mirror of
https://github.com/hpcaitech/Open-Sora.git
synced 2026-04-12 05:46:22 +02:00
febf3ad4b2
* 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>
36 lines
704 B
Python
36 lines
704 B
Python
_base_ = ["t2i2v_768px.py"]
|
|
|
|
# no need for parallelism
|
|
plugin = None
|
|
plugin_config = None
|
|
plugin_ae = None
|
|
plugin_config_ae = None
|
|
|
|
# model settings
|
|
patch_size = 1
|
|
model = dict(
|
|
from_pretrained="./ckpts/Open_Sora_v2_Video_DC_AE.safetensors",
|
|
in_channels=128,
|
|
cond_embed=True,
|
|
patch_size=1,
|
|
)
|
|
|
|
# AE settings
|
|
ae = dict(
|
|
_delete_=True,
|
|
type="dc_ae",
|
|
from_scratch=True,
|
|
model_name="dc-ae-f32t4c128",
|
|
from_pretrained="./ckpts/F32T4C128_AE.safetensors",
|
|
use_spatial_tiling=True,
|
|
use_temporal_tiling=True,
|
|
spatial_tile_size=256,
|
|
temporal_tile_size=32,
|
|
tile_overlap_factor=0.25,
|
|
)
|
|
ae_spatial_compression = 32
|
|
|
|
sampling_option = dict(
|
|
num_frames=128,
|
|
)
|