[refactor]: migrate examples/scripts to typed VideoGenerator API; rename api/compat.py to api/translation.py
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
@@ -13,6 +13,10 @@ 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 = (
|
||||
@@ -38,40 +42,54 @@ SEED = 42
|
||||
def basic_generation():
|
||||
"""
|
||||
Run basic LongCat T2V generation (50 steps at 480p).
|
||||
|
||||
|
||||
This uses the full 50-step denoising process for highest quality.
|
||||
"""
|
||||
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
|
||||
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-T2V-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_t2v_basic"
|
||||
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
negative_prompt=NEGATIVE_PROMPT,
|
||||
output_path=output_path,
|
||||
save_video=True,
|
||||
height=480,
|
||||
width=832,
|
||||
num_frames=93,
|
||||
num_inference_steps=50,
|
||||
fps=15,
|
||||
guidance_scale=4.0,
|
||||
seed=SEED,
|
||||
|
||||
generator.generate(
|
||||
GenerationRequest(
|
||||
prompt=PROMPT,
|
||||
negative_prompt=NEGATIVE_PROMPT,
|
||||
output=OutputConfig(
|
||||
output_path=output_path,
|
||||
save_video=True,
|
||||
),
|
||||
sampling=SamplingConfig(
|
||||
height=480,
|
||||
width=832,
|
||||
num_frames=93,
|
||||
num_inference_steps=50,
|
||||
fps=15,
|
||||
guidance_scale=4.0,
|
||||
seed=SEED,
|
||||
),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
print(f"\nBasic generation complete! Video saved to: {output_path}")
|
||||
generator.shutdown()
|
||||
|
||||
@@ -79,54 +97,72 @@ def basic_generation():
|
||||
def distill_refine_generation():
|
||||
"""
|
||||
Run LongCat T2V with distill+refine pipeline (16 steps + refinement to 720p).
|
||||
|
||||
|
||||
This uses the distilled LoRA for fast 480p generation (16 steps),
|
||||
then refines to 720p using the refinement LoRA with BSA enabled.
|
||||
"""
|
||||
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,
|
||||
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-T2V-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_t2v_distill"
|
||||
|
||||
generator.generate_video(
|
||||
prompt=PROMPT,
|
||||
negative_prompt=NEGATIVE_PROMPT,
|
||||
output_path=distill_output_path,
|
||||
save_video=True,
|
||||
height=480,
|
||||
width=832,
|
||||
num_frames=93,
|
||||
num_inference_steps=16,
|
||||
fps=15,
|
||||
guidance_scale=1.0,
|
||||
seed=SEED,
|
||||
|
||||
generator.generate(
|
||||
GenerationRequest(
|
||||
prompt=PROMPT,
|
||||
negative_prompt=NEGATIVE_PROMPT,
|
||||
output=OutputConfig(
|
||||
output_path=distill_output_path,
|
||||
save_video=True,
|
||||
),
|
||||
sampling=SamplingConfig(
|
||||
height=480,
|
||||
width=832,
|
||||
num_frames=93,
|
||||
num_inference_steps=16,
|
||||
fps=15,
|
||||
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:
|
||||
@@ -134,43 +170,65 @@ 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",
|
||||
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, 8],
|
||||
bsa_chunk_k=[4, 4, 8],
|
||||
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, 8],
|
||||
"bsa_chunk_k": [4, 4, 8],
|
||||
"lora_nickname": "refinement",
|
||||
},
|
||||
),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
refine_output_path = "outputs_video/longcat_t2v_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=1280,
|
||||
num_inference_steps=50,
|
||||
fps=30,
|
||||
guidance_scale=1.0,
|
||||
seed=SEED,
|
||||
|
||||
refine_generator.generate(
|
||||
GenerationRequest(
|
||||
prompt=PROMPT,
|
||||
negative_prompt=NEGATIVE_PROMPT,
|
||||
output=OutputConfig(
|
||||
output_path=refine_output_path,
|
||||
save_video=True,
|
||||
),
|
||||
inputs=InputConfig(
|
||||
refine_from=distill_video_path,
|
||||
),
|
||||
sampling=SamplingConfig(
|
||||
height=720,
|
||||
width=1280,
|
||||
num_inference_steps=50,
|
||||
fps=30,
|
||||
guidance_scale=1.0,
|
||||
seed=SEED,
|
||||
),
|
||||
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()
|
||||
|
||||
@@ -180,13 +238,13 @@ 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 +252,3 @@ def main():
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user