CivArchive
    CineVisionXL by SoCalGuitarist - Release-v1.5.0-BakedVAE
    NSFW
    Preview 3368607
    Preview 3369694
    Preview 3369692
    Preview 3369695
    Preview 3369700
    Preview 3369697
    Preview 3369698
    Preview 3369701
    Preview 3369699
    Preview 3369703
    Preview 3369702
    Preview 3369709
    Preview 3369704
    Preview 3369706
    Preview 3369707
    Preview 3369705
    Preview 3369753

    Like the work I do and want to help support me? Buy me a coffee to say thanks or Support me on Patreon for exclusive early access to my models and more!

    Join us on SCG-Playground where we have fun contests, discuss model and prompt creation, AI news and share our art to our hearts content in THE FLOOD! ๐Ÿ’–๐Ÿ’–๐Ÿ’–


    This is CineVision XL, a new trained model I have built with several of the awesome folks from my Discord channel SCG-Playground. This model has been trained on widescreen (16:9, 21:10) formatted images and can produce stunning "straight out of a movie" scenes that are coherent and beautiful.

    CineVision XL is capable of both SFW and (mild) NSFW output. As with all of my other models, tools and embeddings, CineVision XL is easy to use, preferring simple prompts and letting the model do the heavy lifting, but also can understand complex scene building to a surprising level of detail (try it!)

    Special thanks and shout-out to @Blink, @Klinter, @humblemikey for their direct contributions to this model, and big thanks and love โค๏ธโค๏ธ to my ultra-patient model testing crew on Discord who I'm constantly barraging with new LoRAs and internal builds to try to break. ๐Ÿค™๐Ÿฝ๐Ÿค™๐Ÿฝ

    Follow me on IG!

    Follow me on Threads!

    Chat with me on Discord

    Support me on Patreon

    Description

    Version 1.5.0 - Initial Public Release Notes

    I'm so excited to be releasing this model out to the world! Several hundred hours worth of work went into building this model out, and while it's not perfect, I think it's at least as high quality as my other model lines DynaVision, ProtoVision, and NightVision.

    CineVisionXL was Initially tuned with several hundred synthetic movie themed images that were generated using MidJourney, DALL-E and NightVisionXL and "themed" using Lightroom for cinematic feeling and styling. Next, a low value merge (at 10%) with PixelWave in coordination with HumbleMikey as well as the LoRAs Anthroid from Klinter and CaricatureXL from Blink (Thanks guys!). On top of this, another 3 rounds of training using cinematic "establishing shots" style synthetic scenes, and working in of my own internally trained detailer and cinematic LoRAs to get us where we are now.

    Known Issues

    • hands

    • eyes and teeth need more work, sometimes teeth on lips or eyeshine weirdness can happen

    • male genitalia is pretty much non-existent (use a LoRA)

    FAQ

    Comments (6)

    socalguitarist
    Author
    Nov 4, 2023ยท 10 reactions
    CivitAI

    Version 1.5.0 - Initial Public Release Notes

    I'm so excited to be releasing this model out to the world! Several hundred hours worth of work went into building this model out, and while it's not perfect, I think it's at least as high quality as my other model lines DynaVision, ProtoVision, and NightVision.

    CineVisionXL was Initially tuned with several hundred synthetic movie themed images that were generated using MidJourney, DALL-E and NightVisionXL and "themed" using Lightroom for cinematic feeling and styling. Next, a low value merge (at 10%) with PixelWave in coordination with HumbleMikey as well as the LoRAs Anthroid from Klinter and CaricatureXL from Blink (Thanks guys!). On top of this, another 3 rounds of training using cinematic "establishing shots" style synthetic scenes, and working in of my own internally trained detailer and cinematic LoRAs to get us where we are now.

    Known Issues

    hands

    eyes and teeth need more work, sometimes teeth on lips or eyeshine weirdness can happen

    male genitalia is pretty much non-existent (use a LoRA)

    yofoton174609Mar 12, 2024

    very cool. How about "medieval realism" Lora? For medival clothes, settings, horses, castles and so on, similar to lord of the rings, the hobbit, and so on?

    parallelepipedonNov 14, 2023ยท 3 reactions
    CivitAI

    It sometimes does too much "Mama of Drama" darkness with heavy shadows, but when I can convince it otherwise... it's turning out to be one of my fave XL models!

    crowav98995Nov 30, 2023ยท 2 reactions
    CivitAI

    What are the compatible resolutions? For example, if I want a wide 16:9 resolution, what would it be?

    shapeshifter83Jan 20, 2024

    oooooold comment, I know, sorry for the necro... but for anyone interested: the answer to this question is "whatever set of 16:9 ratio numbers multiplies up to be as close as possible to 1,048,576 total pixels". The base SDXL tech was designed for and operates best right at that mark. AKA "1 megapixel"

    as far as the geometry or Pythagorean equation or whatever's needed to find the exact width and height when you know the total area of the rectangle (1 megapixel) and the ratio of the sides (16:9), see here: https://www.youtube.com/watch?v=fCKjYIEIDio

    bellibrain846Jan 17, 2024
    CivitAI

    why isnt it available for on side anymore

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    3,833
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/3/2023
    Updated
    4/30/2026
    Deleted
    -

    Files

    cinevisionxlBy_releaseV150Bakedvae.safetensors

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.