Skip to content

feat: add logit-normal schedule#1669

Open
stduhpf wants to merge 3 commits into
leejet:masterfrom
stduhpf:logit-normal
Open

feat: add logit-normal schedule#1669
stduhpf wants to merge 3 commits into
leejet:masterfrom
stduhpf:logit-normal

Conversation

@stduhpf

@stduhpf stduhpf commented Jun 16, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds support for the logit-normal schedule that supposed to be the default noise schedule for Ideogram4 (see https://github.com/ideogram-oss/ideogram4/blob/main/docs/pipeline.md#noise-schedule).

It's now set as default scheduler when running an Ideogram4 model.

Related Issue / Discussion

N/A

Additional Information

Uses Acklam's Algorithm to approximate the Inverse Normal CDF to avoid adding a boost dependency.

Discrete scheduler Logit-normal (mu=0,std=1.75)
output output - Copy (326)

I'm noticing the results seem pretty consistently slightly worse with (my implementaion of) this schedule, so I don't know if I'm doing something wrong, or if it's just not that good despite being recommended in the official implementation.

Checklist

@stduhpf

stduhpf commented Jun 19, 2026

Copy link
Copy Markdown
Contributor Author

I played around with the formula a bit, by carefully chosing the mean and std parameters, it seems to be possible to approximate roughly any other schedule...

Examples:

mean std closest schedule
0 1.7 discrete
0 2.6 smoothstep
3.3 2.6 exponential

https://www.desmos.com/calculator/irnfqihjqa

For some reason, the recommended parameters seem to give subpar results compared to discrete (the current default), especially at high resolution (at 512x512 is should be pretty close but the resolution-aware thing steers it away at higher resolution).

Maybe it's just that I'm comparing with prompts/seeds that were cherry-picked because they were working great with the discrete scheduler.

@stduhpf stduhpf force-pushed the logit-normal branch 3 times, most recently from 6bc8091 to 9dd0471 Compare June 19, 2026 16:16
@stduhpf stduhpf marked this pull request as ready for review June 19, 2026 16:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant