Update README.md

README.md

@@ -44,18 +44,23 @@ fastvideo generate \
     --sp-size $num_gpus \
     --tp-size 1 \
     --num-gpus $num_gpus \
-    --height 720 \
-    --width 1280 \
-    --num-frames 81 \
+    --dit-cpu-offload False \
+    --vae-cpu-offload False \
+    --text-encoder-cpu-offload True \
+    --pin-cpu-memory False \
+    --height 448 \
+    --width 832 \
+    --num-frames 77 \
     --num-inference-steps 50 \
     --fps 16 \
-    --guidance-scale 4.0 \
+    --guidance-scale 5.0 \
     --flow-shift 5.0 \
     --VSA-sparsity 0.9 \
-    --prompt "A beautiful woman in a red dress walking down a street" \
+    --prompt-txt assets/prompt.txt \
     --negative-prompt "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards" \
     --seed 1024 \
-    --output-path VSA-DMD/sparsity_0.9/
+    --output-path outputs_Wan-VSA-14B/ \
+    --enable_torch_compile
 ```
 - Try it out on **FastVideo** — we support a wide range of GPUs from **H100** to **4090**
 - We use [FastVideo 720P Synthetic Wan dataset](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x768x1280_250k) for training.