⚙️ RunPod Configuration
+🖼️ Input Image
+✨ Generation Parameters
+🚀 Execute
+ + + +Generating video... This may take a few minutes.
+diff --git a/Dockerfile b/Dockerfile index 464953c..14685f6 100644 --- a/Dockerfile +++ b/Dockerfile @@ -65,9 +65,10 @@ WORKDIR /tmp ENV EXT_PARALLEL=2 ENV NVCC_APPEND_FLAGS="--threads 2" ENV MAX_JOBS=4 -# Target RunPod GPU architectures: H100/H200(9.0) +# Target RunPod GPU architectures: +# 8.0 = A100, 8.6 = A10/RTX 3090, 8.9 = RTX 4090/L40, 9.0 = H100/H200 # Note: Blackwell (10.0) not yet supported by SageAttention -ENV TORCH_CUDA_ARCH_LIST="9.0" +ENV TORCH_CUDA_ARCH_LIST="8.0;8.6;8.9;9.0" RUN git clone https://github.com/thu-ml/SageAttention.git && \ cd SageAttention && \ pip install --no-build-isolation . && \ diff --git a/test-runpod.html b/test-runpod.html new file mode 100644 index 0000000..1327abe --- /dev/null +++ b/test-runpod.html @@ -0,0 +1,612 @@ + + +
+ + +Test your image-to-video generation API with custom parameters
+Generating video... This may take a few minutes.
+