update readme (#501)

README.md

@@ -42,39 +42,65 @@ uv pip install -v . # pip install -v .
 For attention operators installation, please refer to our documentation: **[English Docs](https://lightx2v-en.readthedocs.io/en/latest/getting_started/quickstart.html#step-4-install-attention-operators) | [中文文档](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/quickstart.html#id9)**
 
 ### Quick Start
+
 ```python
-# examples/hunyuan_video/hunyuan_t2v.py
+# examples/wan/wan_i2v.py
+"""
+Wan2.2 image-to-video generation example.
+This example demonstrates how to use LightX2V with Wan2.2 model for I2V generation.
+"""
+
 from lightx2v import LightX2VPipeline
 
+# Initialize pipeline for Wan2.2 I2V task
+# For wan2.1, use model_cls="wan2.1"
 pipe = LightX2VPipeline(
-    model_path="/path/to/ckpts/hunyuanvideo-1.5/",
-    model_cls="hunyuan_video_1.5",
-    transformer_model_name="720p_t2v",
-    task="t2v",
+    model_path="/path/to/Wan2.2-I2V-A14B",
+    model_cls="wan2.2_moe",
+    task="i2v",
+)
+
+# Alternative: create generator from config JSON file
+# pipe.create_generator(
+#     config_json="configs/wan22/wan_moe_i2v.json"
+# )
+
+# Enable offloading to significantly reduce VRAM usage with minimal speed impact
+# Suitable for RTX 30/40/50 consumer GPUs
+pipe.enable_offload(
+    cpu_offload=True,
+    offload_granularity="block",  # For Wan models, supports both "block" and "phase"
+    text_encoder_offload=True,
+    image_encoder_offload=False,
+    vae_offload=False,
 )
 
+# Create generator manually with specified parameters
 pipe.create_generator(
     attn_mode="sage_attn2",
-    infer_steps=50,
-    num_frames=121,
-    guidance_scale=6.0,
-    sample_shift=9.0,
-    aspect_ratio="16:9",
-    fps=24,
+    infer_steps=40,
+    height=480,  # Can be set to 720 for higher resolution
+    width=832,  # Can be set to 1280 for higher resolution
+    num_frames=81,
+    guidance_scale=[3.5, 3.5],  # For wan2.1, guidance_scale is a scalar (e.g., 5.0)
+    sample_shift=5.0,
 )
 
-seed = 123
-prompt = "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
-negative_prompt = ""
-save_result_path="/path/to/save_results/output.mp4"
+# Generation parameters
+seed = 42
+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."
+negative_prompt = "镜头晃动，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"
+image_path="/path/to/img_0.jpg"
+save_result_path = "/path/to/save_results/output.mp4"
 
+# Generate video
 pipe.generate(
     seed=seed,
+    image_path=image_path,
     prompt=prompt,
     negative_prompt=negative_prompt,
     save_result_path=save_result_path,
 )
-
 ```
 
 > 💡 **More Examples**: For more usage examples including quantization, offloading, caching, and other advanced configurations, please refer to the [examples directory](https://github.com/ModelTC/LightX2V/tree/main/examples).
@@ -98,13 +124,14 @@ pipe.generate(
 
 ### Lightweight Autoencoder Models (**🚀 Recommended: fast inference & low memory usage**)
 - ✅ [Autoencoders](https://huggingface.co/lightx2v/Autoencoders)
-🔔 Follow our [HuggingFace page](https://huggingface.co/lightx2v) for the latest model releases from our team.
 
 ### Autoregressive Models
 - ✅ [Wan2.1-T2V-CausVid](https://huggingface.co/lightx2v/Wan2.1-T2V-14B-CausVid)
 - ✅ [Self-Forcing](https://github.com/guandeh17/Self-Forcing)
 - ✅ [Matrix-Game-2.0](https://huggingface.co/Skywork/Matrix-Game-2.0)
 
+🔔 Follow our [HuggingFace page](https://huggingface.co/lightx2v) for the latest model releases from our team.
+
 💡 Refer to the [Model Structure Documentation](https://lightx2v-en.readthedocs.io/en/latest/getting_started/model_structure.html) to quickly get started with LightX2V
 
 ## 🚀 Frontend Interfaces

README_zh.md

@@ -44,33 +44,59 @@ uv pip install -v . # pip install -v .
 
 ### 快速开始
 ```python
-# examples/hunyuan_video/hunyuan_t2v.py
+# examples/wan/wan_i2v.py
+"""
+Wan2.2 image-to-video generation example.
+This example demonstrates how to use LightX2V with Wan2.2 model for I2V generation.
+"""
+
 from lightx2v import LightX2VPipeline
 
+# Initialize pipeline for Wan2.2 I2V task
+# For wan2.1, use model_cls="wan2.1"
 pipe = LightX2VPipeline(
-    model_path="/path/to/ckpts/hunyuanvideo-1.5/",
-    model_cls="hunyuan_video_1.5",
-    transformer_model_name="720p_t2v",
-    task="t2v",
+    model_path="/path/to/Wan2.2-I2V-A14B",
+    model_cls="wan2.2_moe",
+    task="i2v",
+)
+
+# Alternative: create generator from config JSON file
+# pipe.create_generator(
+#     config_json="configs/wan22/wan_moe_i2v.json"
+# )
+
+# Enable offloading to significantly reduce VRAM usage with minimal speed impact
+# Suitable for RTX 30/40/50 consumer GPUs
+pipe.enable_offload(
+    cpu_offload=True,
+    offload_granularity="block",  # For Wan models, supports both "block" and "phase"
+    text_encoder_offload=True,
+    image_encoder_offload=False,
+    vae_offload=False,
 )
 
+# Create generator manually with specified parameters
 pipe.create_generator(
     attn_mode="sage_attn2",
-    infer_steps=50,
-    num_frames=121,
-    guidance_scale=6.0,
-    sample_shift=9.0,
-    aspect_ratio="16:9",
-    fps=24,
+    infer_steps=40,
+    height=480,  # Can be set to 720 for higher resolution
+    width=832,  # Can be set to 1280 for higher resolution
+    num_frames=81,
+    guidance_scale=[3.5, 3.5],  # For wan2.1, guidance_scale is a scalar (e.g., 5.0)
+    sample_shift=5.0,
 )
 
-seed = 123
-prompt = "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
-negative_prompt = ""
-save_result_path="/path/to/save_results/output.mp4"
+# Generation parameters
+seed = 42
+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."
+negative_prompt = "镜头晃动，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"
+image_path="/path/to/img_0.jpg"
+save_result_path = "/path/to/save_results/output.mp4"
 
+# Generate video
 pipe.generate(
     seed=seed,
+    image_path=image_path,
     prompt=prompt,
     negative_prompt=negative_prompt,
     save_result_path=save_result_path,
@@ -97,13 +123,14 @@ pipe.generate(
 
 ### 轻量级自编码器模型(**🚀 推荐：推理快速 + 内存占用低**)
 - ✅ [Autoencoders](https://huggingface.co/lightx2v/Autoencoders)
-🔔 可以关注我们的[HuggingFace主页](https://huggingface.co/lightx2v)，及时获取我们团队的模型。
 
 ### 自回归模型
 - ✅ [Wan2.1-T2V-CausVid](https://huggingface.co/lightx2v/Wan2.1-T2V-14B-CausVid)
 - ✅ [Self-Forcing](https://github.com/guandeh17/Self-Forcing)
 - ✅ [Matrix-Game-2.0](https://huggingface.co/Skywork/Matrix-Game-2.0)
 
+🔔 可以关注我们的[HuggingFace主页](https://huggingface.co/lightx2v)，及时获取我们团队的模型。
+
 💡 参考[模型结构文档](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/model_structure.html)快速上手 LightX2V
 
 ## 🚀 前端展示

examples/README.md

@@ -63,7 +63,6 @@ Pass the model path to `LightX2VPipeline`:
 
 ```python
 pipe = LightX2VPipeline(
-    image_path="/path/to/img_0.jpg",  # Required for I2V tasks
     model_path="/path/to/Wan2.2-I2V-A14B",
     model_cls="wan2.2_moe",  # For wan2.1, use "wan2.1"
     task="i2v",

examples/README_zh.md

@@ -63,7 +63,6 @@ pipe.generate(
 
 ```python
 pipe = LightX2VPipeline(
-    image_path="/path/to/img_0.jpg",  # I2V 任务需要
     model_path="/path/to/Wan2.2-I2V-A14B",
     model_cls="wan2.2_moe",  # 对于 wan2.1，使用 "wan2.1"
     task="i2v",

examples/hunyuan_video/hunyuan_i2v.py

@@ -8,7 +8,6 @@ from lightx2v import LightX2VPipeline
 
 # Initialize pipeline for HunyuanVideo-1.5 I2V task
 pipe = LightX2VPipeline(
-    image_path="/path/to/assets/inputs/imgs/img_0.jpg",
     model_path="/path/to/ckpts/hunyuanvideo-1.5/",
     model_cls="hunyuan_video_1.5",
     transformer_model_name="720p_i2v",

examples/wan/wan_animate.py

@@ -31,9 +31,6 @@ from lightx2v import LightX2VPipeline
 # Initialize pipeline for animate task
 pipe = LightX2VPipeline(
     model_path="/path/to/Wan2.1-FLF2V-14B-720P",
-    src_pose_path="../save_results/animate/process_results/src_pose.mp4",
-    src_face_path="../save_results/animate/process_results/src_face.mp4",
-    src_ref_images="../save_results/animate/process_results/src_ref.png",
     model_cls="wan2.2_animate",
     task="animate",
 )
@@ -59,10 +56,16 @@ pipe.create_generator(
 seed = 42
 prompt = "视频中的人在做动作"
 negative_prompt = "镜头晃动，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"
+src_pose_path = "../save_results/animate/process_results/src_pose.mp4"
+src_face_path = "../save_results/animate/process_results/src_face.mp4"
+src_ref_images = "../save_results/animate/process_results/src_ref.png"
 save_result_path = "/path/to/save_results/output.mp4"
 
 pipe.generate(
     seed=seed,
+    src_pose_path=src_pose_path,
+    src_face_path=src_face_path,
+    src_ref_images=src_ref_images,
     prompt=prompt,
     negative_prompt=negative_prompt,
     save_result_path=save_result_path,

examples/wan/wan_flf2v.py

@@ -8,8 +8,6 @@ from lightx2v import LightX2VPipeline
 # Initialize pipeline for FLF2V task
 pipe = LightX2VPipeline(
     model_path="/path/to/Wan2.1-FLF2V-14B-720P",
-    image_path="../assets/inputs/imgs/flf2v_input_first_frame-fs8.png",
-    last_frame_path="../assets/inputs/imgs/flf2v_input_last_frame-fs8.png",
     model_cls="wan2.1",
     task="flf2v",
 )
@@ -43,9 +41,13 @@ pipe.create_generator(
 seed = 42
 prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings. The bird’s feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its flight and the vastness of the sky from a close-up, low-angle perspective."
 negative_prompt = "镜头晃动，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"
+image_path = "../assets/inputs/imgs/flf2v_input_first_frame-fs8.png"
+last_frame_path = "../assets/inputs/imgs/flf2v_input_last_frame-fs8.png"
 save_result_path = "/path/to/save_results/output.mp4"
 
 pipe.generate(
+    image_path=image_path,
+    last_frame_path=last_frame_path,
     seed=seed,
     prompt=prompt,
     negative_prompt=negative_prompt,

examples/wan/wan_i2v.py

@@ -8,7 +8,6 @@ from lightx2v import LightX2VPipeline
 # Initialize pipeline for Wan2.2 I2V task
 # For wan2.1, use model_cls="wan2.1"
 pipe = LightX2VPipeline(
-    image_path="/path/to/img_0.jpg",
     model_path="/path/to/Wan2.2-I2V-A14B",
     model_cls="wan2.2_moe",
     task="i2v",
@@ -44,11 +43,13 @@ pipe.create_generator(
 seed = 42
 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."
 negative_prompt = "镜头晃动，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"
+image_path = "/path/to/img_0.jpg"
 save_result_path = "/path/to/save_results/output.mp4"
 
 # Generate video
 pipe.generate(
     seed=seed,
+    image_path=image_path,
     prompt=prompt,
     negative_prompt=negative_prompt,
     save_result_path=save_result_path,

examples/wan/wan_i2v_distilled.py

@@ -8,7 +8,6 @@ from lightx2v import LightX2VPipeline
 # Initialize pipeline for Wan2.2 distilled I2V task
 # For wan2.1, use model_cls="wan2.1_distill"
 pipe = LightX2VPipeline(
-    image_path="/path/to/img_0.jpg",
     model_path="/path/to/wan2.2/Wan2.2-I2V-A14B",
     model_cls="wan2.2_moe_distill",
     task="i2v",
@@ -47,9 +46,11 @@ seed = 42
 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."
 negative_prompt = "镜头晃动，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"
 save_result_path = "/path/to/save_results/output.mp4"
+image_path = "/path/to/img_0.jpg"
 
 pipe.generate(
     seed=seed,
+    image_path=image_path,
     prompt=prompt,
     negative_prompt=negative_prompt,
     save_result_path=save_result_path,

examples/wan/wan_i2v_with_distill_loras.py

@@ -8,7 +8,6 @@ from lightx2v import LightX2VPipeline
 # Initialize pipeline for Wan2.2 distilled I2V task with LoRA
 # For wan2.1, use model_cls="wan2.1_distill"
 pipe = LightX2VPipeline(
-    image_path="/path/to/img_0.jpg",
     model_path="/path/to/wan2.2/Wan2.2-I2V-A14B",
     model_cls="wan2.2_moe_distill",
     task="i2v",
@@ -52,9 +51,11 @@ seed = 42
 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."
 negative_prompt = "镜头晃动，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"
 save_result_path = "/path/to/save_results/output.mp4"
+image_path = "/path/to/img_0.jpg"
 
 pipe.generate(
     seed=seed,
+    image_path=image_path,
     prompt=prompt,
     negative_prompt=negative_prompt,
     save_result_path=save_result_path,

lightx2v/pipeline.py

@@ -12,6 +12,13 @@ import torch
 import torch.distributed as dist
 from loguru import logger
 
+from lightx2v.models.runners.hunyuan_video.hunyuan_video_15_runner import HunyuanVideo15Runner  # noqa: F401
+from lightx2v.models.runners.qwen_image.qwen_image_runner import QwenImageRunner  # noqa: F401
+from lightx2v.models.runners.wan.wan_animate_runner import WanAnimateRunner  # noqa: F401
+from lightx2v.models.runners.wan.wan_audio_runner import Wan22AudioRunner, WanAudioRunner  # noqa: F401
+from lightx2v.models.runners.wan.wan_distill_runner import WanDistillRunner  # noqa: F401
+from lightx2v.models.runners.wan.wan_matrix_game2_runner import WanSFMtxg2Runner  # noqa: F401
+from lightx2v.models.runners.wan.wan_runner import Wan22MoeRunner, WanRunner  # noqa: F401
 from lightx2v.models.runners.wan.wan_sf_runner import WanSFRunner  # noqa: F401
 from lightx2v.models.runners.wan.wan_vace_runner import WanVaceRunner  # noqa: F401
 from lightx2v.utils.input_info import set_input_info
@@ -53,13 +60,7 @@ class LightX2VPipeline:
         task,
         model_path,
         model_cls,
-        image_path=None,
-        last_frame_path=None,
-        audio_path=None,
         sf_model_path=None,
-        src_ref_images=None,
-        src_video=None,
-        src_mask=None,
         dit_original_ckpt=None,
         low_noise_original_ckpt=None,
         high_noise_original_ckpt=None,
@@ -69,13 +70,6 @@ class LightX2VPipeline:
         self.model_path = model_path
         self.model_cls = model_cls
         self.sf_model_path = sf_model_path
-        self.image_path = image_path
-        self.last_frame_path = last_frame_path
-        self.audio_path = audio_path
-        self.src_ref_images = src_ref_images
-        self.src_video = src_video
-        self.src_mask = src_mask
-
         self.dit_original_ckpt = dit_original_ckpt
         self.low_noise_original_ckpt = low_noise_original_ckpt
         self.high_noise_original_ckpt = high_noise_original_ckpt
@@ -326,10 +320,23 @@ class LightX2VPipeline:
         prompt,
         negative_prompt,
         save_result_path,
+        image_path=None,
+        last_frame_path=None,
+        audio_path=None,
+        src_ref_images=None,
+        src_video=None,
+        src_mask=None,
         return_result_tensor=False,
     ):
         # Run inference (following LightX2V pattern)
         self.seed = seed
+
+        self.image_path = image_path
+        self.last_frame_path = last_frame_path
+        self.audio_path = audio_path
+        self.src_ref_images = src_ref_images
+        self.src_video = src_video
+        self.src_mask = src_mask
         self.prompt = prompt
         self.negative_prompt = negative_prompt
         self.save_result_path = save_result_path

scripts/hunyuan_video_15/README.md

@@ -17,7 +17,9 @@ docker run --gpus all -itd --ipc=host --name [container_name] -v [mount_settings
 
 Please follow the instructions in [HunyuanVideo1.5 Github](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/main/checkpoints-download.md) to download and place the model files.
 
-4. Run the script
+4. Running
+
+Running using bash script
 ```bash
 # enter the docker container
 
@@ -28,6 +30,70 @@ cd LightX2V/scripts/hunyuan_video_15
 bash run_hy15_t2v_480p.sh
 ```
 
+Running using Python code
+```python
+"""
+HunyuanVideo-1.5 text-to-video generation example.
+This example demonstrates how to use LightX2V with HunyuanVideo-1.5 model for T2V generation.
+"""
+
+from lightx2v import LightX2VPipeline
+
+# Initialize pipeline for HunyuanVideo-1.5
+pipe = LightX2VPipeline(
+    model_path="/path/to/ckpts/hunyuanvideo-1.5/",
+    model_cls="hunyuan_video_1.5",
+    transformer_model_name="720p_t2v",
+    task="t2v",
+)
+
+# Alternative: create generator from config JSON file
+# pipe.create_generator(config_json="configs/hunyuan_video_15/hunyuan_video_t2v_720p.json")
+
+# Enable offloading to significantly reduce VRAM usage with minimal speed impact
+# Suitable for RTX 30/40/50 consumer GPUs
+pipe.enable_offload(
+    cpu_offload=True,
+    offload_granularity="block",  # For HunyuanVideo-1.5, only "block" is supported
+    text_encoder_offload=True,
+    image_encoder_offload=False,
+    vae_offload=False,
+)
+
+# Use lighttae
+pipe.enable_lightvae(
+    use_tae=True,
+    tae_path="/path/to/lighttaehy1_5.safetensors",
+    use_lightvae=False,
+    vae_path=None,
+)
+
+# Create generator with specified parameters
+pipe.create_generator(
+    attn_mode="sage_attn2",
+    infer_steps=50,
+    num_frames=121,
+    guidance_scale=6.0,
+    sample_shift=9.0,
+    aspect_ratio="16:9",
+    fps=24,
+)
+
+# Generation parameters
+seed = 123
+prompt = "A close-up shot captures a scene on a polished, light-colored granite kitchen counter, illuminated by soft natural light from an unseen window. Initially, the frame focuses on a tall, clear glass filled with golden, translucent apple juice standing next to a single, shiny red apple with a green leaf still attached to its stem. The camera moves horizontally to the right. As the shot progresses, a white ceramic plate smoothly enters the frame, revealing a fresh arrangement of about seven or eight more apples, a mix of vibrant reds and greens, piled neatly upon it. A shallow depth of field keeps the focus sharply on the fruit and glass, while the kitchen backsplash in the background remains softly blurred. The scene is in a realistic style."
+negative_prompt = ""
+save_result_path = "/path/to/save_results/output.mp4"
+
+# Generate video
+pipe.generate(
+    seed=seed,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    save_result_path=save_result_path,
+)
+```
+
 5. Check results
 
 You can find the generated video files in the `save_results` folder.