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!
DynaVision XL was born from a merge of my NightVision XL model and several fantastic LORAs including Sameritan's wonderful 3D Cartoon LORA and the Wowifier LORA, to create a model that produces stylized 3D model output similar to computer graphics animation like Pixar, Dreamworks, Disney Studios, Nickelodeon, etc.
DynaVision XL is capable of both SFW and NSFW output. As with all of my other models, tools and embeddings, DynaVision XL is easy to use, preferring simple prompts and letting the model do the heavy lifting for scene building.
WARNING - DO NOT USE SDXL REFINER WITH DYNAVISION XL
The SDXL refiner is incompatible and you will have reduced quality output if you try to use the base model refiner with DynaVision XL.
Follow me here by clicking the heart ❤️ and liking the model 👍, and you will be notified of any future versions I release. I also need your help with feedback, please please please post your images and your honest feedback below, I will use your feedback and your output to help guide future revisions!
Description
DynaVisionXL_v0.6.1.0 Release Notes
Hi everybody, happy new year! This was my last model update right before I hit the holidays, and is my first public release of 2024 and I'm excited it's DynaVisionXL! This time around I've performed 5 trainings targeting improving widescreen aspect ratio output, improvements to eye and pupil quality, These trainings I used my own training tools and methods that have shown to improve coherence and prompt accuracy, even for more complex prompt situations.
Changelog 1/13/24
5 total internal tunings applied
3 trained on varying wide and tall images
2 focused on coherence and detail, especially eyes
low-value back-merge with DV534 to help stabilize the DynaVision style
Known issues
male genitalia
hands
medium distance mushiness for faces and fine details (this is a VAE issue, but still worth tracking here)
long necks in tall aspect ratios
FAQ
Comments (22)
Can someone please suggest VAE for SDXL 😁
This checkpoint has a VAE baked in. You won't need one to use this.
@GhostBear1111 yeah i was asking in general
@NoobFromEgypt if you're using A1111 you may still need to manually set sdxl_vae_fp16_fix.safetensors as VAE. I don't have a handle on why it happens yet, but sometimes a checkpoint will require it to be manually set even when it's supposedly baked in. In the case of DynaVision here, I don't know specifically. Nowadays I just run everything with sdxl_vae_fp16_fix.safetensors, it doesn't hurt.
@shapeshifter83 Thank you 🫡
@GhostBear1111 Still keeps giving me black images without VAE for some reason. Works fine with sdxl VAE.
This model is good, BUT not NSFW at all. Really hard to pull any nudity with it. Even with a clearly NSFW already nicely inpainted, this model just removes anything related to vaginas or dicks, even at very low denoise.
Nice model. But definitely a misleading title.
NB
Ok it is MY opinion but ... v0411 is best compare to v0534 or v0610.
Well well, gonna stick to that v0411 😛
How can i use this model with Controlnet?
(idk if you've find out how, but:)
As an XL model, you should use Control Lora instead of the well-known ControlNet models, which are for SD1.5
pruned version ?
witch VAE should i use,please
VAE is baked
@altoiddealer Yeah .... all of those models with "baked" VAE keep giving me black images for some reason. This one like any other XL based model works fine with sdxl VAE.
@socalguitarist - Thanks for this! Very quickly was able to dial in a series that was, for me, next level. https://civitai.com/posts/3222539
This model is amazing, Thank you
Love this model
Would love a FLUX version of this!
Just wanted to drop in and say this model is still one of my all-time favorites! Flux/Illustrious/SD3.5 versions would be great too!
Are you using Euler A / Simple?
@prolakeenterprise836 No
Details
Files
dynavisionXLAllInOneStylized_releaseV0610Bakedvae.safetensors
Mirrors
DynaVision_XL_ALLINONE.safetensors
dynavisionXLAllInOneStylized_releaseV0610Bakedvae.safetensors
dynavisionXLAllInOneStylized_releaseV0610Bakedvae.safetensors
DynaVisionXL_0.6.safetensors
dynavisionXLAllInOneStylized_releaseV0610Bakedvae.safetensors
dynavisionXLAllInOneStylized_releaseV0610Bakedvae.safetensors
DynaVisionXLAllinonestylized3DSFWandNSFWoutputnorefinerneeded.safetensors
dynavisionXLAllInOneStylized_releaseV0610Bakedvae.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.