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>
58 lines
3.3 KiB
Python
58 lines
3.3 KiB
Python
from fastvideo import VideoGenerator
|
|
|
|
# from fastvideo.api.sampling_param import SamplingParam
|
|
|
|
OUTPUT_PATH = "video_samples_wan2_1_Fun"
|
|
OUTPUT_NAME = "wan2.1_test"
|
|
|
|
|
|
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.
|
|
generator = VideoGenerator.from_pretrained(
|
|
"IRMChen/Wan2.1-Fun-1.3B-Control-Diffusers",
|
|
# "alibaba-pai/Wan2.2-Fun-A14B-Control",
|
|
# 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,
|
|
},
|
|
},
|
|
},
|
|
)
|
|
|
|
prompt = "一位年轻女性穿着一件粉色的连衣裙，裙子上有白色的装饰和粉色的纽扣。她的头发是紫色的，头上戴着一个红色的大蝴蝶结，显得非常可爱和精致。她还戴着一个红色的领结，整体造型充满了少女感和活力。她的表情温柔，双手轻轻交叉放在身前，姿态优雅。背景是简单的灰色，没有任何多余的装饰，使得人物更加突出。她的妆容清淡自然，突显了她的清新气质。整体画面给人一种甜美、梦幻的感觉，仿佛置身于童话世界中。"
|
|
negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
|
|
# prompt = "A young woman with beautiful, clear eyes and blonde hair stands in the forest, wearing a white dress and a crown. Her expression is serene, reminiscent of a movie star, with fair and youthful skin. Her brown long hair flows in the wind. The video quality is very high, with a clear view. High quality, masterpiece, best quality, high resolution, ultra-fine, fantastical."
|
|
# negative_prompt = "Twisted body, limb deformities, text captions, comic, static, ugly, error, messy code."
|
|
image_path = "https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/wan_fun/asset_Wan2_2/v1.0/8.png"
|
|
control_video_path = "https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/wan_fun/asset_Wan2_2/v1.0/pose.mp4"
|
|
|
|
video = generator.generate({
|
|
"prompt": prompt,
|
|
"negative_prompt": negative_prompt,
|
|
"inputs": {
|
|
"image_path": image_path,
|
|
"video_path": control_video_path,
|
|
},
|
|
"output": {
|
|
"output_path": OUTPUT_PATH,
|
|
"output_video_name": OUTPUT_NAME,
|
|
"save_video": True,
|
|
},
|
|
})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|