Post
10
Introducing of the "blot" expert, sd15-flow-sol. The twin sister flow-matching experts for tinyflux-lailah; sd15-flow-lune AND sd15-flow-sol will be used in tandem to train tinyflux-Lailah.
Lune was heavily finetuned in the sd3-style and adapted shift timestep system after David's interpolation converted sd15 into geometric basis.
Sol was left abandoned after 50 epochs with David and was considered overcooked and rigid, until I noticed the geometric structure today. Lune doesn't produce geometric structure as solid as Sol, not even close. Lune produces improved fidelity and detail, but Sol produces something very very different, aligned to sd15's behavior, and fully representative of the 5point 4simplex structure that David brought to the table.
Sol is essentially a nearly perfect blob-forming geometric blotter. Sol is SD15, and yet SOL was trained using a specific pattern recognizing and timestep aligned David model. David was tasked with classifying timesteps and patterns using complex deep-recognition structural analysis layer-by-layer, determining full-scale opinions after watching the entirety of sd15's structure during training.
I considered this to be highly successful for converting the implicit nature of one model's predictions to another, when sd15-flow-lune finetuned to a highly-similar representation of sd15 with using sd15 latents as teachers.
Even though the sd15-flow-sol was left abandoned, the structure of Sol is HIGHLY effective at understanding TIMESTEP blotting interpolation. I didn't realize how crucially important this was until Lailah started to show rigidity and compartmentalized behavior with sequence - which likely happens to ALL flow matching models.
AbstractPhil/sd15-flow-matching
AbstractPhil/geo-david-collective-sd15-distilled
AbstractPhil/geo-david-collective-sd15-base-e40
Lune was heavily finetuned in the sd3-style and adapted shift timestep system after David's interpolation converted sd15 into geometric basis.
Sol was left abandoned after 50 epochs with David and was considered overcooked and rigid, until I noticed the geometric structure today. Lune doesn't produce geometric structure as solid as Sol, not even close. Lune produces improved fidelity and detail, but Sol produces something very very different, aligned to sd15's behavior, and fully representative of the 5point 4simplex structure that David brought to the table.
Sol is essentially a nearly perfect blob-forming geometric blotter. Sol is SD15, and yet SOL was trained using a specific pattern recognizing and timestep aligned David model. David was tasked with classifying timesteps and patterns using complex deep-recognition structural analysis layer-by-layer, determining full-scale opinions after watching the entirety of sd15's structure during training.
I considered this to be highly successful for converting the implicit nature of one model's predictions to another, when sd15-flow-lune finetuned to a highly-similar representation of sd15 with using sd15 latents as teachers.
Even though the sd15-flow-sol was left abandoned, the structure of Sol is HIGHLY effective at understanding TIMESTEP blotting interpolation. I didn't realize how crucially important this was until Lailah started to show rigidity and compartmentalized behavior with sequence - which likely happens to ALL flow matching models.
AbstractPhil/sd15-flow-matching
AbstractPhil/geo-david-collective-sd15-distilled
AbstractPhil/geo-david-collective-sd15-base-e40