Instructions to use ussoewwin/CCSR-TensorRT-Engine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use ussoewwin/CCSR-TensorRT-Engine with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -19,6 +19,10 @@ pipeline_tag: image-to-image
|
|
| 19 |
|
| 20 |
High-fidelity **ConvRot INT8** quantized weights and ultra-fast **TensorRT RTX** execution engines for **CCSR (Creative Content Super-Resolution)**, designed for low-VRAM and real-time generative image upscaling in **ComfyUI**.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
---
|
| 23 |
|
| 24 |
## π Overview
|
|
@@ -64,7 +68,9 @@ Measurements conducted on an NVIDIA RTX 4090 / RTX 5090 environment:
|
|
| 64 |
|
| 65 |
## π Usage in ComfyUI
|
| 66 |
|
| 67 |
-
Support for both **ConvRot INT8** and **TensorRT Engine** execution is integrated into the
|
|
|
|
|
|
|
| 68 |
|
| 69 |
### Installation
|
| 70 |
|
|
@@ -99,5 +105,5 @@ git clone https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker.git
|
|
| 99 |
- **Original CCSR Implementation & Weights**: [csslc/CCSR](https://github.com/csslc/CCSR) (Apache-2.0 License)
|
| 100 |
- **Research Paper**: *"Creative Content Super-Resolution with Pre-trained Diffusion Model"* by Liang et al.
|
| 101 |
- **ComfyUI CCSR Node Foundation**: [kijai/ComfyUI-CCSR](https://github.com/kijai/ComfyUI-CCSR) & [Kijai/ccsr-safetensors](https://huggingface.co/Kijai/ccsr-safetensors) (Apache-2.0 License)
|
| 102 |
-
- **
|
| 103 |
- **License**: **Apache-2.0**
|
|
|
|
| 19 |
|
| 20 |
High-fidelity **ConvRot INT8** quantized weights and ultra-fast **TensorRT RTX** execution engines for **CCSR (Creative Content Super-Resolution)**, designed for low-VRAM and real-time generative image upscaling in **ComfyUI**.
|
| 21 |
|
| 22 |
+
> π¦ **ComfyUI Loader & Upscaler Extension:**
|
| 23 |
+
> All nodes supporting both ConvRot INT8 and TensorRT execution are hosted in:
|
| 24 |
+
> π **[https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker](https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker)**
|
| 25 |
+
|
| 26 |
---
|
| 27 |
|
| 28 |
## π Overview
|
|
|
|
| 68 |
|
| 69 |
## π Usage in ComfyUI
|
| 70 |
|
| 71 |
+
Support for both **ConvRot INT8** and **TensorRT Engine** execution is integrated natively into the dedicated loader extension:
|
| 72 |
+
|
| 73 |
+
* **ComfyUI Extension / Loader Repository:** [https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker](https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker)
|
| 74 |
|
| 75 |
### Installation
|
| 76 |
|
|
|
|
| 105 |
- **Original CCSR Implementation & Weights**: [csslc/CCSR](https://github.com/csslc/CCSR) (Apache-2.0 License)
|
| 106 |
- **Research Paper**: *"Creative Content Super-Resolution with Pre-trained Diffusion Model"* by Liang et al.
|
| 107 |
- **ComfyUI CCSR Node Foundation**: [kijai/ComfyUI-CCSR](https://github.com/kijai/ComfyUI-CCSR) & [Kijai/ccsr-safetensors](https://huggingface.co/Kijai/ccsr-safetensors) (Apache-2.0 License)
|
| 108 |
+
- **ComfyUI Loader & TRT Integration**: [ussoewwin/ComfyUI-NunchakuFluxLoraStacker](https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker) (CCSR nodes located under `nodes/CCSR/`)
|
| 109 |
- **License**: **Apache-2.0**
|