Even_Adder@lemmy.dbzer0.com to Stable Diffusion@lemmy.dbzer0.com • 4 days agoStable Diffusion 3 Medium Fine-tuning Tutorial — Stability AIexternal-linkmessage-square8 fedilinkarrow-up16
arrow-up16external-linkStable Diffusion 3 Medium Fine-tuning Tutorial — Stability AIEven_Adder@lemmy.dbzer0.com to Stable Diffusion@lemmy.dbzer0.com • 4 days agomessage-square8 Commentsfedilink
minus-squareclb92@feddit.dkhexbear1·edit-23 days agoPeople have been training great Flux LoRAs for a while now, haven't they? Is a LoRA not a finetune, or have I misunderstood something? linkfedilink
minus-squareEven_Adder@lemmy.dbzer0.comhexagonhexbear1·3 days agoLast I heard, LoRAs cause catastrophic forgetting in the model, and full fine-tuning doesn't really work. linkfedilink
minus-squareerenkoylu@lemmy.mlhexbear1·edit-22 days agoquite the opposite. Lora's are very effective against catastrophic forgetting, and full finetuning is very dangerous (but also much more powerful). linkfedilink
minus-squareclb92@feddit.dkhexbear2·3 days agoOh well, in practice I'll just continue to enjoy this (possibly forgetful and not-fully-finetunable) model then, that still gives me amazing results 😊 linkfedilink
People have been training great Flux LoRAs for a while now, haven't they? Is a LoRA not a finetune, or have I misunderstood something?
Last I heard, LoRAs cause catastrophic forgetting in the model, and full fine-tuning doesn't really work.
quite the opposite. Lora's are very effective against catastrophic forgetting, and full finetuning is very dangerous (but also much more powerful).
Oh well, in practice I'll just continue to enjoy this (possibly forgetful and not-fully-finetunable) model then, that still gives me amazing results 😊