coreml-dynavisionXL-v0557_SDXL_8bit

Core ML Converted SDXL Model:

• This model was converted to Core ML for use on Apple Silicon devices. Conversion instructions can be found here.
• Provide the model to an app such as Mochi Diffusion Github / Discord to generate images.
• original version is only compatible with CPU & GPU option.
• Resolution is the SDXL default of 1024x1024 UNLESS NOTED OTHERWISE.
• This model requires macOS 14.0 or later to run properly.
• This model is quantized to 8-bits.
• This model was converted with a vae-encoder for use with image2image.
• Descriptions are posted as-is from original model source.
• Not all features and/or results may be available in CoreML format.
• This model does not have the unet split into chunks.
• This model does not include a safety checker (for NSFW content).
• This model can not be used with ControlNet.

<br>

dynavisionXL-v0557_SDXL_8-bit:

Source(s): CivitAI<br>

DynaVision XL

This is an SDXL base model converted and quantized to 8-bits.

All-in-one stylized 3D SFW and NSFW output, no refiner needed!

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.

DynaVisionXL 0.5.5.7 Release Notes 10/25/23

Hi everybody! I'm excited to announce the release of DynaVision XL 0.5.5.7. I've put a lot of work into this update, as the last update (0.5.4.3) kind of strayed from that magic that is DynaVision and pushed a little too hard towards realism. With this version, we've come back around to the Disney'esque charm that made DVXL so great to begin with!

Changelog

DVXL is now on it's own branch entirely as it has diverged 100% away from NVXL. This version I used multiple forward and back-merges between 0.5.4.3 and 0.3.7.1, working in a few new loras to help try to bring back the more exaggerated 3D cartoon look, while upping detail level and quality bolstered with some of my own training.

Expect more detail, better hands, better coherence. Teeth have had an improvement across the board/

Added New LoRAs:

• SCG-Detailer-v1 (internal training LoRA)
• SCG-Detailer-v2 (internal training LoRA)
• CuteCartoonRedmond-CuteCartoon-CuteCartoonAF
• CuteCombine
• Artistic-makeup-lip-bite-winks

Known Issues:

• Hands can still be goofy
• Crooked eyes, while mostly banished, still can occur
• Male genitalia still nonexistent
• Still working on improving eyes at distance<br><br>