|
--- |
|
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).<br> |
|
|
|
# lofi-V2: |
|
Source(s): [Hugging Face](https://huggingface.co./SG161222/Realistic_Vision_V2.0) - [CivitAI](https://civitai.com/models/4201/realistic-vision-v20)<br> |
|
|
|
**L.O.F.I: Limitless Originality Free from Interference** |
|
|
|
🧐 No special face alignment |
|
|
|
🚀 Improve line details |
|
|
|
🚀 Improve prompt understanding |
|
|
|
Based on the LOFI-v1 model, finetuned 80,000 steps / 300 epochs |
|
|
|
📷more camera concept |
|
|
|
 |
|
|
|
🎨exact palette |
|
|
|
 |
|
|
|
<br>**Prompt suggestions** |
|
|
|
Since the text-encoder used is enough trained version, do not use a very high attention to control weight, which will cause some wrong drawing, it is recommended that all attention weights be no higher than 1.2 |
|
|
|
If there is no special composition requirement, there is no need for a lot of negative prompts, such as "missing hands", which may affect human body drawing, and DeepNegative is enough for negative prompts |
|
|
|
It is strongly recommended to use hires.fix to generate, Recommended parameters: |
|
|
|
- Final output: 512*768 |
|
- Steps: 20, Sampler: Euler a, CFG scale: 7 |
|
- Size: 256x384, Denoising strength: 0.75 |
|
- Hires upscale: 2, Hires steps: 40 |
|
- Hires upscaler: Latent (bicubic antialiased) |
|
|
|
Most of the sample images are generated with Hires. fix |
|
|
|
Note: that if you use Hires. fix, you may not be able to reproduce the image with the same set of parameters in WebUI, because Hires. fix introduces double randomness.<br><br> |
|
|
|
|
|
 |
|
|
|
 |
|
|
|
 |
|
|
|
 |
