keijiro/UnityMLStableDiffusion
Fork: 54 Star: 598 (更新于 2024-11-02 16:35:38)
license: NOASSERTION
Language: C# .
Core ML Stable Diffusion on Unity
最后发布版本: 1.5.0 ( 2024-09-21 15:00:05)
Unity Core ML Stable Diffusion Plugin
Stable Diffusion plugin for Unity, based on Apple's Core ML port. You can run the model on-editor and at-runtime without needing any extra components.
System Requirements
- Unity 2023.1 or later
- Apple Silicon Mac (editor/runtime support) with macOS 13.1 or later
- iPad Pro with Apple silicon (runtime support) with iOS 16.2 or later
Although the plugin supports iOS, it requires huge amount of memory to run the model, so it only supports memory-rich iPad models.
How To Try
Before running the sample project, you must put the model files in the
Assets/StreamingAssets
directory.
- Clone or download the pre-converted Stable Diffusion 2 model repository.
- Copy the
split_einsum/compiled
directory intoAssets/StreamingAssets
. - Rename the directory to
StableDiffusion
.
It takes a long time (a few minutes) for the first run. After this initialization step, it only takes a few tens of seconds to generate an image.
Performance Considerations
You can change which processing unit it uses by switching the "Compute Units" property in the Tester component.
It depends on the device model to choose the best option:
- M1/M2 Mac and iOS: GPUs in those devices are not powerful enough, so you should select "CPU and NE" (Neural Engine) or "All".
- M1/M2 Pro/Max Mac: GPUs in those devices have enough processing power compared to NE, so "CPU and GPU" can be a better option.
When using "CPU and GPU" mode, you must use the "original" model instead of
the "split_einsum" model. Please overwrite the StreamingAssets/StableDiffusion
directory with the original/compiled
directory.
LCM (SD-Turbo) Support
You can use SD-Turbo or other LCMs (latent consistency models) with setting
Pipeline.Scheduler
to Lcm
. You might also have to change StepCount
to 1~4
and GuidanceScale
to 1~2. Please refer to the model description to know the
correct settings.
You can download the pre-converted SD-Turbo model from my Hugging Face repository.
Sample Projects
- Flipbook3: Running the image-to-image pipeline with a real-time 3D scene.
最近版本更新:(数据更新于 2024-10-11 07:01:50)
2024-09-21 15:00:05 1.5.0
2023-12-04 10:38:46 1.4.0
2023-04-30 22:11:33 1.3.0
2023-04-29 16:44:51 1.2.0
2023-03-29 22:54:30 1.1.0
2023-03-29 09:46:06 1.0.0
keijiro/UnityMLStableDiffusion同语言 C#最近更新仓库
2024-11-19 11:38:46 jellyfin/jellyfin
2024-11-15 10:33:01 DigitalRuby/IPBan
2024-11-13 04:41:56 dotnet/runtime
2024-11-07 00:43:03 huiyadanli/RevokeMsgPatcher
2024-11-06 13:04:33 Pik-4/HsMod
2024-11-05 02:46:31 microsoft/PowerToys