Downloads · 30 days
0
coreml-ez-v10
coreml-community/coreml-ez-v10
coreml-ez-v10 is a text-to-image model from coreml-community. Use it when you need an image from a text prompt. The card lists the license as creativeml-openrail-m.
- This model was converted to Core ML for use on Apple Silicon devices. Conversion instructions can be found here.<br - Provide the model to an app such as Mochi Diffusion Github - Discord to generate images.<br
Access
Public
Updated Apr 5, 2023
Repo size
9.9 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.zip9.9 GB · 100%
At a glance
- Task
- Text-to-Image
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Mar 18, 2023
- Updated
- Apr 5, 2023
- SHA
- d83a2a7f
Model card
From the Hugging Face model README
Core ML Converted Model:
- This model was converted to Core ML for use on Apple Silicon devices. Conversion instructions can be found here.<br>
- Provide the model to an app such as Mochi Diffusion Github - Discord to generate images.<br>
split_einsumversion is compatible with all compute unit options including Neural Engine.originalversion is only compatible with CPU & GPU option.- Custom resolution versions are tagged accordingly.
- The
vae-ft-mse-840000-ema-pruned.ckptvae is embedded into the model. - Descriptions are posted as-is from original model source.
- Not all features and/or results may be available in CoreML format.
- This model was converted with
vae-encoderfor i2i. - This model is fp16.
- This model does not have the unet split into chunks.
- This model does not include a safety checker (for NSFW content)
ez-v10
Source(s): CivitAI
Trained and Mixed model for photorealism.
Recommended sampler: UniPC, DPM++ 2M Karras
Low CFG scale is recommended: 2 - 5
Recommended VAE: vae-ft-mse-840000-ema-pruned
Used Models: SD 1.5 (trained), Anything 3.0 (merged->trained), Anything 4.5 (merged), and some other trained models were merged
- Task
- Text-to-Image
- License
- creativeml-openrail-m
- Created
- Mar 18, 2023
- Updated
- Apr 5, 2023