CivArchive
    TurboVisionXL - Super Fast XL based on new SDXL Turbo - 3 - 5 step quality output at high resolutions! - Alpha-V0.1.0.1-bakedVAE
    NSFW
    Preview 4008011
    Preview 4007805
    Preview 4007835
    Preview 4007800
    Preview 4007801
    Preview 4007803
    Preview 4007808
    Preview 4007819
    Preview 4007820
    Preview 4007821
    Preview 4007822
    Preview 4007834
    Preview 4007836
    Preview 4008023
    Preview 4010365
    Preview 4010366
    Preview 4010367
    Preview 4010368
    Preview 4010369

    Like the work I do and want to say thanks? Buy me a coffee 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! 💖💖💖

    Wow guys, you have to try this for yourself! 😲😲

    Super fast generations at "normal" XL resolutions with much better quality than base SDXL Turbo!

    Suggested settings for best output

    Sampler: DPM++ SDE or DPM++ SDE Karras

    Steps: 3 - 5

    CFG: 1 - 2.25

    You can run this model in Automatic1111 like a normal XL model, however not all samplers work with it. I've found DPM++ SDE is the best output performance in the 3 - 5 range, while DPM2 looks really good in the 6 - 10 step range if you're willing to wait just a bit longer. The LCM sampler and Euler A produce almost identical output, which is usable at low steps, but really lacking in detail vs. the other options.

    LoRAs work fine, I've tested multiple LoRAs and they appear to still produce expected results, tho YMMV of course.

    Coherence is a work in progress with this model. 1024 x 1024 is pretty well solved now, and I very rarely see errors even in 4:3 and 2:3 formats. 16:9 does result in some twinning, but it's not too bad. 21:9 is rougher with an annoying amount of twinning and errors, though not too much worse than normal mainline models.

    NOTE ON LICENSING - This model is based on the SDXL Turbo model released by Stability AI. They have flagged the model as being released under a non-commercial research license and permits personal, non-commercial use only. Be aware this model cannot be used for image generation services at this time. If you have questions, please reach out to me on Discord.

    Description

    Alpha Version 0.1.0.1 Release Notes 20231128

    This model is all about SPEED - It produces better quality output than using the LCM or distilled models, works at 1024 x 1024 (and other "standard" XL aspect ratios) and produces high quality output fast. This model is based on DynaVision and will produce stylized output. I will be working on another version that will target more photographic realistic style output.

    Known Issues

    • Coherence has taken a hit - fingers, hands, extra arms. This stuff will show up now, it's something I will work on fixing with updates

    • doesn't support all samplers, stick to DPM++ SDE Karras for best results!

    • requires really low CFG! 1 - 2.25 is best as tested

    FAQ

    Comments (20)

    MrNoirNov 29, 2023
    CivitAI

    is this turbo? or what does it have on top

    Picky_FlickyNov 29, 2023
    CivitAI

    hmm, so far running at normal speed, but sometimes new models take a little while of using to 'warm up,' once installed. One weird thing - most of the images have a normal amount of arms but random extra legs. Guess I'll see if adjusting my neg prompt can fix that. Seems cool in theory!

    ktiseos_nyxNov 29, 2023
    CivitAI

    I'm still tRYING TO WRAP MY HEAD AROUND LCM and Distilled AFTER i wrap my head around normal XL. XD However, this does look amazeballlssss

    MrNoirNov 29, 2023· 1 reaction
    CivitAI

    can u upload without baked vae?

    RoscosmosNov 29, 2023· 8 reactions
    CivitAI

    will images appear before I hit generate?

    TrueToLife_FauxtoNov 29, 2023
    CivitAI

    Holy cr*p, Batman! Aside from the photorealism, this is freaking awesome!

    NoMansLandNov 29, 2023
    CivitAI

    Can you please enable the model to allow it to be used for civitai's online image generation? Thank you for your consideration.

    socalguitarist
    Author
    Nov 29, 2023· 2 reactions
    CivitAI

    NOTE ON LICENSING - This model is based on the SDXL Turbo model released by Stability AI. They have flagged the model as being released under a non-commercial research license and permits personal, non-commercial use only. Be aware this model cannot be used for image generation services at this time. If you have questions, please reach out to me on Discord.

    jaanisjcNov 29, 2023
    CivitAI

    Could you share your workflow? For some reason I am getting really bad results even after setting up the same suggested settings.

    kellneNov 29, 2023
    CivitAI

    Please add it for onsite generation 🔪

    DSlaterNov 29, 2023· 9 reactions
    CivitAI

    YOU MUST USE 5 OR LESS STEPS

    YOU MUST USE 3 OR LESS CFG

    Normal SDXL LoRAs should work and may actually help consistency.


    In the images section I posted a screenshot of my A1111 settings page & sample images created in 100image batches using a couple of LoRAs. With these new Turbo models you must use a totally different range of settings - 5steps / 1,2,3 CFG - and a LoRA is a good place to start.

    Used a 4090 and could finish a batch of 100 images (1344x784) in a bit over 3minutes. I could probably generate 100images using a normal model w/ 20steps in 6ish. So it's up to you to decide if that speed difference makes the "different" quality worth it to you (Obv may make more or less of a difference on less powerful GPU).

    Good luck!

    godpunisherNov 29, 2023· 6 reactions
    CivitAI

    AI development speed is terrifying. Because of low VRAM, once I thought SDXL to be unusable on A1111, but now I can.

    ThislandNov 29, 2023· 1 reaction
    CivitAI

    Performs worse than standard sdxlTurbo for me with same inputs/seed, even trying different schedulers and cfg

    xueqing12211Nov 30, 2023
    CivitAI

    Thanks for sharing, I hope to continue to update and get better results!

    ausbitbankNov 30, 2023
    CivitAI

    Nice model! It does have some coherence issues with 1024x sometimes but I'm getting some great quality outputs with 13 steps, 2 scale, euler_a sampler

    zakblueNov 30, 2023
    CivitAI

    This is great, nice job! getting good results at 1024x1024 with 8 steps using euler or euler a on an RTX 4080

    mnemicNov 30, 2023
    CivitAI

    What's a good VAE to use with this? My results are really washed out in general.

    Dav1nx1Nov 30, 2023· 2 reactions
    CivitAI

    Amazing results. thanks for sharing.

    for comparison, I created this flow.
    https://gist.github.com/Dav1nx1/d86ba2c3f96298192bca52cf950e16ab

    socalguitarist
    Author
    Nov 30, 2023· 15 reactions
    CivitAI

    New version coming tomorrow! 1.3.1 Beta, my patrons and testers have been using it and reporting much better coherence and better quality output. Coming soon! 😉

    schieloDec 1, 2023· 1 reaction
    CivitAI

    Works great with animation (Deforum YT clip: Sharon Stone/Alice Eve + Chuck Norris vs a beaver): https://youtu.be/AE5R907X_mQ

    Checkpoint
    SDXL Turbo

    Details

    Downloads
    5,511
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    11/29/2023
    Updated
    4/27/2026
    Deleted
    10/16/2025

    Available On (1 platform)

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