martin-rizzo commited on
Commit
a5285b0
·
verified ·
1 Parent(s): 05d0b57

docs: Add acknowledgments section in README

Browse files

Added an "Acknowledgments" section to recognize PixArt-Sigma and Tiny AutoEncoder developers. This ensures proper credit is given for their foundational work.

Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -21,7 +21,7 @@ tags:
21
 
22
  **TinyBreaker** is a hybrid two-step model (base + refiner) designed for efficient image generation on mid-end and low-end hardware. By combining the strengths of PixArt and Photon models, it delivers high-quality images with strong prompt adherence
23
 
24
- ### Key Features
25
 
26
  - **Hybrid Two-Step Architecture**: Combines PixArt-Sigma as the base model with a refiner based on Photon (or any SD1.x model), both chosen for their low GPU consumption.
27
  - **Efficient Parameter Usage**: The base model’s 0.6 billion parameters enable high-quality image generation with minimal computational overhead.
@@ -29,7 +29,7 @@ tags:
29
  - **High Prompt Adherence**: Generates images that closely match user prompts and expectations, thanks to the robust performance of the PixArt-Sigma model and the T5 text encoder.
30
  - **Optimized Latent Space Processing**: Leverages Tiny Autoencoders for efficient latent space conversion.
31
 
32
- ### Current Usage
33
 
34
  Currently, TinyBreaker can only be used with ComfyUI. To utilize it, you'll need to install the custom nodes specific to this model through the [ComfyUI-TinyBreaker GitHub repository](https://github.com/martin-rizzo/ComfyUI-TinyBreaker).
35
 
@@ -46,3 +46,14 @@ Note: The current "Prototype1" version of TinyBreaker utilizes PixArt-Sigma 1024
46
  ## Future Directions
47
 
48
  I am dedicated to improving TinyBreaker's performance and accessibility, especially for users with mid-range or lower-end hardware. Looking forward to future updates as I continue to expand TinyBreaker's capabilities.
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  **TinyBreaker** is a hybrid two-step model (base + refiner) designed for efficient image generation on mid-end and low-end hardware. By combining the strengths of PixArt and Photon models, it delivers high-quality images with strong prompt adherence
23
 
24
+ ## Key Features
25
 
26
  - **Hybrid Two-Step Architecture**: Combines PixArt-Sigma as the base model with a refiner based on Photon (or any SD1.x model), both chosen for their low GPU consumption.
27
  - **Efficient Parameter Usage**: The base model’s 0.6 billion parameters enable high-quality image generation with minimal computational overhead.
 
29
  - **High Prompt Adherence**: Generates images that closely match user prompts and expectations, thanks to the robust performance of the PixArt-Sigma model and the T5 text encoder.
30
  - **Optimized Latent Space Processing**: Leverages Tiny Autoencoders for efficient latent space conversion.
31
 
32
+ ## Usage Requirements
33
 
34
  Currently, TinyBreaker can only be used with ComfyUI. To utilize it, you'll need to install the custom nodes specific to this model through the [ComfyUI-TinyBreaker GitHub repository](https://github.com/martin-rizzo/ComfyUI-TinyBreaker).
35
 
 
46
  ## Future Directions
47
 
48
  I am dedicated to improving TinyBreaker's performance and accessibility, especially for users with mid-range or lower-end hardware. Looking forward to future updates as I continue to expand TinyBreaker's capabilities.
49
+
50
+ ## Acknowledgments
51
+
52
+ I extend my sincere thanks to the PixArt-Σ developers for their exceptional model, which has been vital to this project's development.
53
+ * [PixArt-Σ GitHub Repository](https://github.com/PixArt-alpha/PixArt-sigma)
54
+ * [PixArt-Σ Hugging Face Model](https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS)
55
+ * [PixArt-Σ arXiv Report](https://arxiv.org/abs/2403.04692)
56
+
57
+ Additional thanks to Ollin Boer Bohan for the Tiny AutoEncoder models, which offer efficient latent image processing and served as the foundation for the encoding, decoding, and transcoding operations in TinyBreaker.
58
+ * [Tiny AutoEncoder GitHub Repository](https://github.com/madebyollin/taesd)
59
+