[HN Gopher] Diffusion Finetuning Myself
       ___________________________________________________________________
        
       Diffusion Finetuning Myself
        
       Author : frotaur
       Score  : 12 points
       Date   : 2025-09-24 19:44 UTC (3 hours ago)
        
 (HTM) web link (vassi.life)
 (TXT) w3m dump (vassi.life)
        
       | throwaway314155 wrote:
       | Your concern about catastrophic forgetting is mostly unfounded in
       | the regime of fine-tuning large diffusion models. The weights in
       | this case will maybe suffer from some damage to accuracy on some
       | downstream tasks. In general though, it is not "catastrophic". I
       | believe this is due to the attention mechanism but I'm happy to
       | be corrected.
        
         | frotaur wrote:
         | I see, it was probably my high learning rate that caused
         | problems. To be honest, I got a bit lazy to retry full
         | finetuning since LoRA worked so well, but maybe I'll revisit
         | this in the future, maybe with Qwen Image.
        
       | adzm wrote:
       | Minor observation: the formula text appears to go above the
       | sticky header in the website.
        
         | frotaur wrote:
         | True, I hadn't noticed, thanks! I'll try to fix that in the
         | near future.
         | 
         | Edit : Fixed!
        
       ___________________________________________________________________
       (page generated 2025-09-24 23:01 UTC)