Quick lora test on Priscilla Ricart, trained for 800 steps on BS 4 with 0.0004 LR using AdamW and FP8 Flux.dev. Dataset is small, but seems like Flux learns really well or the information is already in the model but not aligned. Likely overfit and affects gens without trigger, but not tested meticulously.
Description
Looks like we don't have an active mirror for this one right now.
This archive is kept alive by community contributions, so there are still some gaps, especially for newly removed content.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Downloads
67
Platform
CivitAI
Platform Status
Deleted
Created
9/5/2024
Updated
7/7/2025
Deleted
5/23/2025
Trigger Words:
Priscilla Ricart
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.