|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- coreml |
|
- stable-diffusion |
|
- text-to-image |
|
--- |
|
# Core ML Converted Model: |
|
|
|
- This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML). |
|
- Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images. |
|
- `split_einsum` version is compatible with all compute unit options including Neural Engine. |
|
- `original` version is only compatible with `CPU & GPU` option. |
|
- Custom resolution versions are tagged accordingly. |
|
- The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model. |
|
- This model was converted with a `vae-encoder` for use with `image2image`. |
|
- This model is `fp16`. |
|
- 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](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). |
|
- This model does not include a `safety checker` (for NSFW content). |
|
- This model can be used with ControlNet. |
|
|
|
<br> |
|
|
|
# inkpunkDiffusion-v2_cn: |
|
Source(s): [CivitAI](https://civitai.com/models/1087) / [Hugging Face](https://huggingface.co/Envvi/Inkpunk-Diffusion)<br> |
|
|
|
## Inkpunk Diffusion v2 |
|
|
|
Finetuned Stable Diffusion model trained on Dreambooth. |
|
|
|
Vaguely inspired by Gorillaz, FLCL, and Yoji Shinkawa |
|
|
|
Use nvinkpunk in your prompts. |
|
|
|
### About Version 2 |
|
|
|
Improvements: |
|
|
|
Excorsized the woman that seemed to be haunting the model and appearing in basically every prompt. (She still pops in here and there, I honestly don't know where she comes from.) |
|
|
|
Faces are better overall, and characters are more responsive to descriptive language in prompts. Try playing around with emotions/nationality/age/poses to get the best results. |
|
|
|
Hair anarchy has been toned down slightly and added more diverse hairstyles to the dataset to avoid everyone having tumbleweed hair. Again, descriptive language in prompts helps. |
|
|
|
Full body poses are also more diverse, though keep in mind that wide angle shots tend to lead to distorted faces that may need to be touched up with img2img/inpainting.<br><br> |
|
|
|
|
|
 |
|
|
|
 |
|
|
|
),_((detailed_face)),_((award_winning)),_(High_Detail),_Sharp,_8k,__trending_o.jpeg) |
|
|
|
 |
