Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -83,6 +83,10 @@ git clone https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker.git
|
|
| 83 |
|
| 84 |
### Method 1: ConvRot INT8 (PyTorch Execution)
|
| 85 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
1. Place `real-world_ccsr_convrot_int8.safetensors` in:
|
| 87 |
- `ComfyUI/models/checkpoints/` (for `CCSR_Model_Select`) or
|
| 88 |
- `ComfyUI/models/CCSR/` (for `DownloadAndLoadCCSRModel`)
|
|
@@ -92,6 +96,10 @@ git clone https://github.com/ussoewwin/ComfyUI-NunchakuFluxLoraStacker.git
|
|
| 92 |
|
| 93 |
### Method 2: TensorRT RTX Engine (Ultra-Fast Execution)
|
| 94 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
1. Place both `ccsr_apply_f16io.rtxplan` and `ccsr_trt_aux.safetensors` into:
|
| 96 |
- `ComfyUI/custom_nodes/ComfyUI-NunchakuFluxLoraStacker/nodes/CCSR/trt_engines/`
|
| 97 |
2. In ComfyUI, add **`Load CCSR Model (TensorRT)`** (`LoadCCSRModelTensorRT`). The node populates the dropdown with available `.rtxplan` engines and automatically loads the companion `ccsr_trt_aux.safetensors`.
|
|
|
|
| 83 |
|
| 84 |
### Method 1: ConvRot INT8 (PyTorch Execution)
|
| 85 |
|
| 86 |
+
<p align="center">
|
| 87 |
+
<img src="https://huggingface.co/ussoewwin/CCSR-ConvRot-INT8-and-TensorRT-Engine/resolve/main/png/ccsr.png" alt="CCSR PyTorch / ConvRot INT8 Workflow in ComfyUI" width="800">
|
| 88 |
+
</p>
|
| 89 |
+
|
| 90 |
1. Place `real-world_ccsr_convrot_int8.safetensors` in:
|
| 91 |
- `ComfyUI/models/checkpoints/` (for `CCSR_Model_Select`) or
|
| 92 |
- `ComfyUI/models/CCSR/` (for `DownloadAndLoadCCSRModel`)
|
|
|
|
| 96 |
|
| 97 |
### Method 2: TensorRT RTX Engine (Ultra-Fast Execution)
|
| 98 |
|
| 99 |
+
<p align="center">
|
| 100 |
+
<img src="https://huggingface.co/ussoewwin/CCSR-ConvRot-INT8-and-TensorRT-Engine/resolve/main/png/ccsrtensor.png" alt="CCSR TensorRT RTX Engine Workflow in ComfyUI" width="800">
|
| 101 |
+
</p>
|
| 102 |
+
|
| 103 |
1. Place both `ccsr_apply_f16io.rtxplan` and `ccsr_trt_aux.safetensors` into:
|
| 104 |
- `ComfyUI/custom_nodes/ComfyUI-NunchakuFluxLoraStacker/nodes/CCSR/trt_engines/`
|
| 105 |
2. In ComfyUI, add **`Load CCSR Model (TensorRT)`** (`LoadCCSRModelTensorRT`). The node populates the dropdown with available `.rtxplan` engines and automatically loads the companion `ccsr_trt_aux.safetensors`.
|