modelscope / modelscope/DiffSynth-Studio
how to understand tile_size_height and tile_stride_height args in wan training script
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
parser.add_argument(
"--tile_size_height",
type=int,
default=34,
help="Tile size (height) in VAE.",
)
parser.add_argument(
"--tile_size_width",
type=int,
default=34,
help="Tile size (width) in VAE.",
)
parser.add_argument(
"--tile_stride_height",
type=int,
default=18,
help="Tile stride (height) in VAE.",
)
parser.add_argument(
"--tile_stride_width",
type=int,
default=16,
help="Tile stride (width) in VAE.",
)
Is this size referring to the number of RGB pixels or the latent space?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names the Wan training script and its VAE tiling arguments, but no file path. Locate that script and the VAE tiling implementation first, then determine whether the values use pixel or latent units. Done means documenting the units and explaining tile size versus stride for all four arguments.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100