feat: Add FastVideo evaluation support for Wan models #19
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add support for evaluating FastVideo models (FastWan and base Wan)
in the VideoScience benchmark framework.
Changes:
- backend/api_providers.py: Fix attention backend selection
- FastWan DMD models use VIDEO_SPARSE_ATTN
- Base Wan models use FLASH_ATTN for optimal performance
- scripts/prepare_fastvideo_experiments.py: New script to prepare
evaluation experiments for FastVideo models
- Supports FastWan-1.3B (3-step DMD distilled)
- Supports Wan-1.3B (50-step base model)
- Skip-existing logic to resume interrupted runs
- Multi-run support for variance analysis
Usage:
python scripts/prepare_fastvideo_experiments.py \
--data-file data/database/data_filtered.jsonl \
--output-dir out/fastvideo_eval \
--models both
python frontend.py --json out/fastvideo_eval/experiments.json
yixinhuang48
force-pushed
the
feature/fastvideo-evaluation
branch
from
9996096 to
49ea604
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Add support for evaluating FastVideo models (FastWan and base Wan) in the VideoScience benchmark framework.
Changes
backend/api_providers.py: Fix attention backend selectionVIDEO_SPARSE_ATTNFLASH_ATTNscripts/prepare_fastvideo_experiments.py: New script to prepare evaluation experimentsFastWan-1.3B(3-step DMD distilled, ~17x faster)Wan-1.3B(50-step base model)Usage
Supported Models
FastVideo/FastWan2.1-T2V-1.3B-DiffusersWan-AI/Wan2.1-T2V-1.3B-DiffusersTest plan