add demo

examples/inference/basic/basic.py

@@ -1,6 +1,10 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.configs.sample import SamplingParam
+from fastvideo.configs.sample import SamplingParam
+
+import os
+
+os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "VIDEO_SPARSE_ATTN"
 
 OUTPUT_PATH = "video_samples"
 def main():
@@ -8,30 +12,41 @@ def main():
     # model.
     # If a local path is provided, FastVideo will make a best effort
     # attempt to identify the optimal arguments.
+    model_name = "FastVideo/FastWan2.1-T2V-14B-Diffusers"
     generator = VideoGenerator.from_pretrained(
-        "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
+        model_name,
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
         use_fsdp_inference=True,
         dit_cpu_offload=False,
         vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
+        text_encoder_cpu_offload=False,
         # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
-        pin_cpu_memory=False,
+        pin_cpu_memory=True,
         # image_encoder_cpu_offload=False,
     )
 
-    # sampling_param = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
-    # sampling_param.num_frames = 45
-    # sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
+    sampling_param = SamplingParam.from_pretrained(model_name)
+    # sampling_param.image_path = "test.jpg"
+    # sampling_param.num_inference_steps = 0
     # Generate videos with the same simple API, regardless of GPU count
-    prompt = (
-        "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
-        "wide with interest. The playful yet serene atmosphere is complemented by soft "
-        "natural light filtering through the petals. Mid-shot, warm and cheerful tones."
-    )
-    video = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True)
+    i2v_prompt = "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
+    i2v_prompt = "A little girl is packing a suitcase and the contents starts flying out of the suitcase everywhere."
+    prompt = i2v_prompt
+    # prompt = (
+    #     "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
+    #     "wide with interest. The playful yet serene atmosphere is complemented by soft "
+    #     "natural light filtering through the petals. Mid-shot, warm and cheerful tones."
+    # )
+    results = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, sampling_param=sampling_param)
+    stage_names = results["stage_names"]
+    stage_execution_times = results["stage_execution_times"]
+    # print(logging_info)
+    print(stage_names)
+    print(stage_execution_times)
+
     # video = generator.generate_video(prompt, sampling_param=sampling_param, output_path="wan_t2v_videos/")
+    return
 
     # Generate another video with a different prompt, without reloading the
     # model!

examples/inference/basic/basic_dmd.py

@@ -31,6 +31,7 @@ def main():
     prompt = (
         "A neon-lit alley in futuristic Tokyo during a heavy rainstorm at night. The puddles reflect glowing signs in kanji, advertising ramen, karaoke, and VR arcades. A woman in a translucent raincoat walks briskly with an LED umbrella. Steam rises from a street food cart, and a cat darts across the screen. Raindrops are visible on the camera lens, creating a cinematic bokeh effect."
     )
+    prompt = "A vintage train snakes through the mountains, its plume of white steam rising dramatically against the jagged peaks. The cars glint in the late afternoon sun, their deep crimson and gold accents lending a touch of elegance. The tracks carve a precarious path along the cliffside, revealing glimpses of a roaring river far below. Inside, passengers peer out the large windows, their faces lit with awe as the landscape unfolds."
     start_time = time.perf_counter()
     video = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, sampling_param=sampling_param)
     end_time = time.perf_counter()
@@ -45,7 +46,7 @@ def main():
         "embodying the raw energy of the wild. Low angle, steady tracking shot, "
         "cinematic.")
     start_time = time.perf_counter()
-    video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True)
+    video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=False)
     end_time = time.perf_counter()
     gen_time2 = end_time - start_time