[HN Gopher] Open-source PixArt-d image generator spits out high-...
       ___________________________________________________________________
        
       Open-source PixArt-d image generator spits out high-res AI images
       in 0.5 seconds
        
       Author : danboarder
       Score  : 40 points
       Date   : 2024-01-28 18:38 UTC (4 hours ago)
        
 (HTM) web link (the-decoder.com)
 (TXT) w3m dump (the-decoder.com)
        
       | stavros wrote:
       | From the comparisons, this seems quite a bit better than SDXL-
       | LCM. I wonder how long it will take projects like Fooocus to add
       | support for it, I'd be very interested in trying it out.
        
         | Zetobal wrote:
         | You can use it in comfyui instead of the checkpoint loader use
         | the uber loader. The model has a different unet architecture
         | than standard sdxl models.
        
       | artninja1988 wrote:
       | On how many images was this one trained? I remember their last
       | model being quite undertrained compared to stable diffusion
       | models
        
       | kken wrote:
       | Looks great, but it seems to be weak in consistency.
       | 
       | e.g. try prompts like "a cat riding a horse" or "a duck riding a
       | horse".
       | 
       | It will give you a duck-horse (or horse-duck?).
        
       ___________________________________________________________________
       (page generated 2024-01-28 23:01 UTC)