coreml-cineDiffusion-vae-ft-mse-v3_cn

coreml-community/coreml-cineDiffusion-vae-ft-mse-v3_cn

coreml-cineDiffusion-vae-ft-mse-v3_cn 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. - Provide the model to an app such as Mochi Diffusion Github / Discord to generate images.

Downloads · 30 days

Access

Public

Updated Jul 27, 2023

Repo size

17.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.zip17.9 GB · 100%

At a glance

Task: Text-to-Image
License: creativeml-openrail-m
Access: Public
Created: Jul 25, 2023
Updated: Jul 27, 2023
SHA: 38903fc4

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.
Provide the model to an app such as Mochi Diffusion Github / Discord 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.
This model does not include a safety checker (for NSFW content).
This model can be used with ControlNet.

<br>

cineDiffusion-vae-ft-mse-v3_cn:

Source(s): CivitAI<br>

Cine Diffusion v3

Important: Having multiple models uploaded here on civitai has made it difficult for me to respond to each and every comment. Visit my thread of the Unstable Diffusion Discord

Like photorealism? Try my new fine-tune Lomostyle

A VAE is required. The recommended one is already baked into the file versions available here.

Cine Diffusion - Fine tuned on cinematic stills and 35mm film.

Note: Description is limited atm. Full PDF documentation is in the works.

Have you heard of the high elves?

If you're attempting to generate an image of a elf and aren't seeing pointy ears:

Set your CFG to 7+
Make sure elf is closer towards the beginning of the prompt.

Warning - This model is a bit horny at times. I tried to alleviate this by fine tuning the text-encoder using the class nsfw and sfw. This solution is not perfect. More experimentation is needed. I've had most success with adding sfw or nsfw within the first 75 tokens of the prompt. Adding sfw or nsfw to the negative prompt can also help.

Settings

Clipskip: 1
ETA Noise Seed Delta: 31337
CFG: 6 - 8

Sampler recommendations:

DPM++ SDE Karras, 18-40 steps
Euler a, 20-32 steps
DPM++ 2M Karras, 30-70 steps
Heun, 20-30 steps
Euler, 20-70 steps, Sigma Churn = 1

These parameters are not strictly required, experiment around with other samplers and parameter values. You might find something that works better for you.

Textual Inversion (Negative) used in sample images :
Bad_prompts_version2: https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt
Install location: stable-diffusion-webui -> embeddigs -> <place .pt embedding here>