Fix prompt schedule for second order samplers #9669
Merged
+9
−2
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Outdated suggestions cannot be applied.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.
Describe what this pull request is trying to achieve.
Closes #7508
Second order samplers (Heun, DPM2/a, DPM++ 2S/a, DPM++ SDE / Karras) cause the prompt schedule to run twice as fast when prompting something like
[dog:cat:0.5]
(i.e. for 100 steps, prompt isdog
until step 25,cat
until 50, and remainsdog
until 100). This fixes that by checking if the sampler is any of these second order samplers and multiplies the step count by 2 for calculating the prompt schedule.Additional notes and description of your changes
I've also added a compatibility option to replicate old seeds, as it's otherwise impossible to replicate them since the prompt would always run as twice as fast.
Environment this was tested in