Update Download Links
Browse files
README.md
CHANGED
|
@@ -1,115 +1 @@
|
|
| 1 |
-
--
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
language:
|
| 4 |
-
- en
|
| 5 |
-
---
|
| 6 |
-
|
| 7 |
-
<p align="center" width="100%">
|
| 8 |
-
<img width="35%" src="Assets/Diffuse-Logo-512.png">
|
| 9 |
-
</p>
|
| 10 |
-
|
| 11 |
-
`Diffuse` is a Windows desktop UI for `Huggingface Diffusers`. It integrates directly with Python using the Python C API via `CSnakes`, enabling high-performance interop between .NET and Python for running diffusion models.
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
[](https://github.com/TensorStack-AI/Diffuse/releases)
|
| 15 |
-
[](https://github.com/TensorStack-AI/Diffuse/releases)
|
| 16 |
-
[](https://github.com/TensorStack-AI/Diffuse/commits/master/)
|
| 17 |
-
[](https://discord.gg/ptgMMv36Xu)
|
| 18 |
-
---
|
| 19 |
-
|
| 20 |
-
[Project Github](https://github.com/TensorStack-AI/Diffuse) | [Download Latest Release](https://github.com/TensorStack-AI/Diffuse/releases) | [Discord](https://discord.gg/ptgMMv36Xu)
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
## Features
|
| 24 |
-
- Automatic installation of isolated portable Python
|
| 25 |
-
- Device-specific Python virtual environments
|
| 26 |
-
- Automatic model downloads from Huggingface repositories
|
| 27 |
-
|
| 28 |
-
---
|
| 29 |
-
|
| 30 |
-
## Supported Pipelines
|
| 31 |
-
- **Z-Image:** ZImagePipeline, ZImageImg2ImgPipeline
|
| 32 |
-
- **Qwen Image:** QwenImagePipeline, QwenImageImg2ImgPipeline, QwenImageEditPlusPipeline
|
| 33 |
-
- **FLUX.1:** FluxPipeline, FluxImg2ImgPipeline, FluxKontextPipeline, FluxControlNetPipeline
|
| 34 |
-
- **FLUX.2:** Flux2Pipeline
|
| 35 |
-
- **Chroma:** ChromaPipeline, ChromaImg2ImgPipeline
|
| 36 |
-
- **LTX-Video:** LTXPipeline, LTXImageToVideoPipeline
|
| 37 |
-
- **Wan Video:** WanPipeline, WanImageToVideoPipeline
|
| 38 |
-
- **CogVideoX:** CogVideoXPipeline, CogVideoXImageToVideoPipeline, CogVideoXVideoToVideoPipeline
|
| 39 |
-
- **Kandinsky5:** Kandinsky5T2IPipeline, Kandinsky5I2IPipeline, Kandinsky5T2VPipeline, Kandinsky5I2VPipeline
|
| 40 |
-
- **StableDiffusionXL:** StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, StableDiffusionXLControlNetPipeline, StableDiffusionXLControlNetImg2ImgPipeline
|
| 41 |
-
|
| 42 |
-
---
|
| 43 |
-
|
| 44 |
-
## Installation
|
| 45 |
-
|
| 46 |
-
1. Download and extract **Diffuse.zip**
|
| 47 |
-
*A fast SSD with plenty of free space is recommended, as model downloads can be large.*
|
| 48 |
-
|
| 49 |
-
2. Run **Diffuse.exe**
|
| 50 |
-
|
| 51 |
-
3. Load a model
|
| 52 |
-
Diffuse will automatically:
|
| 53 |
-
- Install an isolated portable Python runtime
|
| 54 |
-
- Create the required virtual environment
|
| 55 |
-
- Download the selected model from Hugging Face
|
| 56 |
-
|
| 57 |
-
### First-run notice
|
| 58 |
-
On first launch or when loading a model for the first time, setup may take several minutes while Python, dependencies, and model files are downloaded and initialized. This is expected behavior.
|
| 59 |
-
|
| 60 |
-
No manual Python setup is required.
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
---
|
| 64 |
-
|
| 65 |
-
## Project Roadmap
|
| 66 |
-
|
| 67 |
-
### Alpha
|
| 68 |
-
Proof of concept, Focus on core functionality.
|
| 69 |
-
- Portable Python installation and management
|
| 70 |
-
- Device-specific virtual environments
|
| 71 |
-
- Minimal but functional Windows UI
|
| 72 |
-
- Basic Diffusers pipeline support
|
| 73 |
-
|
| 74 |
-
### Beta
|
| 75 |
-
Focus on usability, stability, and feature expansion.
|
| 76 |
-
- Fully isolated Python execution
|
| 77 |
-
- Installer and deployment tooling
|
| 78 |
-
- Advanced UI and workflow options
|
| 79 |
-
- Upscaling and interpolation support
|
| 80 |
-
- Extractor pipeline support
|
| 81 |
-
- Stability, performance, and reliability improvements
|
| 82 |
-
|
| 83 |
-
---
|
| 84 |
-
|
| 85 |
-
## Screenshots
|
| 86 |
-
|
| 87 |
-
### TextToImage
|
| 88 |
-
<p align="center" width="100%">
|
| 89 |
-
<img src="Assets/Screenshots/TextToImage.png">
|
| 90 |
-
</p>
|
| 91 |
-
|
| 92 |
-
### ImageToImage
|
| 93 |
-
<p align="center" width="100%">
|
| 94 |
-
<img src="Assets/Screenshots/ImageToImage.png">
|
| 95 |
-
</p>
|
| 96 |
-
|
| 97 |
-
### ImageEdit
|
| 98 |
-
<p align="center" width="100%">
|
| 99 |
-
<img src="Assets/Screenshots/ImgeEdit.png">
|
| 100 |
-
</p>
|
| 101 |
-
|
| 102 |
-
### ImageEdit-Multi
|
| 103 |
-
<p align="center" width="100%">
|
| 104 |
-
<img src="Assets/Screenshots/ImgeEdit-Multi.png">
|
| 105 |
-
</p>
|
| 106 |
-
|
| 107 |
-
### TextToVideo
|
| 108 |
-
<p align="center" width="100%">
|
| 109 |
-
<img src="Assets/Screenshots/TextToVideo.png">
|
| 110 |
-
</p>
|
| 111 |
-
|
| 112 |
-
### ImageToVideo
|
| 113 |
-
<p align="center" width="100%">
|
| 114 |
-
<img src="Assets/Screenshots/ImageToVideo.png">
|
| 115 |
-
</p>
|
|
|
|
| 1 |
+
[Project Github](https://github.com/TensorStack-AI/Diffuse) | [Download Latest Release](https://github.com/TensorStack-AI/Diffuse/releases)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|