|
--- |
|
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. Instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-files-to-Core-ML).<br> |
|
- Provide the model to an app such as [Mochi Diffusion](https://github.com/godly-devotion/MochiDiffusion) to generate images.<br> |
|
- `split_einsum` version is compatible with all compute unit options including Neural Engine.<br> |
|
- vae-ft-mse-840000-ema embeded |
|
|
|
# Note: This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml). |
|
|
|
# AnalogDream3D: |
|
Source(s): [CivitAI](https://civitai.com/models/3086/analogdream3d) |
|
|
|
It is a Remix Model of the following amazing models: |
|
|
|
Analog_diffusion |
|
|
|
Dreamlike_photoreal |
|
|
|
3DKX_v1.0B |
|
|
|
It strongly enhanced the photorealistic power from Analog and DreamLike, and with a good merged method for 3DKX_v1, it come out with the ability for higher resolution ouputs like 1024*768 and more+ !! |
|
|
|
you can try to use it to output some of scene,it can handled a lot of describition like hugging and kiss. |
|
|
|
I think ,by this merged method, we might try to UPGRADE a large numbers of old model to a higher resolution output level. I also try this recipe with other models, some works, some failed. |
