hpcaitech/Open-Sora · error · ValueError
downsample factor {factor} is not supported for encoder proj
Error message
downsample factor {factor} is not supported for encoder project in What it means
build_encoder_project_in_block only supports project_in factors 1 and 2. Any other factor value in the encoder config raises this ValueError at model construction.
Source
Thrown at opensora/models/dc_ae/models/dc_ae.py:274
if factor == 1:
block = ConvLayer(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=3,
stride=1,
use_bias=True,
norm=None,
act_func=None,
is_video=is_video,
)
elif factor == 2:
if is_video:
raise NotImplementedError("Downsample during project_in is not supported for video")
block = build_downsample_block(
block_type=downsample_block_type, in_channels=in_channels, out_channels=out_channels, shortcut=None
)
else:
raise ValueError(f"downsample factor {factor} is not supported for encoder project in")
return block
def build_encoder_project_out_block(
in_channels: int,
out_channels: int,
norm: Optional[str],
act: Optional[str],
shortcut: Optional[str],
is_video: bool,
):
block = OpSequential(
[
build_norm(norm),
build_act(act),
ConvLayer(
in_channels=in_channels,
out_channels=out_channels,View on GitHub (pinned to 7ad6a96a13)
Solutions
- Set project_in_factor to 1 or 2
- Use a shipped config for the target checkpoint
- If you need another factor, implement it in build_encoder_project_in_block and contribute/patch locally
Example fix
# before project_in_factor: 4 # after project_in_factor: 2
Defensive patterns
Strategy: validation
Validate before calling
assert project_in_factor in (1, 2), f'unsupported project_in factor: {project_in_factor}' Prevention
- Whitelist factor values at config load
- Validate the full encoder config schema before init
When it happens
Trigger: Setting project_in_factor to 4, 8, 0.5, or any value besides 1/2 in the DCAE encoder config.
Common situations: Trying to match a different VAE's channel/stride scheme by changing the project-in factor; hand-editing configs without checking supported values.
Understand the failure class
Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.
Related errors
- block_type {block_type} is not supported
- block_type {block_type} is not supported for downsampling
- shortcut {shortcut} is not supported for downsample
- block_type {block_type} is not supported for upsampling
- shortcut {shortcut} is not supported for upsample
AI-assisted analysis of hpcaitech/Open-Sora@7ad6a96a13 (2026-08-28).
Data as JSON: /api/errors/1b3e8999ee881895.
Report an issue: GitHub.