coreml-talmendoXL-v1.1beta_SDXL_8-bit

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.
• 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>

talmendoXL-v1.1beta_SDXL_8-bit:

Source(s): CivitAI<br>

TalmendoXL - Uncensored SDXL

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

An attempt to uncensor SDXL and bias it more towards photorealism and non professional images.

Should be just as good at non nude images as SDXL, but they will be less professional looking and more like an amateur photo with more natural lighting. Might or might not be to your preference.

Tips: Use "natural light" for natural look, "full body shot" works quite well and directions should also be easy to prompt for with "from the side/front/below"

Recommended:

• Sampler: Heun, Euler or DPM++ 2M
• CFG: 6-10.5
• Steps: 30
• Resolution: 1024x1024, 896x1152, 832x1216, 768x1344 and their inverse (Same as SDXL Base)

Changelog Beta v1.1

• Much higher image quality, overall sharper images
• More skin details
• More different body types<br><br>