Add temporal_downscale_ratio to LatentFormat (CORE-147)#13702
Add temporal_downscale_ratio to LatentFormat (CORE-147)#13702Kosinkadink merged 4 commits intoComfy-Org:masterfrom
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThe change introduces a 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Review rate limit: 7/8 reviews remaining, refill in 7 minutes and 30 seconds.Comment |
Symmetric counterpart to the existing
LatentFormat.spacial_downscale_ratio. Default1, overridden on video formats with their VAE temporal factor (Mochi 6, LTXV 8, HunyuanVideo / HunyuanVideo15 / Wan21 / CogVideoX 4, Cosmos1CV8x8x8 8; LTXAV and Wan22 inherit). Each value verified against the corresponding VAE'supscale_index_formulaincomfy/sd.py.Metadata-only, no behavior change. Lets code that has a model but no VAE in scope read
model.model.latent_format.temporal_downscale_ratiodirectly, mirroring howspacial_downscale_ratiois already used atcomfy/sample.py:48-49.