Evermore Pony Mix

mixboymixboy
109
969
base modelphoto realisticrealisticcheckpoint
v0.9 Fp16

Details

Download Files

Model description

a Realistic 2.5D Pony based Mixed model

This is another merged model named Evermore Pony mix.

This model is mainly a mixed pony model, mixing it's text-encoder with the text-encoder of Illustrious + SDXL, and merging the pony model and SDXL model at the block level.

Merged Models

Thanks to the original authors for sharing their great models!!

Recipes

Model Mixer https://github.com/wkpark/sd-webui-model-mixer is used to mix models. The recipe details are included in the model checkpoint or some images. (so you can use/modify this recpie easily by using the model-mixer)

  • Fp16 fixed VAE included.

  • all recipes of each version are included in the checkpoint metadata!

Recommends

  • All posted images use μ-DDetailer script extension

    • Note: for some case, use noise multiplier ~0.8 to fix face rendering issue.

    • lower CFG scale ~3.5 to get less distorted face.

  • recommended sampler: Euler a

  • recommended image size (width range is about 6401024 / height range is 6401344):

  • recommended CFG scale: 3.5~6.5

  • Set Clip skip: 2 recommended (Clip skip:1 also works fine), ENSD: 31337

License

Many models here have "Have different permissions when sharing merges" license permission, but some model use Fair-AI-public-1.0-sd - This license disclaim "Same license restriction" so I do not add any additonal restriction except same license restriction.

especially, the license of the Pony Diffusion V6 XL model has "Same license restriction", and it means that any Pony diffusion V6 derivatives (mixed or trained model) have to be the same license.

CreativeML-Open Rail++-M and Fair-AI-public-1.0-sd

This model permits users to:

✔Use the model without crediting the creator

✔Sell images they generate

✔Run on services that generate images for money

✔Share merges using this model

✔Sell this model or merges using this model

❌Have different permissions when sharing merges

the OpenRAIL-M license permits users to own the rights to the images they generate and to use these images for commercial purposes​ (Stable Diffusion)​​ (Baseten)​. This openness supports a wide range of applications, from creative projects to commercial services, enabling businesses and individuals to leverage the model's capabilities for various purposes.

Therefore, if you're considering using Stable Diffusion for commercial products or services, the licensing terms do support such use, as long as the guidelines and restrictions outlined in the license are followed. (from chatgpt)

Support me

If you like my work, feel free to buy me a coffee at ko-fi. https://ko-fi.com/mixboy

Images made by this model

No Images Found.