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

[refactor]: migrate examples/scripts to typed VideoGenerator API; rename api/compat.py to api/translation.py

Browse Source 
Move all examples/inference and scripts off the legacy
VideoGenerator.from_pretrained(model, **kwargs) +
generate_video(prompt, **kwargs) surface onto the typed
from_config(GeneratorConfig(...)) + generate(GenerationRequest(...))
convention, including the Kandinsky-5 and DreamX-World examples added
on main after the original migration. git-mv api/compat.py to
api/translation.py ('compat' implied a temporary shim; the forward
translation is its honest permanent role) and repoint all importers,
tests, and doc links.
This commit is contained in:
SolitaryThinker
2026-07-11 03:26:24 -07:00
parent 19a51a1fe6
commit bbbb7ab021
87 changed files with 2493 additions and 1461 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/inference/basic/basic_longcat_i2v.py
+140 -95
View File
@@ -19,6 +19,10 @@ import glob
import os
from fastvideo import VideoGenerator
from fastvideo.api import (
ComponentConfig, EngineConfig, GenerationRequest, GeneratorConfig,
InputConfig, OffloadConfig, OutputConfig, PipelineSelection, SamplingConfig,
)
# Common prompts and settings matching the shell script examples
PROMPT = (
@@ -45,41 +49,50 @@ SEED = 42
def basic_generation():
"""
Run basic LongCat I2V generation (50 steps at 480p).
This uses the full 50-step denoising process for highest quality.
"""
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
dit_cpu_offload=False,
vae_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=False,
enable_bsa=False,
generator = VideoGenerator.from_config(
GeneratorConfig(
model_path="FastVideo/LongCat-Video-I2V-Diffusers",
engine=EngineConfig(
num_gpus=1,
use_fsdp_inference=False, # set to True if GPU is out of memory
offload=OffloadConfig(
dit=False,
vae=True,
text_encoder=True,
pin_cpu_memory=False,
),
),
pipeline=PipelineSelection(experimental={"enable_bsa": False}),
)
)
output_path = "outputs_video/longcat_i2v_basic"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
image_path=IMAGE_PATH,
output_path=output_path,
save_video=True,
height=480,
width=480, # Square
num_frames=93,
num_inference_steps=50,
fps=15,
guidance_scale=4.0,
seed=SEED,
generator.generate(
GenerationRequest(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
inputs=InputConfig(image_path=IMAGE_PATH),
sampling=SamplingConfig(
height=480,
width=480, # Square
num_frames=93,
num_inference_steps=50,
fps=15,
guidance_scale=4.0,
seed=SEED,
),
output=OutputConfig(output_path=output_path, save_video=True),
)
)
print(f"\nBasic generation complete! Video saved to: {output_path}")
generator.shutdown()
@@ -87,55 +100,70 @@ def basic_generation():
def distill_refine_generation():
"""
Run LongCat I2V with distill+refine pipeline (16 steps + refinement to 768p).
This uses the distilled LoRA for fast 480p generation (16 steps),
then refines to 768p using the refinement LoRA with BSA enabled.
"""
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,
use_fsdp_inference=True,
dit_cpu_offload=False,
vae_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=False,
enable_bsa=False,
lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
lora_nickname="distilled",
generator = VideoGenerator.from_config(
GeneratorConfig(
model_path="FastVideo/LongCat-Video-I2V-Diffusers",
engine=EngineConfig(
num_gpus=1,
use_fsdp_inference=True,
offload=OffloadConfig(
dit=False,
vae=True,
text_encoder=True,
pin_cpu_memory=False,
),
),
pipeline=PipelineSelection(
components=ComponentConfig(
lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
),
experimental={
"enable_bsa": False,
"lora_nickname": "distilled",
},
),
)
)
distill_output_path = "outputs_video/longcat_i2v_distill"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
image_path=IMAGE_PATH,
output_path=distill_output_path,
save_video=True,
height=480,
width=480, # Square
num_frames=93,
num_inference_steps=16,
fps=15,
guidance_scale=1.0,
seed=SEED,
generator.generate(
GenerationRequest(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
inputs=InputConfig(image_path=IMAGE_PATH),
sampling=SamplingConfig(
height=480,
width=480, # Square
num_frames=93,
num_inference_steps=16,
fps=15,
guidance_scale=1.0,
seed=SEED,
),
output=OutputConfig(output_path=distill_output_path, save_video=True),
)
)
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:
@@ -143,46 +171,63 @@ 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
# 768x768: latent 48x48, 48%8=0 ✓
refine_generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-T2V-Diffusers",
num_gpus=1,
use_fsdp_inference=True,
dit_cpu_offload=True,
vae_cpu_offload=True,
text_encoder_cpu_offload=True,
pin_cpu_memory=False,
enable_bsa=True,
bsa_sparsity=0.875,
bsa_chunk_q=[4, 4, 4],
bsa_chunk_k=[4, 4, 4],
lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
lora_nickname="refinement",
refine_generator = VideoGenerator.from_config(
GeneratorConfig(
model_path="FastVideo/LongCat-Video-T2V-Diffusers",
engine=EngineConfig(
num_gpus=1,
use_fsdp_inference=True,
offload=OffloadConfig(
dit=True,
vae=True,
text_encoder=True,
pin_cpu_memory=False,
),
),
pipeline=PipelineSelection(
components=ComponentConfig(
lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
),
experimental={
"enable_bsa": True,
"bsa_sparsity": 0.875,
"bsa_chunk_q": [4, 4, 4],
"bsa_chunk_k": [4, 4, 4],
"lora_nickname": "refinement",
},
),
)
)
refine_output_path = "outputs_video/longcat_i2v_refine_720p"
refine_generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
output_path=refine_output_path,
save_video=True,
refine_from=distill_video_path,
t_thresh=0.5,
spatial_refine_only=False,
num_cond_frames=0,
height=720,
width=720,
num_inference_steps=50,
fps=30,
guidance_scale=1.0,
seed=SEED,
refine_generator.generate(
GenerationRequest(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
inputs=InputConfig(refine_from=distill_video_path),
sampling=SamplingConfig(
height=720,
width=720,
num_inference_steps=50,
fps=30,
guidance_scale=1.0,
seed=SEED,
),
output=OutputConfig(output_path=refine_output_path, save_video=True),
extensions={
"t_thresh": 0.5,
"spatial_refine_only": False,
"num_cond_frames": 0,
},
)
)
print(f"Refinement complete! Video saved to: {refine_output_path}")
refine_generator.shutdown()
@@ -192,13 +237,13 @@ 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)