Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 870820f

Browse files
Update README.md
1 parent 7608faf commit 870820f

File tree

1 file changed

+19
-2
lines changed

1 file changed

+19
-2
lines changed

‎README.md

Lines changed: 19 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -13,16 +13,33 @@ The example app supports only ``split_einsum`` models. In terms of performance `
1313

1414
![The concept](https://github.com/The-Igor/coreml-stable-diffusion-swift-example/blob/main/img/img_03.png)
1515

16+
| File Name | Description |
17+
|--------------------------------------|------------------------------------------------------------------|
18+
| `TextEncoder.mlmodelc` | Encodes input text into a vector space for further processing. |
19+
| `Unet.mlmodelc` | Core model handling the transformation of encoded vectors into intermediate image representations. |
20+
| `UnetChunk1.mlmodelc` | First segment of a segmented U-Net model for optimized processing in environments with memory constraints. |
21+
| `UnetChunk2.mlmodelc` | Second segment of the segmented U-Net model, completing the tasks started by the first chunk. |
22+
| `VAEDecoder.mlmodelc` | Decodes the latent representations into final image outputs. |
23+
| `VAEEncoder.mlmodelc` | Compresses input image data into a latent space for reconstruction or further processing. |
24+
| `SafetyChecker.mlmodelc` | Ensures generated content adheres to safety guidelines by checking against predefined criteria. |
25+
| `vocab.json` | Contains the vocabulary used by the text encoder for tokenization and encoding processes. |
26+
| `merges.txt` | Stores the merging rules for byte-pair encoding used in the text encoder. |
27+
| `ControlledUnet.mlmodelc` | Modified U-Net model incorporating control mechanisms from the ControlNet to steer output characteristics. |
28+
| `ControlledUnetChunk1.mlmodelc` | First part of the controlled U-Net model designed for sequential or partitioned processing. |
29+
| `ControlledUnetChunk2.mlmodelc` | Second part of the controlled U-Net model completing the image synthesis process started by the first chunk. |
30+
| `controlnet/` | Directory containing various ControlNet models for different control scenarios. |
31+
| `MultilingualTextEncoderProjection.mlmodelc` | Specialized model for projecting multilingual text into a consistent vector space, supporting diverse language inputs. |
32+
1633
## Model set example
1734
[coreml-stable-diffusion-2-base](https://huggingface.co/pcuenq/coreml-stable-diffusion-2-base/blob/main/coreml-stable-diffusion-2-base_split_einsum_compiled.zip )
1835

1936
### Performance
2037

2138
The speed can be unpredictable. Sometimes a model will suddenly run a lot slower than before. It appears as if Core ML is trying to be smart in how to schedule things, but doesn’t always optimal.
2239

23-
## SwiftUI example [for the package](https://github.com/The-Igor/coreml-stable-diffusion-swift)
40+
## The package [source](https://github.com/The-Igor/coreml-stable-diffusion-swift)
2441

2542

26-
## Case study [Deploying Transformers on the Apple Neural Engine](https://machinelearning.apple.com/research/neural-engine-transformers)
43+
## Deploying Transformers on the Apple Neural Engine[Case study](https://machinelearning.apple.com/research/neural-engine-transformers)
2744

2845

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /