feat: first benchmark — Wan 2.2 I2V on Modal A100#25
Merged
Conversation
Generated a 5-second video from the OpenX logo using Wan2.2-TI2V-5B. Results (A100-40GB, Modal): - Model load: 225.6s (includes HF download, first run) - Generation: 54.1s (30 steps, 81 frames, 832x480) - Total GPU: 281.6s - Cost: $0.15 Includes: - benchmarks/run_benchmark.py — reproducible Modal benchmark script - benchmarks/prompts/openx-intro-15s.json — pre-made scene definitions - benchmarks/results/benchmark-results.json — timing metrics - benchmarks/results/samples/scene_1_i2v.mp4 — generated video output - benchmarks/assets/ — OpenX brand images used as first frame
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
First Real Video Generation 🎬
Successfully generated a 5-second AI video from the OpenX logo using Wan 2.2 TI2V-5B on Modal.
Results (A100-40GB)
What's included
benchmarks/run_benchmark.py— Reproducible benchmark script (Modal)benchmarks/prompts/openx-intro-15s.json— Pre-made scene definitionsbenchmarks/results/benchmark-results.json— Timing metricsbenchmarks/results/samples/scene_1_i2v.mp4— Generated video (242KB)benchmarks/assets/— Brand images used as first frame inputKey takeaway
On a warm start (model already cached), generation alone takes ~54 seconds for a 5-second clip. That's ~$0.03/clip — meaning a 60-second video (12 clips) costs approximately $0.36 on an A100.