Update README.md

I2V/Wan2_1-I2V-14B-MAGREF_fp8_e5m2_scaled_KJ.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19705674087aee231a64ed9c6a76005a63c169818de534eac979184248ab2ae9
+size 136

README.md

@@ -1,11 +1,12 @@
 ---
+tags:
+- diffusion-single-file
+- comfyui
 license: apache-2.0
----
 base_model:
 - Wan-AI/Wan2.1-VACE-14B
 - Wan-AI/Wan2.1-VACE-1.3B
 ---
-
 Better fp8 scaled models (when measured against fp16) based on quantization code from https://github.com/Tencent-Hunyuan/HunyuanVideo/blob/main/hyvideo/modules/fp8_optimization.py
 
 Can be used with: https://github.com/kijai/ComfyUI-WanVideoWrapper (latest version) and ComfyUI native WanVideo nodes.
@@ -22,4 +23,4 @@ Can be used with: https://github.com/kijai/ComfyUI-WanVideoWrapper (latest versi
 
 <video controls autoplay width=50% src=https://cdn-uploads.huggingface.co/production/uploads/63297908f0b2fc94904a65b8/GpuqQ4YwoR3kjxkhuvP8P.mp4></video>
 
-The e5m2 marked as v2 is the one uploaded here and these are all scaled even if I forgot to label properly.
+The e5m2 marked as v2 is the one uploaded here and these are all scaled even if I forgot to label properly.

T2V/Wan2_1-T2V-14B-Phantom_fp8_e4m3fn_scaled_KJ.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69ba52d41c6e70924f24b594cc89ebbe866161e0c12bead39c11274abb9988b
+size 136

T2V/Wan2_1-T2V-14B-Phantom_fp8_e5m2_scaled_KJ.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8288965266cc768d57334003355f92c687c5a30e83cfc47ce129f9b257dde9
+size 136