Edit model card

『Ginger Mix』

a a a


『Ginger MixR』

a a

  • "Ginger MixR" is a model based on "Ginger Mix" with improved composition and background, and is as close to "LimeMixV2" as possible.

『Ginger V1』

a a


◆Discord

Join Discord Server

  • The merged model community of Hemlok.

◆About

  • Sampler: DDIM or DPM++ SDE Karras

  • Steps: 20~

  • Clipskip: 2

  • CFG Scale: 5-8

  • Denoise strength: 0.5-0.65

  • Negative prompts should be as few as possible.

  • vae: Use "Any" or similar.


◆How to use

  • Please download the file by yourself and use it with WebUI(AUTOMATIC1111) etc.

  • Use the fp16 version for Colab(T4) or a PC with low RAM.


◆Comparison

a a

1girl, white hair, floating hair, looking at viewer, cowboy shot, winter, jacket

◆Sampler & CFG Scale

(GingerMix)

a a

1girl, solo, (winter coat), (chino), (downtown:1.2),

Disclaimer

  • The creation of SFW and NSFW images is at the discretion of the individual creator.

  • This model is not a model created to publish NSFW content in public places, etc.


License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.

The CreativeML OpenRAIL License specifies:

  1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content

  2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license

  3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)

(Full text of the license: https://huggingface.co/spaces/CompVis/stable-diffusion-license)

Downloads last month
88
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using Hemlok/GingerMix 2