nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

Browse Source
This commit is contained in:
William Lin
2026-08-08 22:24:17 -07:00
committed by GitHub
parent 6eb95693a1
commit 9028953625
582 changed files with 19387 additions and 23526 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/inference/basic/basic.py
+12 -13
View File
@@ -3,6 +3,8 @@ from fastvideo import VideoGenerator
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -12,11 +14,11 @@ def main():
"Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=False,
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"
pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
# image_encoder_cpu_offload=False,
)
@@ -24,22 +26,19 @@ def main():
# sampling_param.num_frames = 45
# sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
# 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."
)
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)
# 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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True)
examples/inference/basic/basic_cosmos2_5_i2w.py
+1 -3
View File
@@ -30,8 +30,7 @@ def main():
"and casting reflections onto adjacent vehicles. "
"The motion creates space in the lineup, signaling activity within the otherwise quiet station. "
"It then comes to a smooth stop, resuming its position in line. "
"Overhead signage in Chinese characters remains illuminated, enhancing the vibrant, urban night scene."
)
"Overhead signage in Chinese characters remains illuminated, enhancing the vibrant, urban night scene.")
generator.generate_video(
prompt,
@@ -47,4 +46,3 @@ def main():
if __name__ == "__main__":
main()
examples/inference/basic/basic_cosmos2_5_t2w.py
+1 -5
View File
@@ -31,8 +31,7 @@ def main():
"The welding torch consistently emits sparks and light, and the smoke continues to rise, diffusing slightly as it moves upward. "
"The metal surface beneath the torch shows ongoing signs of heating and melting. "
"The scene retains its industrial ambiance, with the welding sparks and smoke dominating the visual field, "
"underscoring the ongoing nature of the welding operation."
)
"underscoring the ongoing nature of the welding operation.")
generator.generate_video(
prompt,
@@ -46,6 +45,3 @@ def main():
if __name__ == "__main__":
main()
examples/inference/basic/basic_cosmos2_5_v2w.py
-1
View File
@@ -50,4 +50,3 @@ def main():
if __name__ == "__main__":
main()
examples/inference/basic/basic_dmd.py
+9 -10
View File
@@ -5,6 +5,8 @@ from fastvideo import VideoGenerator
from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_dmd2"
def main():
os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "VIDEO_SPARSE_ATTN"
@@ -14,10 +16,10 @@ def main():
model_name,
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
# Adjust these offload parameters if you have < 32GB of VRAM
text_encoder_cpu_offload=True,
pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
dit_cpu_offload=False,
vae_cpu_offload=False,
VSA_sparsity=0.8,
@@ -25,7 +27,6 @@ def main():
load_end_time = time.perf_counter()
load_time = load_end_time - load_start_time
sampling_param = SamplingParam.from_pretrained(model_name)
sampling_param.num_frames = 81
@@ -39,18 +40,16 @@ def main():
# 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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
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, "
"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, num_frames=81)
end_time = time.perf_counter()
gen_time2 = end_time - start_time
print(f"Time taken to load model: {load_time} seconds")
print(f"Time taken to generate video: {gen_time} seconds")
print(f"Time taken to generate video2: {gen_time2} seconds")
examples/inference/basic/basic_dmd_new_api.py
+14 -20
View File
@@ -32,11 +32,9 @@ def main():
),
# PR 2 still routes a few advanced inference knobs through the
# compatibility bridge until they get first-class typed fields.
pipeline=PipelineSelection(
experimental={
"VSA_sparsity": 0.8,
},
),
pipeline=PipelineSelection(experimental={
"VSA_sparsity": 0.8,
}, ),
)
load_start_time = time.perf_counter()
@@ -44,14 +42,12 @@ def main():
load_end_time = time.perf_counter()
load_time = load_end_time - load_start_time
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 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.")
request = GenerationRequest(
prompt=prompt,
output=OutputConfig(
@@ -66,13 +62,11 @@ def main():
end_time = time.perf_counter()
gen_time = end_time - start_time
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, embodying the raw energy of the wild. Low angle, steady "
"tracking shot, cinematic."
)
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, embodying the raw energy of the wild. Low angle, steady "
"tracking shot, cinematic.")
request2 = GenerationRequest(
prompt=prompt2,
output=OutputConfig(
examples/inference/basic/basic_dreamx_world.py
+2 -5
View File
@@ -2,7 +2,6 @@ import os
from fastvideo import VideoGenerator
OUTPUT_PATH = os.getenv("DREAMX_WORLD_OUTPUT_PATH", "video_samples_dreamx_world")
@@ -46,10 +45,8 @@ def main():
"num_inference_steps": _env_int("DREAMX_WORLD_STEPS", 30),
"guidance_scale": _env_float("DREAMX_WORLD_GUIDANCE", 5.0),
"action_list": os.getenv("DREAMX_WORLD_ACTIONS", "w,d,w").split(","),
"action_speed_list": [
float(value)
for value in os.getenv("DREAMX_WORLD_ACTION_SPEEDS", "4.0,2.0,4.0").split(",")
],
"action_speed_list":
[float(value) for value in os.getenv("DREAMX_WORLD_ACTION_SPEEDS", "4.0,2.0,4.0").split(",")],
}
if image_path:
kwargs["image_path"] = image_path
examples/inference/basic/basic_flux2.py
+2 -6
View File
@@ -64,12 +64,8 @@ def main() -> None:
output = Path(args.output)
output.parent.mkdir(parents=True, exist_ok=True)
tp_size = args.tp_size if args.tp_size is not None else (
args.num_gpus if args.num_gpus > 1 else 1
)
sp_size = args.sp_size if args.sp_size is not None else (
1 if args.num_gpus > 1 else args.num_gpus
)
tp_size = args.tp_size if args.tp_size is not None else (args.num_gpus if args.num_gpus > 1 else 1)
sp_size = args.sp_size if args.sp_size is not None else (1 if args.num_gpus > 1 else args.num_gpus)
generator_config = GeneratorConfig(
model_path=args.model_path,
examples/inference/basic/basic_flux2_klein.py
-1
View File
@@ -21,7 +21,6 @@ from fastvideo.api import (
SamplingConfig,
)
DEFAULT_PROMPT = "a brushed steel espresso machine on a marble counter, morning window light"
examples/inference/basic/basic_flux_dev.py
+5 -11
View File
@@ -9,11 +9,9 @@ import re
DEFAULT_PROMPTS = [
"a photo of a cat",
(
"a cinematic photo of a red panda wearing a tiny backpack, standing on a "
"rainy neon-lit street at night, shallow depth of field, sharp focus, "
"35mm, bokeh"
),
("a cinematic photo of a red panda wearing a tiny backpack, standing on a "
"rainy neon-lit street at night, shallow depth of field, sharp focus, "
"35mm, bokeh"),
]
@@ -42,9 +40,7 @@ def _remove_existing_outputs(out_dir: str, filename_base: str) -> None:
def parse_args() -> argparse.Namespace:
p = argparse.ArgumentParser(
description="Run FLUX.1-dev text-to-image with FastVideo VideoGenerator.",
)
p = argparse.ArgumentParser(description="Run FLUX.1-dev text-to-image with FastVideo VideoGenerator.", )
p.add_argument(
"--model-path",
default="official_weights/FLUX.1-dev",
@@ -108,9 +104,7 @@ def main() -> None:
try:
for i, prompt in enumerate(prompts):
seed = args.seed + i
filename_base = (
f"flux_dev_{i:02d}_seed{seed}_{_safe_filename(prompt, max_len=80)}"
)
filename_base = (f"flux_dev_{i:02d}_seed{seed}_{_safe_filename(prompt, max_len=80)}")
_remove_existing_outputs(args.out_dir, filename_base)
output_path = os.path.join(args.out_dir, f"{filename_base}.png")
print(f"[flux] prompt_idx={i} seed={seed} output_path={output_path}")
examples/inference/basic/basic_gamecraft.py
+10 -11
View File
@@ -33,21 +33,20 @@ MODEL_PATH = os.environ.get("GAMECRAFT_MODEL_PATH", "FastVideo/HunyuanGameCraft-
# Default prompts for demo
DEFAULT_PROMPTS = {
"village": "A charming medieval village with cobblestone streets, thatched-roof houses, and vibrant flower gardens under a bright blue sky.",
"temple": "A majestic ancient temple stands under a clear blue sky, its grandeur highlighted by towering Doric columns and intricate architectural details.",
"forest": "A lush green forest with tall trees, dappled sunlight filtering through the leaves, and a winding dirt path.",
"village":
"A charming medieval village with cobblestone streets, thatched-roof houses, and vibrant flower gardens under a bright blue sky.",
"temple":
"A majestic ancient temple stands under a clear blue sky, its grandeur highlighted by towering Doric columns and intricate architectural details.",
"forest":
"A lush green forest with tall trees, dappled sunlight filtering through the leaves, and a winding dirt path.",
"beach": "A tropical beach with crystal clear turquoise water, white sand, and palm trees swaying in the breeze.",
}
# I2V: default reference image (URL). Can override with a local path.
DEFAULT_I2V_IMAGE_URL = (
"https://huggingface.co/datasets/huggingface/documentation-images/"
"resolve/main/diffusers/astronaut.jpg"
)
DEFAULT_I2V_PROMPT = (
"An astronaut hatching from an egg, on the surface of the moon, "
"the darkness and depth of space realised in the background."
)
DEFAULT_I2V_IMAGE_URL = ("https://huggingface.co/datasets/huggingface/documentation-images/"
"resolve/main/diffusers/astronaut.jpg")
DEFAULT_I2V_PROMPT = ("An astronaut hatching from an egg, on the surface of the moon, "
"the darkness and depth of space realised in the background.")
OUTPUT_PATH = "video_samples_gamecraft"
examples/inference/basic/basic_gen3c.py
+16 -32
View File
@@ -26,51 +26,35 @@ from fastvideo import VideoGenerator
def main():
parser = argparse.ArgumentParser(description="GEN3C video generation")
parser.add_argument("--model_path",
type=str,
default="converted_weights/GEN3C-Cosmos-7B")
parser.add_argument("--image_path",
type=str,
default=None,
help="Input image for 3D cache conditioning")
parser.add_argument("--prompt",
type=str,
default="A slow camera pan over a sunlit landscape.")
parser.add_argument("--model_path", type=str, default="converted_weights/GEN3C-Cosmos-7B")
parser.add_argument("--image_path", type=str, default=None, help="Input image for 3D cache conditioning")
parser.add_argument("--prompt", type=str, default="A slow camera pan over a sunlit landscape.")
parser.add_argument(
"--negative_prompt",
type=str,
default=(
"The video captures a series of frames showing ugly scenes, static with no motion, motion blur, "
"over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, "
"underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, "
"jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special "
"effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and "
"flickering. Overall, the video is of poor quality."
),
default=("The video captures a series of frames showing ugly scenes, static with no motion, motion blur, "
"over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, "
"underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, "
"jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special "
"effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and "
"flickering. Overall, the video is of poor quality."),
)
parser.add_argument("--trajectory",
type=str,
default="left",
choices=[
"left", "right", "up", "down", "zoom_in",
"zoom_out", "clockwise", "counterclockwise", "none"
])
parser.add_argument(
"--trajectory",
type=str,
default="left",
choices=["left", "right", "up", "down", "zoom_in", "zoom_out", "clockwise", "counterclockwise", "none"])
parser.add_argument("--movement_distance", type=float, default=0.3)
parser.add_argument("--camera_rotation",
type=str,
default="center_facing",
choices=[
"center_facing", "no_rotation",
"trajectory_aligned"
])
choices=["center_facing", "no_rotation", "trajectory_aligned"])
parser.add_argument("--height", type=int, default=704)
parser.add_argument("--width", type=int, default=1280)
parser.add_argument("--num_frames", type=int, default=121)
parser.add_argument("--num_inference_steps", type=int, default=35)
parser.add_argument("--guidance_scale", type=float, default=1.0)
parser.add_argument("--output_path",
type=str,
default="outputs_video/gen3c.mp4")
parser.add_argument("--output_path", type=str, default="outputs_video/gen3c.mp4")
parser.add_argument("--seed", type=int, default=42)
args = parser.parse_args()
examples/inference/basic/basic_hy15.py
+25 -16
View File
@@ -3,6 +3,8 @@ import json
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_hy15"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -12,31 +14,38 @@ def main():
"hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True,
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"
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 "
"wide with interest. The playful yet serene atmosphere is complemented by soft "
"natural light filtering through the petals. Mid-shot, warm and cheerful tones."
)
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, negative_prompt="", num_frames=81, fps=16)
video = generator.generate_video(prompt,
output_path=OUTPUT_PATH,
save_video=True,
negative_prompt="",
num_frames=81,
fps=16)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True, negative_prompt="", num_frames=81, fps=16)
video2 = generator.generate_video(prompt2,
output_path=OUTPUT_PATH,
save_video=True,
negative_prompt="",
num_frames=81,
fps=16)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_hy15_1080p.py
+13 -14
View File
@@ -3,38 +3,37 @@ import json
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_hy15_1080p"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
# If a local path is provided, FastVideo will make a best effort
# attempt to identify the optimal arguments.
generator = VideoGenerator.from_pretrained(
"weizhou03/HunyuanVideo-1.5-Diffusers-1080p-2SR", # 480p -> 720p -> 1080p
"weizhou03/HunyuanVideo-1.5-Diffusers-1080p-2SR", # 480p -> 720p -> 1080p
# or "weizhou03/HunyuanVideo-1.5-Diffusers-1080p" # 720p -> 1080p
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True,
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"
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 "
"wide with interest. The playful yet serene atmosphere is complemented by soft "
"natural light filtering through the petals. Mid-shot, warm and cheerful tones."
)
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, negative_prompt="")
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True, negative_prompt="")
examples/inference/basic/basic_hyworld.py
+2
View File
@@ -6,6 +6,8 @@ DEFAULT_PROMPT = 'A paved pathway leads towards a stone arch bridge spanning a c
DEFAULT_IMAGE = 'https://raw.githubusercontent.com/Tencent-Hunyuan/HY-WorldPlay/main/assets/img/test.png'
OUTPUT_PATH = "video_samples_hyworld"
def main():
import argparse
examples/inference/basic/basic_kandinsky5_i2v.py
+2 -4
View File
@@ -7,7 +7,7 @@ IMAGE_PATH = "assets/girl.png"
def main():
generator = VideoGenerator.from_pretrained(
"kandinskylab/Kandinsky-5.0-I2V-Pro-distilled-5s-Diffusers",
"kandinskylab/Kandinsky-5.0-I2V-Pro-distilled-5s-Diffusers",
# "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers"
# "kandinskylab/Kandinsky-5.0-I2V-Lite-5s-Diffusers"
num_gpus=1,
@@ -19,9 +19,7 @@ def main():
# image_encoder_cpu_offload=False,
)
prompt = (
"A woman stands up and walks away"
)
prompt = ("A woman stands up and walks away")
_ = generator.generate_video(
prompt,
image_path=IMAGE_PATH,
examples/inference/basic/basic_kandinsky5_t2v.py
+22 -14
View File
@@ -2,6 +2,7 @@ from fastvideo import VideoGenerator
OUTPUT_PATH = "video_samples_kandinsky5_t2v"
def main():
generator = VideoGenerator.from_pretrained(
"kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers",
@@ -17,21 +18,28 @@ def main():
# image_encoder_cpu_offload=False,
)
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."
)
_ = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True,height=512, width=768, num_frames=121)
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.")
_ = generator.generate_video(prompt,
output_path=OUTPUT_PATH,
save_video=True,
height=512,
width=768,
num_frames=121)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
_ = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True, height=512, width=768, num_frames=121)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
_ = generator.generate_video(prompt2,
output_path=OUTPUT_PATH,
save_video=True,
height=512,
width=768,
num_frames=121)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_lingbotworld2_causal_fast.py
-1
View File
@@ -6,7 +6,6 @@ from pathlib import Path
from fastvideo import VideoGenerator
REPO_ROOT = Path(__file__).resolve().parents[3]
DATASET_DIR = REPO_ROOT / "examples" / "dataset" / "lingbotworld2"
OUTPUT_PATH = REPO_ROOT / "outputs" / "lingbotworld2_causal_fast.mp4"
examples/inference/basic/basic_lingbotworld_base_cam.py
+5 -3
View File
@@ -3,17 +3,19 @@ from fastvideo.models.dits.lingbotworld.cam_utils import prepare_camera_embeddin
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_lingbotworld"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
# If a local path is provided, FastVideo will make a best effort
# attempt to identify the optimal arguments.
generator = VideoGenerator.from_pretrained(
"FastVideo/LingBot-World-Base-Cam-Diffusers",
"FastVideo/LingBot-World-Base-Cam-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
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
examples/inference/basic/basic_longcat_i2v.py
+28 -34
View File
@@ -21,20 +21,16 @@ import os
from fastvideo import VideoGenerator
# Common prompts and settings matching the shell script examples
PROMPT = (
"A woman sits at a wooden table by the window in a cozy café. She reaches out "
"with her right hand, picks up the white coffee cup from the saucer, and gently "
"brings it to her lips to take a sip. After drinking, she places the cup back on "
"the table and looks out the window, enjoying the peaceful atmosphere."
)
PROMPT = ("A woman sits at a wooden table by the window in a cozy café. She reaches out "
"with her right hand, picks up the white coffee cup from the saucer, and gently "
"brings it to her lips to take a sip. After drinking, she places the cup back on "
"the table and looks out the window, enjoying the peaceful atmosphere.")
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"
)
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")
# Input image path
IMAGE_PATH = "assets/girl.png"
@@ -51,20 +47,20 @@ def basic_generation():
print("=" * 60)
print("LongCat I2V: Basic Generation (50 steps, 480p)")
print("=" * 60)
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-I2V-Diffusers",
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=False,
vae_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=False,
enable_bsa=False,
)
output_path = "outputs_video/longcat_i2v_basic"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -79,7 +75,7 @@ def basic_generation():
guidance_scale=4.0,
seed=SEED,
)
print(f"\nBasic generation complete! Video saved to: {output_path}")
generator.shutdown()
@@ -94,11 +90,11 @@ def distill_refine_generation():
print("\n" + "=" * 60)
print("LongCat I2V: Distill + Refine Pipeline")
print("=" * 60)
# Stage 1: Distilled generation (16 steps at 480p)
print("\n[Stage 1] Distilled generation (16 steps, 480p)")
print("-" * 40)
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-I2V-Diffusers",
num_gpus=1,
@@ -111,9 +107,9 @@ def distill_refine_generation():
lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
lora_nickname="distilled",
)
distill_output_path = "outputs_video/longcat_i2v_distill"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -128,14 +124,14 @@ def distill_refine_generation():
guidance_scale=1.0,
seed=SEED,
)
print(f"Distilled generation complete! Video saved to: {distill_output_path}")
generator.shutdown()
# Stage 2: Refinement (480p -> 768p)
print("\n[Stage 2] Refinement (480p -> 768p with BSA)")
print("-" * 40)
# Find the actual saved video file from stage 1
video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
if not video_files:
@@ -143,7 +139,7 @@ def distill_refine_generation():
# Use the most recently created video file
distill_video_path = max(video_files, key=os.path.getmtime)
print(f"Using stage 1 video: {distill_video_path}")
# Create a new generator with refinement LoRA and BSA enabled
# Note: Refinement uses the T2V model (not I2V) since it's upscaling the generated video
# For BSA [4, 4, 8]: latent must be divisible by 8
@@ -163,9 +159,9 @@ def distill_refine_generation():
lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
lora_nickname="refinement",
)
refine_output_path = "outputs_video/longcat_i2v_refine_720p"
refine_generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -182,7 +178,7 @@ def distill_refine_generation():
guidance_scale=1.0,
seed=SEED,
)
print(f"Refinement complete! Video saved to: {refine_output_path}")
refine_generator.shutdown()
@@ -192,13 +188,13 @@ def main():
print("\n" + "=" * 60)
print("LongCat Image-to-Video Example")
print("=" * 60 + "\n")
# Run basic generation
basic_generation()
# Run distill+refine pipeline
distill_refine_generation()
print("\n" + "=" * 60)
print("All generations complete!")
print("=" * 60)
@@ -206,5 +202,3 @@ def main():
if __name__ == "__main__":
main()
examples/inference/basic/basic_longcat_t2v.py
+30 -36
View File
@@ -15,22 +15,18 @@ import os
from fastvideo import VideoGenerator
# Common prompts and settings matching the shell script examples
PROMPT = (
"In a realistic photography style, a white boy around seven or eight years old "
"sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. "
"He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a "
"medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, "
"who eagerly licks it with its tongue. The sun is shining brightly, and the background "
"features a green lawn and several tall trees, creating a warm and loving scene."
)
PROMPT = ("In a realistic photography style, a white boy around seven or eight years old "
"sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. "
"He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a "
"medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, "
"who eagerly licks it with its tongue. The sun is shining brightly, and the background "
"features a green lawn and several tall trees, creating a warm and loving scene.")
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"
)
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 = 42
@@ -44,20 +40,20 @@ def basic_generation():
print("=" * 60)
print("LongCat T2V: Basic Generation (50 steps, 480p)")
print("=" * 60)
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-T2V-Diffusers",
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=False,
vae_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=False,
enable_bsa=False,
)
output_path = "outputs_video/longcat_t2v_basic"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -71,7 +67,7 @@ def basic_generation():
guidance_scale=4.0,
seed=SEED,
)
print(f"\nBasic generation complete! Video saved to: {output_path}")
generator.shutdown()
@@ -86,11 +82,11 @@ def distill_refine_generation():
print("\n" + "=" * 60)
print("LongCat T2V: Distill + Refine Pipeline")
print("=" * 60)
# Stage 1: Distilled generation (16 steps at 480p)
print("\n[Stage 1] Distilled generation (16 steps, 480p)")
print("-" * 40)
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-T2V-Diffusers",
num_gpus=1,
@@ -103,9 +99,9 @@ def distill_refine_generation():
lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
lora_nickname="distilled",
)
distill_output_path = "outputs_video/longcat_t2v_distill"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -119,14 +115,14 @@ def distill_refine_generation():
guidance_scale=1.0,
seed=SEED,
)
print(f"Distilled generation complete! Video saved to: {distill_output_path}")
generator.shutdown()
# Stage 2: Refinement (480p -> 720p)
print("\n[Stage 2] Refinement (480p -> 720p with BSA)")
print("-" * 40)
# Find the actual saved video file from stage 1
video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
if not video_files:
@@ -134,7 +130,7 @@ def distill_refine_generation():
# Use the most recently created video file
distill_video_path = max(video_files, key=os.path.getmtime)
print(f"Using stage 1 video: {distill_video_path}")
# Create a new generator with refinement LoRA and BSA enabled
refine_generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-T2V-Diffusers",
@@ -151,9 +147,9 @@ def distill_refine_generation():
lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
lora_nickname="refinement",
)
refine_output_path = "outputs_video/longcat_t2v_refine_720p"
refine_generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -170,7 +166,7 @@ def distill_refine_generation():
guidance_scale=1.0,
seed=SEED,
)
print(f"Refinement complete! Video saved to: {refine_output_path}")
refine_generator.shutdown()
@@ -180,13 +176,13 @@ def main():
print("\n" + "=" * 60)
print("LongCat Text-to-Video Example")
print("=" * 60 + "\n")
# Run basic generation
basic_generation()
# Run distill+refine pipeline
distill_refine_generation()
print("\n" + "=" * 60)
print("All generations complete!")
print("=" * 60)
@@ -194,5 +190,3 @@ def main():
if __name__ == "__main__":
main()
examples/inference/basic/basic_longcat_vc.py
+35 -45
View File
@@ -21,21 +21,17 @@ import os
from fastvideo import VideoGenerator
# Common prompts and settings matching the shell script examples
PROMPT = (
"A person rides a motorcycle along a long, straight road that stretches between "
"a body of water and a forested hillside. The rider steadily accelerates, keeping "
"the motorcycle centered between the guardrails, while the scenery passes by on "
"both sides. The video captures the journey from the rider's perspective, emphasizing "
"the sense of motion and adventure."
)
PROMPT = ("A person rides a motorcycle along a long, straight road that stretches between "
"a body of water and a forested hillside. The rider steadily accelerates, keeping "
"the motorcycle centered between the guardrails, while the scenery passes by on "
"both sides. The video captures the journey from the rider's perspective, emphasizing "
"the sense of motion and adventure.")
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"
)
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")
# Input video path
VIDEO_PATH = "assets/motorcycle.mp4"
@@ -55,27 +51,25 @@ def basic_generation():
print("=" * 60)
print("LongCat VC: Basic Generation (50 steps, 480p)")
print("=" * 60)
# Check if video exists
if not os.path.exists(VIDEO_PATH):
raise FileNotFoundError(
f"Video not found at {VIDEO_PATH}. "
"Please provide a valid video path."
)
raise FileNotFoundError(f"Video not found at {VIDEO_PATH}. "
"Please provide a valid video path.")
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-VC-Diffusers",
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=False,
vae_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=False,
enable_bsa=False,
)
output_path = "outputs_video/longcat_vc_basic"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -91,7 +85,7 @@ def basic_generation():
guidance_scale=4.0,
seed=SEED,
)
print(f"\nBasic generation complete! Video saved to: {output_path}")
generator.shutdown()
@@ -106,18 +100,16 @@ def distill_refine_generation():
print("\n" + "=" * 60)
print("LongCat VC: Distill + Refine Pipeline")
print("=" * 60)
# Check if video exists
if not os.path.exists(VIDEO_PATH):
raise FileNotFoundError(
f"Video not found at {VIDEO_PATH}. "
"Please provide a valid video path."
)
raise FileNotFoundError(f"Video not found at {VIDEO_PATH}. "
"Please provide a valid video path.")
# Stage 1: Distilled generation (16 steps at 480p)
print("\n[Stage 1] Distilled generation (16 steps, 480p)")
print("-" * 40)
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-VC-Diffusers",
num_gpus=1,
@@ -130,9 +122,9 @@ def distill_refine_generation():
lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
lora_nickname="distilled",
)
distill_output_path = "outputs_video/longcat_vc_distill"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -148,14 +140,14 @@ def distill_refine_generation():
guidance_scale=1.0,
seed=SEED,
)
print(f"Distilled generation complete! Video saved to: {distill_output_path}")
generator.shutdown()
# Stage 2: Refinement (480p -> 720p)
print("\n[Stage 2] Refinement (480p -> 720p with BSA)")
print("-" * 40)
# Find the actual saved video file from stage 1
video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
if not video_files:
@@ -163,7 +155,7 @@ def distill_refine_generation():
# Use the most recently created video file
distill_video_path = max(video_files, key=os.path.getmtime)
print(f"Using stage 1 video: {distill_video_path}")
# Create a new generator with refinement LoRA and BSA enabled
# Note: Refinement uses the T2V model (not VC) since it's upscaling the generated video
refine_generator = VideoGenerator.from_pretrained(
@@ -181,9 +173,9 @@ def distill_refine_generation():
lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
lora_nickname="refinement",
)
refine_output_path = "outputs_video/longcat_vc_refine_720p"
refine_generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
@@ -200,7 +192,7 @@ def distill_refine_generation():
guidance_scale=1.0,
seed=SEED,
)
print(f"Refinement complete! Video saved to: {refine_output_path}")
refine_generator.shutdown()
@@ -210,13 +202,13 @@ def main():
print("\n" + "=" * 60)
print("LongCat Video Continuation Example")
print("=" * 60 + "\n")
# Run basic generation
basic_generation()
# Run distill+refine pipeline
distill_refine_generation()
print("\n" + "=" * 60)
print("All generations complete!")
print("=" * 60)
@@ -224,5 +216,3 @@ def main():
if __name__ == "__main__":
main()
examples/inference/basic/basic_ltx2.py
+12 -15
View File
@@ -1,19 +1,16 @@
from fastvideo import VideoGenerator
PROMPT = (
"A warm sunny backyard. The camera starts in a tight cinematic close-up "
"of a woman and a man in their 30s, facing each other with serious "
"expressions. The woman, emotional and dramatic, says softly, \"That's "
"it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
"annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
"then mutters defensively, \"He's just having fun.\" The camera slowly "
"pans right, revealing the grandfather in the garden wearing enormous "
"butterfly wings, waving his arms in the air like he's trying to take "
"off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
"The woman covers her face, on the verge of tears. The tone is deadpan, "
"absurd, and quietly tragic."
)
PROMPT = ("A warm sunny backyard. The camera starts in a tight cinematic close-up "
"of a woman and a man in their 30s, facing each other with serious "
"expressions. The woman, emotional and dramatic, says softly, \"That's "
"it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
"annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
"then mutters defensively, \"He's just having fun.\" The camera slowly "
"pans right, revealing the grandfather in the garden wearing enormous "
"butterfly wings, waving his arms in the air like he's trying to take "
"off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
"The woman covers her face, on the verge of tears. The tone is deadpan, "
"absurd, and quietly tragic.")
def main() -> None:
@@ -36,4 +33,4 @@ def main() -> None:
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_ltx2_3_distilled_i2v.py
+25 -39
View File
@@ -67,25 +67,19 @@ _inductor.coordinate_descent_tuning = True
_inductor.coordinate_descent_check_all_directions = True
_inductor.epilogue_fusion = False
MODEL_ID = os.path.expandvars(
os.path.expanduser(
os.getenv("LTX23_MODEL_PATH", "FastVideo/LTX-2.3-Distilled-Diffusers")
)
)
OUTPUT_DIR = Path(
os.getenv("LTX23_OUTPUT_DIR", "outputs_video/ltx2_3_distilled_i2v")
)
MODEL_ID = os.path.expandvars(os.path.expanduser(os.getenv("LTX23_MODEL_PATH",
"FastVideo/LTX-2.3-Distilled-Diffusers")))
OUTPUT_DIR = Path(os.getenv("LTX23_OUTPUT_DIR", "outputs_video/ltx2_3_distilled_i2v"))
I2V_IMAGE = os.getenv("LTX23_I2V_IMAGE", "")
DEFAULT_PROMPT = (
"A fashion model takes a slow step forward and shifts her weight, "
"the soft fabric of her clothing swaying and rippling with the "
"motion, her hair shifting gently, soft even studio lighting on a "
"clean light background, elegant slow-motion runway feel."
)
DEFAULT_PROMPT = ("A fashion model takes a slow step forward and shifts her weight, "
"the soft fabric of her clothing swaying and rippling with the "
"motion, her hair shifting gently, soft even studio lighting on a "
"clean light background, elegant slow-motion runway feel.")
PROMPT = os.getenv("LTX23_I2V_PROMPT", DEFAULT_PROMPT)
# Per-stage timing helpers --------------------------------------------------
def _print_stage_breakdown(result: dict, label: str) -> float | None:
"""Print stage execution times and return the sum, or None if missing."""
logging_info = result.get("logging_info")
@@ -114,9 +108,7 @@ def _collect_stage_times(
return
for name, metrics in stages.items():
stage_order.setdefault(name, None)
stage_times.setdefault(name, []).append(
float(metrics.get("execution_time", 0.0))
)
stage_times.setdefault(name, []).append(float(metrics.get("execution_time", 0.0)))
def _resolve_refine_upsampler(model_root: str) -> Path:
@@ -125,21 +117,18 @@ def _resolve_refine_upsampler(model_root: str) -> Path:
cand = Path(model_root) / name
if (cand / "config.json").is_file():
return cand
raise FileNotFoundError(
f"No refine upsampler directory under {model_root}. "
f"Expected `{model_root}/spatial_upscaler/config.json`."
)
raise FileNotFoundError(f"No refine upsampler directory under {model_root}. "
f"Expected `{model_root}/spatial_upscaler/config.json`.")
# Main ---------------------------------------------------------------------
def main() -> None:
if not I2V_IMAGE:
raise SystemExit(
"LTX23_I2V_IMAGE is required for i2v. Example:\n"
" export LTX23_I2V_IMAGE=/path/to/portrait_or_product.jpg\n"
" python examples/inference/basic/basic_ltx2_3_distilled_i2v.py"
)
raise SystemExit("LTX23_I2V_IMAGE is required for i2v. Example:\n"
" export LTX23_I2V_IMAGE=/path/to/portrait_or_product.jpg\n"
" python examples/inference/basic/basic_ltx2_3_distilled_i2v.py")
if not Path(I2V_IMAGE).is_file():
raise SystemExit(f"LTX23_I2V_IMAGE not found: {I2V_IMAGE}")
@@ -201,11 +190,13 @@ def main() -> None:
common_kwargs = dict(
prompt=PROMPT,
negative_prompt="", # distilled is CFG-free; no negative needed
guidance_scale=1.0, # CFG=1 for distilled
height=1280, width=832, # portrait runway aspect
num_frames=121, fps=24, # ~5s clip
num_inference_steps=8, # distilled denoise steps
negative_prompt="", # distilled is CFG-free; no negative needed
guidance_scale=1.0, # CFG=1 for distilled
height=1280,
width=832, # portrait runway aspect
num_frames=121,
fps=24, # ~5s clip
num_inference_steps=8, # distilled denoise steps
# i2v: anchor the input image at frame 0 with full strength.
# `ltx2_image_crf=0.0` skips an extra JPEG re-encode of an already
# JPEG conditioning image.
@@ -251,10 +242,7 @@ def main() -> None:
**common_kwargs,
)
wall = time.perf_counter() - t0
e2e = (
result.get("e2e_latency")
if isinstance(result, dict) else None
) or wall
e2e = (result.get("e2e_latency") if isinstance(result, dict) else None) or wall
measured_secs.append(e2e)
print(f"[measured {m + 1}/{measured_runs}] e2e={e2e:.2f}s wall={wall:.2f}s")
if isinstance(result, dict):
@@ -266,10 +254,8 @@ def main() -> None:
print(f"warmup wall-times: {[round(x, 1) for x in warmup_secs]}")
if measured_secs:
avg = sum(measured_secs) / len(measured_secs)
print(
f"measured e2e (n={len(measured_secs)}): "
f"{[round(x, 2) for x in measured_secs]} -> avg {avg:.2f}s"
)
print(f"measured e2e (n={len(measured_secs)}): "
f"{[round(x, 2) for x in measured_secs]} -> avg {avg:.2f}s")
if stage_times:
print(f"average stage times over {measured_runs} measured runs:")
avg_total = 0.0
examples/inference/basic/basic_ltx2_3_distilled_i2v_typed.py
+28 -64
View File
@@ -100,23 +100,14 @@ _inductor.coordinate_descent_tuning = True
_inductor.coordinate_descent_check_all_directions = True
_inductor.epilogue_fusion = False
MODEL_ID = os.path.expandvars(
os.path.expanduser(
os.getenv("LTX23_MODEL_PATH", "FastVideo/LTX-2.3-Distilled-Diffusers")
)
)
OUTPUT_DIR = Path(
os.getenv(
"LTX23_OUTPUT_DIR", "outputs_video/ltx2_3_distilled_i2v_typed"
)
)
MODEL_ID = os.path.expandvars(os.path.expanduser(os.getenv("LTX23_MODEL_PATH",
"FastVideo/LTX-2.3-Distilled-Diffusers")))
OUTPUT_DIR = Path(os.getenv("LTX23_OUTPUT_DIR", "outputs_video/ltx2_3_distilled_i2v_typed"))
I2V_IMAGE = os.getenv("LTX23_I2V_IMAGE", "")
DEFAULT_PROMPT = (
"A fashion model takes a slow step forward and shifts her weight, "
"the soft fabric of her clothing swaying and rippling with the "
"motion, her hair shifting gently, soft even studio lighting on a "
"clean light background, elegant slow-motion runway feel."
)
DEFAULT_PROMPT = ("A fashion model takes a slow step forward and shifts her weight, "
"the soft fabric of her clothing swaying and rippling with the "
"motion, her hair shifting gently, soft even studio lighting on a "
"clean light background, elegant slow-motion runway feel.")
PROMPT = os.getenv("LTX23_I2V_PROMPT", DEFAULT_PROMPT)
@@ -147,9 +138,7 @@ def _collect_stage_times(
return
for name, metrics in stages.items():
stage_order.setdefault(name, None)
stage_times.setdefault(name, []).append(
float(metrics.get("execution_time", 0.0))
)
stage_times.setdefault(name, []).append(float(metrics.get("execution_time", 0.0)))
def _resolve_refine_upsampler(model_root: str) -> Path:
@@ -157,20 +146,16 @@ def _resolve_refine_upsampler(model_root: str) -> Path:
cand = Path(model_root) / name
if (cand / "config.json").is_file():
return cand
raise FileNotFoundError(
f"No refine upsampler directory under {model_root}. "
f"Expected `{model_root}/spatial_upscaler/config.json`."
)
raise FileNotFoundError(f"No refine upsampler directory under {model_root}. "
f"Expected `{model_root}/spatial_upscaler/config.json`.")
def main() -> None:
if not I2V_IMAGE:
raise SystemExit(
"LTX23_I2V_IMAGE is required for i2v. Example:\n"
" export LTX23_I2V_IMAGE=/path/to/portrait_or_product.jpg\n"
" python examples/inference/basic/"
"basic_ltx2_3_distilled_i2v_typed.py"
)
raise SystemExit("LTX23_I2V_IMAGE is required for i2v. Example:\n"
" export LTX23_I2V_IMAGE=/path/to/portrait_or_product.jpg\n"
" python examples/inference/basic/"
"basic_ltx2_3_distilled_i2v_typed.py")
if not Path(I2V_IMAGE).is_file():
raise SystemExit(f"LTX23_I2V_IMAGE not found: {I2V_IMAGE}")
@@ -220,10 +205,9 @@ def main() -> None:
# model-specific VAE precision / decoder defaults are picked up
# the same way the legacy example's
# ``PipelineConfig.from_pretrained(model_root)`` did them.
components=ComponentConfig(
upsampler_weights=str(refine_upsampler_path),
# Distilled has no refine LoRA — omit ``lora_path``.
),
components=ComponentConfig(upsampler_weights=str(refine_upsampler_path),
# Distilled has no refine LoRA — omit ``lora_path``.
),
vae_tiling=False,
preset_overrides={
"refine": {
@@ -278,11 +262,7 @@ def main() -> None:
for w in range(warmup_runs):
print(f"\n[warmup {w + 1}/{warmup_runs}] compiling + generating…")
t0 = time.perf_counter()
generator.generate(
build_request(
OUTPUT_DIR / f"_warmup_{w + 1}.mp4", seed=7
)
)
generator.generate(build_request(OUTPUT_DIR / f"_warmup_{w + 1}.mp4", seed=7))
dt = time.perf_counter() - t0
warmup_secs.append(dt)
print(f"[warmup {w + 1}/{warmup_runs}] wall={dt:.1f}s")
@@ -291,46 +271,30 @@ def main() -> None:
(OUTPUT_DIR / f"_warmup_{w + 1}.mp4").unlink(missing_ok=True)
for m in range(measured_runs):
out_path = (
OUTPUT_DIR
/ f"output_ltx2_3_distilled_i2v_typed_run_{m + 1}.mp4"
)
print(
f"\n[measured {m + 1}/{measured_runs}] generating: {out_path}"
)
out_path = (OUTPUT_DIR / f"output_ltx2_3_distilled_i2v_typed_run_{m + 1}.mp4")
print(f"\n[measured {m + 1}/{measured_runs}] generating: {out_path}")
t0 = time.perf_counter()
result = generator.generate(
build_request(out_path, seed=2002 + m)
)
result = generator.generate(build_request(out_path, seed=2002 + m))
wall = time.perf_counter() - t0
# ``e2e_latency`` is currently surfaced via ``result.extra``;
# ``GenerationResult`` exposes ``generation_time`` as a
# first-class field but the LTX-2 pipeline only fills the
# legacy ``e2e_latency`` key. Prefer the explicit one, fall
# back to wall-clock.
e2e = (
result.extra.get("e2e_latency")
if hasattr(result, "extra") else None
) or wall
e2e = (result.extra.get("e2e_latency") if hasattr(result, "extra") else None) or wall
measured_secs.append(e2e)
print(
f"[measured {m + 1}/{measured_runs}] "
f"e2e={e2e:.2f}s wall={wall:.2f}s"
)
print(f"[measured {m + 1}/{measured_runs}] "
f"e2e={e2e:.2f}s wall={wall:.2f}s")
_print_stage_breakdown(result, f"measured {m + 1}")
_collect_stage_times(result, stage_times, stage_order)
print("\n=== summary ===")
print(
f"warmup wall-times: "
f"{[round(x, 1) for x in warmup_secs]}"
)
print(f"warmup wall-times: "
f"{[round(x, 1) for x in warmup_secs]}")
if measured_secs:
avg = sum(measured_secs) / len(measured_secs)
print(
f"measured e2e (n={len(measured_secs)}): "
f"{[round(x, 2) for x in measured_secs]} -> avg {avg:.2f}s"
)
print(f"measured e2e (n={len(measured_secs)}): "
f"{[round(x, 2) for x in measured_secs]} -> avg {avg:.2f}s")
if stage_times:
print(f"average stage times over {measured_runs} measured runs:")
avg_total = 0.0
examples/inference/basic/basic_ltx2_distilled.py
+13 -13
View File
@@ -1,21 +1,21 @@
from fastvideo import VideoGenerator
PROMPT = (
"A warm sunny backyard. The camera starts in a tight cinematic close-up "
"of a woman and a man in their 30s, facing each other with serious "
"expressions. The woman, emotional and dramatic, says softly, \"That's "
"it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
"annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
"then mutters defensively, \"He's just having fun.\" The camera slowly "
"pans right, revealing the grandfather in the garden wearing enormous "
"butterfly wings, waving his arms in the air like he's trying to take "
"off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
"The woman covers her face, on the verge of tears. The tone is deadpan, "
"absurd, and quietly tragic."
)
PROMPT = ("A warm sunny backyard. The camera starts in a tight cinematic close-up "
"of a woman and a man in their 30s, facing each other with serious "
"expressions. The woman, emotional and dramatic, says softly, \"That's "
"it... Dad's lost it. And we've lost Dad.\" The man exhales, slightly "
"annoyed: \"Stop being so dramatic, Jess.\" A beat. He glances aside, "
"then mutters defensively, \"He's just having fun.\" The camera slowly "
"pans right, revealing the grandfather in the garden wearing enormous "
"butterfly wings, waving his arms in the air like he's trying to take "
"off. He shouts, \"Wheeeew!\" as he flaps his wings with full commitment. "
"The woman covers her face, on the verge of tears. The tone is deadpan, "
"absurd, and quietly tragic.")
import os
os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "FLASH_ATTN"
def main() -> None:
generator = VideoGenerator.from_pretrained(
"FastVideo/LTX2-Distilled-Diffusers",
examples/inference/basic/basic_ltx2_distilled_fast_profile.py
+16 -34
View File
@@ -12,15 +12,11 @@ from fastvideo.configs.pipelines.base import PipelineConfig
from fastvideo.layers.quantization.nvfp4_config import NVFP4Config
from fastvideo.utils import maybe_download_model
VALIDATION_JSON = (
Path(__file__).resolve().parents[2] / "training" / "finetune" / "ltx2" / "validation.json"
)
VALIDATION_JSON = (Path(__file__).resolve().parents[2] / "training" / "finetune" / "ltx2" / "validation.json")
# Override with a local snapshot or converted directory when needed, e.g.
# export LTX2_MODEL_PATH=/raid/$USER/hf/FastVideo/LTX2-Distilled-Diffusers
MODEL_ID = os.path.expandvars(
os.path.expanduser(os.getenv("LTX2_MODEL_PATH", "FastVideo/LTX2-Distilled-Diffusers"))
)
MODEL_ID = os.path.expandvars(os.path.expanduser(os.getenv("LTX2_MODEL_PATH", "FastVideo/LTX2-Distilled-Diffusers")))
OUTPUT_DIR = Path("outputs_video/ltx2_distilled_fast_profile")
os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "FLASH_ATTN"
@@ -69,9 +65,7 @@ def print_stage_breakdown(
return total
def extract_sr_forward_latency(
result: dict,
) -> tuple[float | None, list[tuple[str, float]], list[str]]:
def extract_sr_forward_latency(result: dict, ) -> tuple[float | None, list[tuple[str, float]], list[str]]:
logging_info = result.get("logging_info")
if logging_info is None:
return None, [], []
@@ -89,12 +83,8 @@ def extract_sr_forward_latency(
if sr_match_substr:
is_sr_stage = sr_match_substr in stage_name_l
else:
is_sr_stage = (
"srdenoisingstage" in stage_name_l
or "sr_denoising" in stage_name_l
or "upsample" in stage_name_l
or ("refine" in stage_name_l and "denois" in stage_name_l)
)
is_sr_stage = ("srdenoisingstage" in stage_name_l or "sr_denoising" in stage_name_l
or "upsample" in stage_name_l or ("refine" in stage_name_l and "denois" in stage_name_l))
if not is_sr_stage:
continue
exec_time = float(stage_metrics.get("execution_time", 0.0))
@@ -161,11 +151,9 @@ def resolve_refine_upsampler_path(model_root: str) -> Path:
return candidate
checked = "\n".join(f" - {candidate}" for candidate in candidates)
raise FileNotFoundError(
"Could not find an LTX2 refine upsampler directory.\n"
"Checked:\n"
f"{checked}"
)
raise FileNotFoundError("Could not find an LTX2 refine upsampler directory.\n"
"Checked:\n"
f"{checked}")
def main() -> None:
@@ -314,19 +302,15 @@ def main() -> None:
measured_times = run_times[measured_start_idx:]
avg_time = sum(measured_times) / len(measured_times)
print(
f"Average video generation time over {len(measured_times)} runs "
f"(runs {measured_start_idx + 1}-{len(run_times)}, skipping first {warmup_runs} warmup runs): "
f"{avg_time:.2f}s"
)
print(f"Average video generation time over {len(measured_times)} runs "
f"(runs {measured_start_idx + 1}-{len(run_times)}, skipping first {warmup_runs} warmup runs): "
f"{avg_time:.2f}s")
measured_e2e_times = e2e_times[measured_start_idx:]
avg_e2e_time = sum(measured_e2e_times) / len(measured_e2e_times)
print(
f"Average end-to-end latency over {len(measured_e2e_times)} runs "
f"(runs {measured_start_idx + 1}-{len(e2e_times)}, skipping first {warmup_runs} warmup runs): "
f"{avg_e2e_time:.2f}s"
)
print(f"Average end-to-end latency over {len(measured_e2e_times)} runs "
f"(runs {measured_start_idx + 1}-{len(e2e_times)}, skipping first {warmup_runs} warmup runs): "
f"{avg_e2e_time:.2f}s")
if sr_forward_times:
avg_sr_forward = sum(sr_forward_times) / len(sr_forward_times)
@@ -338,10 +322,8 @@ def main() -> None:
if non_stage_overhead_times:
avg_non_stage_overhead = sum(non_stage_overhead_times) / len(non_stage_overhead_times)
print(
"Average non-stage overhead over "
f"{len(non_stage_overhead_times)} measured runs: {avg_non_stage_overhead:.3f}s"
)
print("Average non-stage overhead over "
f"{len(non_stage_overhead_times)} measured runs: {avg_non_stage_overhead:.3f}s")
else:
print("Average non-stage overhead unavailable (no stage timings).")
finally:
examples/inference/basic/basic_matrixgame2.py
+22 -12
View File
@@ -13,24 +13,34 @@ MODEL_VARIANT = "base_distilled_model"
# Variant-specific settings
VARIANT_CONFIG = {
"base_distilled_model": {
"model_path": "FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
"keyboard_dim": 4,
"image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
"model_path":
"FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
"keyboard_dim":
4,
"image_url":
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
},
"gta_distilled_model": {
"model_path": "FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers",
"keyboard_dim": 2,
"image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
"model_path":
"FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers",
"keyboard_dim":
2,
"image_url":
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
},
"templerun_distilled_model": {
"model_path": "FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers",
"keyboard_dim": 7,
"image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
"model_path":
"FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers",
"keyboard_dim":
7,
"image_url":
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
},
}
OUTPUT_PATH = "video_samples_matrixgame2"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -42,8 +52,8 @@ def main():
config["model_path"],
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
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
examples/inference/basic/basic_matrixgame2_streaming.py
+32 -22
View File
@@ -14,27 +14,40 @@ MODEL_VARIANT = "base_distilled_model"
# Variant-specific settings
VARIANT_CONFIG = {
"base_distilled_model": {
"model_path": "FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
"keyboard_dim": 4,
"mode": "universal",
"image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
"model_path":
"FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
"keyboard_dim":
4,
"mode":
"universal",
"image_url":
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
},
"gta_distilled_model": {
"model_path": "FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers",
"keyboard_dim": 2,
"mode": "gta_drive",
"image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
"model_path":
"FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers",
"keyboard_dim":
2,
"mode":
"gta_drive",
"image_url":
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
},
"templerun_distilled_model": {
"model_path": "FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers",
"keyboard_dim": 7,
"mode": "templerun",
"image_url": "https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
"model_path":
"FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers",
"keyboard_dim":
7,
"mode":
"templerun",
"image_url":
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
},
}
OUTPUT_PATH = "video_samples_matrixgame2"
async def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -46,8 +59,8 @@ async def main():
config["model_path"],
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
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
@@ -56,11 +69,8 @@ async def main():
)
max_blocks = 50
num_frames = 597
actions = {
"keyboard": torch.zeros((num_frames, config["keyboard_dim"])),
"mouse": torch.zeros((num_frames, 2))
}
num_frames = 597
actions = {"keyboard": torch.zeros((num_frames, config["keyboard_dim"])), "mouse": torch.zeros((num_frames, 2))}
grid_sizes = torch.tensor([150, 44, 80])
mode = config["mode"]
@@ -81,11 +91,11 @@ async def main():
for block_id in range(max_blocks):
print(f"\n=== Block {block_id + 1}/{max_blocks} ===")
action = await get_current_action_async(mode)
keyboard_cond, mouse_cond = expand_action_to_frames(action, 12)
await generator.step_async(keyboard_cond, mouse_cond)
if (await asyncio.to_thread(input, "\nContinue? (y/n): ")).lower() == 'n':
break
examples/inference/basic/basic_minimax_h3_t2v.py
+25 -23
View File
@@ -30,13 +30,15 @@ def parse_args() -> argparse.Namespace:
parser.add_argument("--steps", type=int, default=50)
parser.add_argument("--seed", type=int, default=0)
parser.add_argument("--num-gpus", type=int, default=4)
parser.add_argument("--torch-compile", action="store_true",
help="torch.compile the DiT transformer path")
parser.add_argument("--compile-mode", default=None,
parser.add_argument("--torch-compile", action="store_true", help="torch.compile the DiT transformer path")
parser.add_argument("--compile-mode",
default=None,
help='torch.compile mode, e.g. "reduce-overhead" for CUDA graphs')
parser.add_argument("--repeats", type=int, default=1,
parser.add_argument("--repeats",
type=int,
default=1,
help="generate N times; with --torch-compile the first run pays "
"compilation, so steady-state is the last repeat")
"compilation, so steady-state is the last repeat")
return parser.parse_args()
@@ -67,24 +69,24 @@ def main() -> None:
))
try:
request = GenerationRequest(
prompt=args.prompt,
negative_prompt="",
sampling=SamplingConfig(
height=args.height,
width=args.width,
num_frames=args.num_frames,
fps=24,
num_inference_steps=args.steps,
guidance_scale=1.0,
batch_cfg=False,
seed=args.seed,
),
output=OutputConfig(
output_path=str(output_dir / "minimax_h3_t2v.mp4"),
save_video=True,
return_frames=False,
),
)
prompt=args.prompt,
negative_prompt="",
sampling=SamplingConfig(
height=args.height,
width=args.width,
num_frames=args.num_frames,
fps=24,
num_inference_steps=args.steps,
guidance_scale=1.0,
batch_cfg=False,
seed=args.seed,
),
output=OutputConfig(
output_path=str(output_dir / "minimax_h3_t2v.mp4"),
save_video=True,
return_frames=False,
),
)
result = generator.generate(request)
print(f"Output written to: {result.video_path}")
if result.generation_time is not None:
examples/inference/basic/basic_mps.py
+17 -15
View File
@@ -1,19 +1,20 @@
from fastvideo import VideoGenerator, PipelineConfig
from fastvideo.api.sampling_param import SamplingParam
def main():
config = PipelineConfig.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
config.text_encoder_precisions = ["fp16"]
generator = VideoGenerator.from_pretrained(
"Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
pipeline_config=config,
use_fsdp_inference=False, # Disable FSDP for MPS
dit_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=True,
disable_autocast=False,
num_gpus=1,
use_fsdp_inference=False, # Disable FSDP for MPS
dit_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=True,
disable_autocast=False,
num_gpus=1,
)
# Create sampling parameters with reduced number of frames
@@ -23,18 +24,19 @@ def main():
sampling_param.width = 256
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.")
"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, sampling_param=sampling_param)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
"glistening under the warm afternoon sun. The tall grass ripples gently in "
"the breeze, enhancing the lion's commanding presence. The tone is vibrant, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(prompt2, sampling_param=sampling_param)
if __name__ == "__main__":
main()
examples/inference/basic/basic_ray.py
+11 -12
View File
@@ -3,6 +3,8 @@ from fastvideo import VideoGenerator
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -16,27 +18,24 @@ def main():
dit_cpu_offload=False,
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"
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."
)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True)
examples/inference/basic/basic_sd35_t2i.py
+3 -2
View File
@@ -7,7 +7,6 @@ import os
import re
from typing import List
DEFAULT_PROMPTS = [
"a photo of a cat",
"a cinematic photo of a red panda wearing a tiny backpack, standing on a rainy neon-lit street at night, shallow depth of field, sharp focus, 35mm, bokeh",
@@ -49,7 +48,9 @@ def _remove_existing_outputs(out_dir: str, filename_base: str) -> None:
def parse_args() -> argparse.Namespace:
p = argparse.ArgumentParser(description="Run SD3.5 Medium text-to-image with FastVideo VideoGenerator.")
p.add_argument("--model-path", default="stabilityai/stable-diffusion-3.5-medium", help="Path to local diffusers-format SD3.5 weights directory.")
p.add_argument("--model-path",
default="stabilityai/stable-diffusion-3.5-medium",
help="Path to local diffusers-format SD3.5 weights directory.")
p.add_argument(
"--out-dir",
"--outdir",
examples/inference/basic/basic_self_forcing_causal.py
+7 -6
View File
@@ -3,6 +3,8 @@ import time
from fastvideo import VideoGenerator, SamplingParam
OUTPUT_PATH = "video_samples_causal"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -13,19 +15,18 @@ def main():
model_name,
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
text_encoder_cpu_offload=False,
dit_cpu_offload=False,
)
sampling_param = SamplingParam.from_pretrained(model_name)
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."
)
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, sampling_param=sampling_param)
if __name__ == "__main__":
main()
examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py
+9 -3
View File
@@ -5,6 +5,8 @@ import json
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_i2v"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -14,8 +16,8 @@ def main():
"FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
dit_precision="fp32",
vae_cpu_offload=False,
text_encoder_cpu_offload=True,
@@ -37,7 +39,11 @@ def main():
for prompt_image_pair in prompt_image_pairs:
prompt = prompt_image_pair["prompt"]
image_path = prompt_image_pair["image_path"]
_ = generator.generate_video(prompt, image_path=image_path, output_path=OUTPUT_PATH, save_video=True, sampling_param=sampling_param)
_ = generator.generate_video(prompt,
image_path=image_path,
output_path=OUTPUT_PATH,
save_video=True,
sampling_param=sampling_param)
if __name__ == "__main__":
examples/inference/basic/basic_self_forcing_causal_wan2_2_t2v.py
+12 -10
View File
@@ -5,6 +5,8 @@ from fastvideo import VideoGenerator
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_t2v"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -14,15 +16,17 @@ def main():
"rand0nmr/SFWan2.2-T2V-A14B-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
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,
init_weights_from_safetensors="/mnt/sharefs/users/hao.zhang/wei/SFwan2.2_distill_self_forcing_release_cfg2/checkpoint-246_weight_only/generator_inference_transformer/",
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/",
init_weights_from_safetensors=
"/mnt/sharefs/users/hao.zhang/wei/SFwan2.2_distill_self_forcing_release_cfg2/checkpoint-246_weight_only/generator_inference_transformer/",
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,
)
@@ -31,13 +35,11 @@ def main():
# sampling_param.num_frames = 45
# sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
# 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."
)
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.")
_ = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, num_frames=81)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_stable_audio_inpaint.py
+5 -6
View File
@@ -54,16 +54,15 @@ PROMPT = "Steady lo-fi hip hop drum loop with vinyl crackle."
# ...) you want to extend or repair. The pipeline raises if a mask is
# passed without a reference, so this must be a real path.
REFERENCE_AUDIO_PATH = "path/to/your/loop.wav"
KEEP_SECONDS = 6.0 # first KEEP_SECONDS preserved exactly
TOTAL_SECONDS = 12.0 # extend the loop to this duration
KEEP_SECONDS = 6.0 # first KEEP_SECONDS preserved exactly
TOTAL_SECONDS = 12.0 # extend the loop to this duration
def main() -> None:
if not os.path.isfile(REFERENCE_AUDIO_PATH):
raise FileNotFoundError(
f"REFERENCE_AUDIO_PATH={REFERENCE_AUDIO_PATH!r} does not exist. "
"Edit this script to point at a real audio file (wav/mp3/mp4/"
"m4a/flac) before running.")
raise FileNotFoundError(f"REFERENCE_AUDIO_PATH={REFERENCE_AUDIO_PATH!r} does not exist. "
"Edit this script to point at a real audio file (wav/mp3/mp4/"
"m4a/flac) before running.")
generator = VideoGenerator.from_pretrained(
"FastVideo/stable-audio-open-1.0-Diffusers",
num_gpus=1,
examples/inference/basic/basic_turbodiffusion.py
+10 -14
View File
@@ -15,19 +15,17 @@ def main() -> None:
"loayrashid/TurboWan2.1-T2V-1.3B-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
# set to false if using RTX 4090
# set to false if using RTX 4090
# pin_cpu_memory=False,
)
# Generate videos with the same simple API, regardless of GPU count
# TurboDiffusion defaults: guidance_scale=1.0 and num_inference_steps=4 (from config)
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."
)
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,
@@ -36,13 +34,11 @@ def main() -> None:
)
# 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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic."
)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(
prompt2,
output_path=OUTPUT_PATH,
examples/inference/basic/basic_turbodiffusion_14b.py
+8 -12
View File
@@ -17,11 +17,9 @@ def main() -> None:
num_gpus=2,
)
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."
)
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,
@@ -30,13 +28,11 @@ def main() -> None:
)
# 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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic."
)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(
prompt2,
output_path=OUTPUT_PATH,
examples/inference/basic/basic_turbodiffusion_i2v.py
+3 -2
View File
@@ -18,12 +18,13 @@ def main() -> None:
)
# Example prompt and image for I2V
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.")
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."
)
# Use an example image path
image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
video = generator.generate_video(
prompt,
image_path=image_path,
examples/inference/basic/basic_wan2_2.py
+25 -16
View File
@@ -3,6 +3,8 @@ from fastvideo import VideoGenerator
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_wan2_2_14B_t2v"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -12,8 +14,8 @@ def main():
"Wan-AI/Wan2.2-T2V-A14B-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=2,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
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
@@ -25,24 +27,31 @@ def main():
# sampling_param.num_frames = 45
# sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
# 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."
)
_ = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, height=720, width=1280, num_frames=81)
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.")
_ = generator.generate_video(prompt,
output_path=OUTPUT_PATH,
save_video=True,
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
_ = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True, height=720, width=1280, num_frames=81)
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
_ = generator.generate_video(prompt2,
output_path=OUTPUT_PATH,
save_video=True,
height=720,
width=1280,
num_frames=81)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_wan2_2_Fun.py
+13 -4
View File
@@ -4,6 +4,8 @@ from fastvideo import VideoGenerator
OUTPUT_PATH = "video_samples_wan2_1_Fun"
OUTPUT_NAME = "wan2.1_test"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -14,8 +16,8 @@ def main():
# "alibaba-pai/Wan2.2-Fun-A14B-Control",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
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
@@ -30,7 +32,14 @@ def main():
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"
video = generator.generate_video(prompt, negative_prompt=negative_prompt, image_path=image_path, video_path=control_video_path, output_path=OUTPUT_PATH, output_video_name=OUTPUT_NAME, save_video=True)
video = generator.generate_video(prompt,
negative_prompt=negative_prompt,
image_path=image_path,
video_path=control_video_path,
output_path=OUTPUT_PATH,
output_video_name=OUTPUT_NAME,
save_video=True)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_wan2_2_i2v.py
+13 -4
View File
@@ -3,6 +3,8 @@ from fastvideo import VideoGenerator
# from fastvideo.api.sampling_param import SamplingParam
OUTPUT_PATH = "video_samples_wan2_2_14B_i2v"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -12,8 +14,8 @@ def main():
"Wan-AI/Wan2.2-I2V-A14B-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True, # DiT need to be offloaded for MoE
use_fsdp_inference=False, # set to True if GPU is out of memory
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
@@ -24,7 +26,14 @@ def main():
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."
image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
video = generator.generate_video(prompt, image_path=image_path, output_path=OUTPUT_PATH, save_video=True, height=832, width=480, num_frames=81)
video = generator.generate_video(prompt,
image_path=image_path,
output_path=OUTPUT_PATH,
save_video=True,
height=832,
width=480,
num_frames=81)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_wan2_2_ti2v.py
+10 -9
View File
@@ -1,6 +1,8 @@
from fastvideo import VideoGenerator
OUTPUT_PATH = "video_samples_wan2_2_5B_ti2v"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
@@ -11,11 +13,11 @@ def main():
model_name,
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
use_fsdp_inference=False, # set to True if GPU is out of memory
dit_cpu_offload=True,
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"
pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
# image_encoder_cpu_offload=False,
)
@@ -28,14 +30,13 @@ def main():
# model!
# T2V mode
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
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, "
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
"cinematic.")
video2 = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True)
if __name__ == "__main__":
main()
main()
examples/inference/basic/basic_zimage.py
+1 -3
View File
@@ -20,13 +20,11 @@ from fastvideo.api import (
SamplingConfig,
)
DEFAULT_PROMPT = (
"Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. "
"Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. "
"Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, "
"silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."
)
"silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights.")
DEFAULT_REVISION = "f332072aa78be7aecdf3ee76d5c247082da564a6"