comment.