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_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()