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!
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
TurboVisionXL Beta 1.3.1 Release Notes
Meet the first update for TurboVision. This has had 8 different tunings applied from my previous model trainings to attempt to curb some of the more troublesome coherence problems and improve the model's 1 shot output. This still works best at 5 steps with DPM++ SDE Karras.
ChangeLog 12/1/23
Added the following (internal only) tunings:
SCG-Detailer-v1
SCG-Detailer-V2
CVXL-Detailer-007
CineClassic-007
SCG-Classic-Cinema-009
Stylevision-tune-020231120
SCG-Cinematic-Detailer-V1-000010
Analog-photography-v2-00008
Known Issues
Coherence is improved over 1.0.1, however it's still not where it needs to be. Expect occasional twinning, floating hands, extra fingers, etc. The next update mostly solves this, but for this version you will still have occasional coherence badness.
Male Genitalia
Eyes and faces at distance (surprisingly improved over other XL models, but still not "good")
FAQ
Comments (8)
Yes!
will this one also break with the refiner?
TurboVisionXL Beta 1.3.1 Release Notes
Meet the first update for TurboVision. This has had 8 different tunings applied from my previous model trainings to attempt to curb some of the more troublesome coherence problems and improve the model's 1 shot output. This still works best at 5 steps with DPM++ SDE Karras.
ChangeLog 12/1/23
Added the following (internal only) tunings:
SCG-Detailer-v1
SCG-Detailer-V2
CVXL-Detailer-007
CineClassic-007
SCG-Classic-Cinema-009
Stylevision-tune-020231120
SCG-Cinematic-Detailer-V1-000010
Analog-photography-v2-00008
Known Issues
Coherence is improved over 1.0.1, however it's still not where it needs to be. Expect occasional twinning, floating hands, extra fingers, etc. The next update mostly solves this, but for this version you will still have occasional coherence badness.
Male Genitalia
Eyes and faces at distance (surprisingly improved over other XL models, but still not "good")
hi! when i try and run either this or the original turbo checkpoint i get a vram error even before generating (using a 6700xt 12gb) is it normal?
Is it possible to use ADetailer with this model and if so then how? No matter what I try it just won't work.
...THAT IS NOT TURBO VERSION.
That is LCM version
Turbo version should works well with 1 STEP ( from 1 -to 4 exactly. Where 4 is a bit too big )
first few steps it generates normally but then at the end it becames green unintelligible mess
I made some grids of all currently uploaded turbo models. all but the base model and jib's need atleast 3 steps for a decent image, and anything over config 2 tends to be either very cartoony or blurry/other artifacts. also almost no difference between 1 step and 2 steps.
(step check 1-4, cfg1)https://civitai.com/posts/929205
(cfg check, 4steps)https://civitai.com/posts/929178
(same model order as pervious grids, cfg 1 steps 3) https://civitai.com/posts/929237
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.