[HN Gopher] Accelerating Stable Diffusion XL Inference with Jax ...
       ___________________________________________________________________
        
       Accelerating Stable Diffusion XL Inference with Jax on Cloud TPU
       v5e
        
       Author : rayshan
       Score  : 13 points
       Date   : 2023-10-03 18:01 UTC (5 hours ago)
        
 (HTM) web link (huggingface.co)
 (TXT) w3m dump (huggingface.co)
        
       | MasterScrat wrote:
       | TPUs are amazing for Stable Diffusion.
       | 
       | We've been doing training (Dreambooth) and inference on TPUs
       | since the beginning of the year at https://dreamlook.ai.
       | 
       | We basically get 2.5x the training speed for Stable Diffusion 1.5
       | compared to A100, a very nice "unfair advantage"!
        
       | brucethemoose2 wrote:
       | That's very fast!
       | 
       | I just tried it on my RTX 3090, with a riced linux environment +
       | pytorch/xformers nightly, and 4 images take 36.7 seconds on the
       | ComfyUI backend (used by Fooocus-MRE).
       | 
       | ...But the issue is, right now, you can either pick high quality
       | tooling (The ComfyUI/automatic1111 backend UIs) or speed
       | (diffusers-based UIs), not both. InvokeAI and VoltaML do not
       | support SDXL as well as Fooocus at the moment, and all the other
       | UIs use the slow Stability backend with no compilation support.
        
         | FloatArtifact wrote:
         | Double check your facts there I think InvokeAI support SDXL
         | 
         | See https://github.com/invoke-ai/InvokeAI/releases
         | 
         | I believe invoke supports caching and a number of interesting
         | features this release.
        
       ___________________________________________________________________
       (page generated 2023-10-03 23:02 UTC)