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_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()