Davids048andClaude Fable 5.1
a5aa64ab6b
VideoGenerator.from_pretrained(model_path, config) takes the same nested
settings as from_config; the 24 flat keywords, from_pretrained_kwargs_to_config,
FROM_PRETRAINED_KWARGS, and every flat_field in the schema are deleted.
nvfp4_fa4 is the typed field engine.attention.nvfp4_fa4, applied by a
resolution step. 65 call sites and the docs use the nested form; the three
kwargs golden cases are config cases with byte-identical results.
Every value is decided during resolution; no runtime code calls
with_override. The device offload policy (unified memory, MPS, layerwise
conflicts, lazy module load) runs as resolution steps in the main process
(fastvideo/api/device_policy.py), and the worker runs on the config it
receives. The LTX-2 refine defaults from model_index.json and the MiniMax-H3
schedule from fastvideo_inference.json are resolution steps
(fastvideo/api/checkpoint_defaults.py) that read local checkpoints or download
only those files; the H3 pipeline validates the schedule against the loaded
schedulers but no longer writes it. The preprocessing entry point passes the
downloaded local path as run state instead of a config override. Teacher and
critic models load with override_transformer_cls_name as a load argument.
The test isolation turns the device policy off, as it blocks downloads, so
that the goldens do not depend on the machine.
Against the 3f6893a0 goldens, every field still matches except boundary_ratio
and ltx2_vae_tiling (DESIGN section 9) and the fields that no longer exist.
The launcher and trainer YAML verifications report 0 unexplained differences.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
94 lines
3.1 KiB
Python
94 lines
3.1 KiB
Python
from fastvideo import VideoGenerator
|
|
from fastvideo.models.dits.matrixgame2.utils import create_action_presets
|
|
|
|
import torch
|
|
|
|
# Available variants: "base_distilled_model", "gta_distilled_model", "templerun_distilled_model"
|
|
# Each variant has different keyboard_dim:
|
|
# - base_distilled_model: keyboard_dim=4
|
|
# - gta_distilled_model: keyboard_dim=2
|
|
# - templerun_distilled_model: keyboard_dim=7 (keyboard only, no mouse)
|
|
MODEL_VARIANT = "base_distilled_model"
|
|
|
|
# Variant-specific settings
|
|
VARIANT_CONFIG = {
|
|
"base_distilled_model": {
|
|
"model_path":
|
|
"FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers",
|
|
"keyboard_dim":
|
|
4,
|
|
"image_url":
|
|
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/universal/0000.png",
|
|
},
|
|
"gta_distilled_model": {
|
|
"model_path":
|
|
"FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers",
|
|
"keyboard_dim":
|
|
2,
|
|
"image_url":
|
|
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/gta_drive/0000.png",
|
|
},
|
|
"templerun_distilled_model": {
|
|
"model_path":
|
|
"FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers",
|
|
"keyboard_dim":
|
|
7,
|
|
"image_url":
|
|
"https://raw.githubusercontent.com/SkyworkAI/Matrix-Game/main/Matrix-Game-2/demo_images/temple_run/0000.png",
|
|
},
|
|
}
|
|
|
|
OUTPUT_PATH = "video_samples_matrixgame2"
|
|
|
|
|
|
def main():
|
|
# FastVideo will automatically use the optimal default arguments for the
|
|
# model.
|
|
# If a local path is provided, FastVideo will make a best effort
|
|
# attempt to identify the optimal arguments.
|
|
config = VARIANT_CONFIG[MODEL_VARIANT]
|
|
|
|
generator = VideoGenerator.from_pretrained(
|
|
config["model_path"],
|
|
# FastVideo will automatically handle distributed setup
|
|
{
|
|
"engine": {
|
|
"num_gpus": 1,
|
|
"use_fsdp_inference": False, # set to True if GPU is out of memory
|
|
"offload": {
|
|
"dit": True, # DiT need to be offloaded for MoE
|
|
"vae": False,
|
|
"text_encoder": True,
|
|
# Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
|
|
"pin_cpu_memory": True,
|
|
# "image_encoder": False,
|
|
},
|
|
},
|
|
},
|
|
)
|
|
|
|
num_frames = 597
|
|
actions = create_action_presets(num_frames, keyboard_dim=config["keyboard_dim"])
|
|
grid_sizes = torch.tensor([150, 44, 80])
|
|
|
|
generator.generate({
|
|
"prompt": "",
|
|
"inputs": {
|
|
"image_path": config["image_url"],
|
|
"mouse_cond": actions["mouse"].unsqueeze(0),
|
|
"keyboard_cond": actions["keyboard"].unsqueeze(0),
|
|
"grid_sizes": grid_sizes,
|
|
},
|
|
"sampling": {
|
|
"num_frames": num_frames,
|
|
"height": 352,
|
|
"width": 640,
|
|
"num_inference_steps": 50,
|
|
},
|
|
"output": {"output_path": OUTPUT_PATH, "save_video": True},
|
|
})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|