Open-Sora/configs/vae/inference/video_dc_ae.py
Zheng Zangwei (Alex Zheng) febf3ad4b2
Update Open-Sora 2.0 (#807)
* upload v2.0

* update docs

* [hotfix] fit latest fa3 (#802)

* update readme

* update readme

* update readme

* update train readme

* update readme

* update readme: motion score

* cleaning video dc ae WIP

* update config

* add dependency functions

* undo cleaning

* use latest dcae

* complete high compression training

* update hcae config

* cleaned up vae

* update ae.md

* further cleanup

* update vae & ae paths

* align naming of ae

* [hotfix] fix ring attn bwd for fa3 (#803)

* train ae default without wandb

* update config

* update evaluation results

* added hcae report

* update readme

* update readme demo

* update readme demo

* update readme gif

* display demo directly in readme

* update paper

* delete files

---------

Co-authored-by: Hongxin Liu <lhx0217@gmail.com>
Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>
Co-authored-by: wuxiwen <wuxiwen.simon@gmail.com>
2025-03-12 13:14:22 +08:00

33 lines
632 B
Python

dtype = "bf16"
batch_size = 1
seed = 42
dataset = dict(
type="video_text",
transform_name="resize_crop",
fps_max=16,
data_path="datasets/pexels_45k_necessary.csv",
)
bucket_config = {
"512px_ar1:1": {96: (1.0, 1)},
}
model = dict(
type="dc_ae",
model_name="dc-ae-f32t4c128",
from_pretrained="./ckpts/F32T4C128_AE.safetensors",
from_scratch=True,
use_spatial_tiling=True,
use_temporal_tiling=True,
spatial_tile_size=256,
temporal_tile_size=32,
tile_overlap_factor=0.25,
)
save_dir = "samples/video_dc_ae"
num_workers = 24
num_bucket_build_workers = 16
prefetch_factor = 4