Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,80 @@
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- coreml
|
| 5 |
+
- stable-diffusion
|
| 6 |
+
- text-to-image
|
| 7 |
---
|
| 8 |
+
# Core ML Converted Model:
|
| 9 |
+
|
| 10 |
+
- 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).
|
| 11 |
+
- 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.
|
| 12 |
+
- `split_einsum` version is compatible with all compute unit options including Neural Engine.
|
| 13 |
+
- `original` version is only compatible with `CPU & GPU` option.
|
| 14 |
+
- Custom resolution versions are tagged accordingly.
|
| 15 |
+
- The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model.
|
| 16 |
+
- This model was converted with a `vae-encoder` for use with `image2image`.
|
| 17 |
+
- This model is `fp16`.
|
| 18 |
+
- Descriptions are posted as-is from original model source.
|
| 19 |
+
- Not all features and/or results may be available in `CoreML` format.
|
| 20 |
+
- This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).
|
| 21 |
+
- This model does not include a `safety checker` (for NSFW content).
|
| 22 |
+
- This model can be used with ControlNet.
|
| 23 |
+
|
| 24 |
+
# epiCRealism pure Evolution V3:
|
| 25 |
+
Source(s): [CivitAI](https://civitai.com/models/25694/epicrealism)<br>
|
| 26 |
+
|
| 27 |
+
## V3 is here!
|
| 28 |
+
|
| 29 |
+
Since SDXL is right around the corner, let's say it is the final version for now since I put a lot effort into it and probably cannot do much more.
|
| 30 |
+
|
| 31 |
+
I tried to refine the understanding of the Prompts, Hands and of course the Realism.
|
| 32 |
+
Let's see what you guys can do with it.
|
| 33 |
+
|
| 34 |
+
Thanks to @drawaline for the in-depth review, so i'd like to give some advices to use this model.
|
| 35 |
+
|
| 36 |
+
## Advices
|
| 37 |
+
Use simple prompts
|
| 38 |
+
|
| 39 |
+
No need to use keywords like "masterpiece, best quality, 8k, intricate, high detail" or "(extremely detailed face), (extremely detailed hands), (extremely detailed hair)" since it doesn't produce appreciable change
|
| 40 |
+
|
| 41 |
+
Use simple negatives or small negative embeddings. gives most realistic look (check samples to get an idea of negatives i used)
|
| 42 |
+
|
| 43 |
+
Add "asian, chinese" to negative if you're looking for ethnicities other than Asian
|
| 44 |
+
|
| 45 |
+
Light, shadows, and details are excellent without extra keywords
|
| 46 |
+
|
| 47 |
+
If you're looking for a natural effect, avoid "cinematic"
|
| 48 |
+
|
| 49 |
+
Avoid using "1girl" since it pushes things to render/anime style
|
| 50 |
+
|
| 51 |
+
To much description of the face will turn out bad mostly
|
| 52 |
+
|
| 53 |
+
For a more fantasy like output use 2M Karras Sampler
|
| 54 |
+
|
| 55 |
+
No extra noise-offset needed, but u can if you like to 😉
|
| 56 |
+
|
| 57 |
+
## How to use?
|
| 58 |
+
|
| 59 |
+
Prompt: simple explanation of the image (try first without extra keywords)
|
| 60 |
+
|
| 61 |
+
Negative: "cartoon, painting, illustration, (worst quality, low quality, normal quality:2)"
|
| 62 |
+
|
| 63 |
+
Steps: >20 (if image has errors or artefacts use higher Steps)
|
| 64 |
+
|
| 65 |
+
CFG Scale: 5 (higher config scale can lose realism, depends on prompt, sampler and Steps)
|
| 66 |
+
|
| 67 |
+
Sampler: Any Sampler (SDE, DPM-Sampler will result in more realism)
|
| 68 |
+
|
| 69 |
+
Size: 512x768 or 768x512
|
| 70 |
+
|
| 71 |
+
Hires upscaler: 4x_NMKD-Superscale-SP_178000_G (Denoising: 0.35, Upscale: 2x)<br><br>
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
%20BREAK_half%20body%20portrait%20of%20a%20young%2020yo%20woman,%20black%20hair,%20wearing%20a%20summer%20dress%20BREAK_det.jpeg)
|
| 75 |
+
|
| 76 |
+
,%20(smile_0.5),%20wearing%20relaxed%20shirt%20and%20trousers,%20causal%20cloth.jpeg)
|
| 77 |
+
|
| 78 |
+
.jpeg)
|
| 79 |
+
|
| 80 |
+
|