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_vc.py
+142 -86
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 = (
@@ -63,35 +67,49 @@ def basic_generation():
"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
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-VC-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_vc_basic"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
video_path=VIDEO_PATH,
num_cond_frames=NUM_COND_FRAMES,
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,
inputs=InputConfig(video_path=VIDEO_PATH),
sampling=SamplingConfig(
height=480,
width=832,
num_frames=93,
num_inference_steps=50,
fps=15,
guidance_scale=4.0,
seed=SEED,
),
output=OutputConfig(
output_path=output_path,
save_video=True,
),
extensions={"num_cond_frames": NUM_COND_FRAMES},
)
)
print(f"\nBasic generation complete! Video saved to: {output_path}")
generator.shutdown()
@@ -118,37 +136,55 @@ def distill_refine_generation():
print("\n[Stage 1] Distilled generation (16 steps, 480p)")
print("-" * 40)
generator = VideoGenerator.from_pretrained(
"FastVideo/LongCat-Video-VC-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-VC-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_vc_distill"
generator.generate_video(
prompt=PROMPT,
negative_prompt=NEGATIVE_PROMPT,
video_path=VIDEO_PATH,
num_cond_frames=NUM_COND_FRAMES,
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,
inputs=InputConfig(video_path=VIDEO_PATH),
sampling=SamplingConfig(
height=480,
width=832,
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,
),
extensions={"num_cond_frames": NUM_COND_FRAMES},
)
)
print(f"Distilled generation complete! Video saved to: {distill_output_path}")
generator.shutdown()
@@ -166,41 +202,61 @@ def distill_refine_generation():
# 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(
"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_vc_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, # For refinement, no conditioning frames
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,
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,
),
output=OutputConfig(
output_path=refine_output_path,
save_video=True,
),
extensions={
"t_thresh": 0.5,
"spatial_refine_only": False,
"num_cond_frames": 0, # For refinement, no conditioning frames
},
)
)
print(f"Refinement complete! Video saved to: {refine_output_path}")
refine_generator.shutdown()