[misc]: remove incidental comments from main

examples/inference/basic/basic.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples"
 
@@ -19,7 +18,6 @@ def main():
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-        # image_encoder_cpu_offload=False,
     )
 
     # sampling_param = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
@@ -30,10 +28,7 @@ def main():
               "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)
-    # video = generator.generate_video(prompt, sampling_param=sampling_param, output_path="wan_t2v_videos/")
 
-    # Generate another video with a different prompt, without reloading the
-    # model!
     prompt2 = ("A majestic lion strides across the golden savanna, its powerful frame "
                "glistening under the warm afternoon sun. The tall grass ripples gently in "
                "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "

examples/inference/basic/basic_cosmos2_5_t2w.py

@@ -16,7 +16,6 @@ def main():
         pin_cpu_memory=True,
     )
 
-    # Load default sampling parameters (negative_prompt, resolution, steps, etc.)
     sampling_param = SamplingParam.from_pretrained(model_path)
 
     prompt = (

examples/inference/basic/basic_dmd.py

@@ -38,8 +38,6 @@ def main():
     end_time = time.perf_counter()
     gen_time = end_time - start_time
 
-    # Generate another video with a different prompt, without reloading the
-    # model!
     prompt2 = ("A majestic lion strides across the golden savanna, its powerful frame "
                "glistening under the warm afternoon sun. The tall grass ripples gently in "
                "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "

examples/inference/basic/basic_hy15.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 import json
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_hy15"
 
@@ -19,7 +18,6 @@ def main():
         vae_cpu_offload=True,
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-        # image_encoder_cpu_offload=False,
     )
 
     prompt = ("A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "

examples/inference/basic/basic_hy15_1080p.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 import json
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_hy15_1080p"
 
@@ -20,7 +19,6 @@ def main():
         vae_cpu_offload=True,
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-        # image_encoder_cpu_offload=False,
     )
 
     prompt = ("A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "

examples/inference/basic/basic_hyworld.py

@@ -31,7 +31,6 @@ def main():
     print(f"Num frames: {args.num_frames}")
     print(f"Output path: {args.output_path}")
 
-    # Initialize generator
     print("\nInitializing VideoGenerator for HYWorld...")
     generator = VideoGenerator.from_pretrained(
         "FastVideo/HY-WorldPlay-Bidirectional-Diffusers",
@@ -44,7 +43,6 @@ def main():
         image_encoder_cpu_offload=True,
     )
 
-    # Generate video
     # The pose string is automatically converted to camera matrices by the pipeline
     print("\nGenerating video...")
     generator.generate_video(

examples/inference/basic/basic_kandinsky5_i2v.py

@@ -16,7 +16,6 @@ def main():
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     prompt = ("A woman stands up and walks away")

examples/inference/basic/basic_kandinsky5_t2v.py

@@ -15,7 +15,6 @@ def main():
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     prompt = ("A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "

examples/inference/basic/basic_lingbotworld_base_cam.py

@@ -1,7 +1,6 @@
 from fastvideo import VideoGenerator
 from fastvideo.models.dits.lingbotworld.cam_utils import prepare_camera_embedding
 
-# from fastvideo.api.sampling_param import SamplingParam
 OUTPUT_PATH = "video_samples_lingbotworld"
 
 
@@ -18,9 +17,7 @@ def main():
         dit_cpu_offload=True,  # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
-        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     num_frames = 81

examples/inference/basic/basic_ltx2_distilled_fast_profile.py

@@ -258,8 +258,6 @@ def main() -> None:
                 width=benchmark_entry.get("width", 1920),
                 num_frames=121,
                 num_inference_steps=5,
-                # image_path="examples/inference/basic/prompt1.png",
-                # ltx2_image_crf=0.0
             )
             if os.environ.get("FASTVIDEO_STAGE_LOGGING") == "0":
                 torch.cuda.synchronize()

examples/inference/basic/basic_matrixgame2.py

@@ -56,9 +56,7 @@ def main():
         dit_cpu_offload=True,  # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
-        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     num_frames = 597

examples/inference/basic/basic_matrixgame2_streaming.py

@@ -65,7 +65,6 @@ async def main():
         text_encoder_cpu_offload=True,
         # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     max_blocks = 50
@@ -99,7 +98,6 @@ async def main():
         if (await asyncio.to_thread(input, "\nContinue? (y/n): ")).lower() == 'n':
             break
 
-    # Save final video
     generator.finalize()
     generator.shutdown()
 

examples/inference/basic/basic_mps.py

@@ -17,7 +17,6 @@ def main():
         num_gpus=1,
     )
 
-    # Create sampling parameters with reduced number of frames
     sampling_param = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
     sampling_param.num_frames = 25  # Reduce from default 81 to 25 frames bc we have to use the SDPA attn backend for mps
     sampling_param.height = 256

examples/inference/basic/basic_ray.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples"
 
@@ -20,17 +19,13 @@ def main():
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
         distributed_executor_backend="ray",
-        # image_encoder_cpu_offload=False,
     )
 
-    # 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)
 
-    # Generate another video with a different prompt, without reloading the
-    # model!
     prompt2 = ("A majestic lion strides across the golden savanna, its powerful frame "
                "glistening under the warm afternoon sun. The tall grass ripples gently in "
                "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "

examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py

@@ -2,7 +2,6 @@
 
 from fastvideo import VideoGenerator, SamplingParam
 import json
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_i2v"
 
@@ -22,9 +21,7 @@ def main():
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
         dmd_denoising_steps=[1000, 850, 700, 550, 350, 275, 200, 125],
-        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     sampling_param = SamplingParam.from_pretrained("FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers")

examples/inference/basic/basic_self_forcing_causal_wan2_2_t2v.py

@@ -2,7 +2,6 @@
 
 from fastvideo import VideoGenerator
 
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_t2v"
 
@@ -28,7 +27,6 @@ def main():
         init_weights_from_safetensors_2=
         "/mnt/sharefs/users/hao.zhang/wei/SFwan2.2_distill_self_forcing_release_cfg2/checkpoint-246_weight_only/generator_2_inference_transformer/",
         num_frame_per_block=7,
-        # image_encoder_cpu_offload=False,
     )
 
     # sampling_param = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")

examples/inference/basic/basic_wan2_2.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_wan2_2_14B_t2v"
 
@@ -20,7 +19,6 @@ def main():
         text_encoder_cpu_offload=True,
         # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     # sampling_param = SamplingParam.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
@@ -36,10 +34,7 @@ def main():
                                  height=720,
                                  width=1280,
                                  num_frames=81)
-    # video = generator.generate_video(prompt, sampling_param=sampling_param, output_path="wan_t2v_videos/")
 
-    # Generate another video with a different prompt, without reloading the
-    # model!
     prompt2 = ("A majestic lion strides across the golden savanna, its powerful frame "
                "glistening under the warm afternoon sun. The tall grass ripples gently in "
                "the breeze, enhancing the lion's commanding presence. The tone is vibrant, "

examples/inference/basic/basic_wan2_2_Fun.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_wan2_1_Fun"
 OUTPUT_NAME = "wan2.1_test"
@@ -22,13 +21,10 @@ def main():
         text_encoder_cpu_offload=True,
         # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     prompt = "一位年轻女性穿着一件粉色的连衣裙，裙子上有白色的装饰和粉色的纽扣。她的头发是紫色的，头上戴着一个红色的大蝴蝶结，显得非常可爱和精致。她还戴着一个红色的领结，整体造型充满了少女感和活力。她的表情温柔，双手轻轻交叉放在身前，姿态优雅。背景是简单的灰色，没有任何多余的装饰，使得人物更加突出。她的妆容清淡自然，突显了她的清新气质。整体画面给人一种甜美、梦幻的感觉，仿佛置身于童话世界中。"
     negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
-    # prompt                  = "A young woman with beautiful, clear eyes and blonde hair stands in the forest, wearing a white dress and a crown. Her expression is serene, reminiscent of a movie star, with fair and youthful skin. Her brown long hair flows in the wind. The video quality is very high, with a clear view. High quality, masterpiece, best quality, high resolution, ultra-fine, fantastical."
-    # negative_prompt         = "Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code."
     image_path = "https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/wan_fun/asset_Wan2_2/v1.0/8.png"
     control_video_path = "https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/wan_fun/asset_Wan2_2/v1.0/pose.mp4"
 

examples/inference/basic/basic_wan2_2_i2v.py

@@ -1,6 +1,5 @@
 from fastvideo import VideoGenerator
 
-# from fastvideo.api.sampling_param import SamplingParam
 
 OUTPUT_PATH = "video_samples_wan2_2_14B_i2v"
 
@@ -18,9 +17,7 @@ def main():
         dit_cpu_offload=True,  # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
-        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
         pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
     )
 
     prompt = "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."

examples/inference/basic/basic_wan2_2_ti2v.py

@@ -18,7 +18,6 @@ def main():
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-        # image_encoder_cpu_offload=False,
     )
 
     # I2V is triggered just by passing in an image_path argument
@@ -26,8 +25,6 @@ def main():
     image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
     video = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, image_path=image_path)
 
-    # Generate another video with a different prompt, without reloading the
-    # model!
 
     # T2V mode
     prompt2 = ("A majestic lion strides across the golden savanna, its powerful frame "