PCM acceleration LoRAs as individual .safetensors files.These are already available in <a target="_blank" rel="ugc" href="https://civarchive.com/models/487073?modelVersionId=541627">https://civarchive.com/models/487073?modelVersionId=541627</a> , but as a single zip file, so can't be used on the Civitai generator.Some quick guidelines:<ul><li>all versions are very sensitive to CFG values: if you get too much contrast or burned-out images, try lowering the CFG. A higher CFG may also need a higher generation step count to fix inconsistencies, artifacts, etc;</li><li>smallCFG versions work pretty much like LCM: they essentially ignore the negative prompt, and need CFG to be very low (&lt;= 2). Try CFG 1 first, since generation will be faster;</li><li>any n-step LoRA should work as long as you keep generation steps above n, but for much higher step counts a higher-step LoRA tends to generate better images;</li><li>for the scheduler, I had good results with DDIM, DEIS, DPM2, TCD, Euler and Euler A; in some cases, UniPC and even LCM work too. The DPM family doesn't seem to work very well;</li></ul>For the on-site gen, I suggest starting with the 8-step normalCFG Lora, and CFG around 3 or 4, leaving the step count at 10. DDIM, Euler, DPM2 and Euler A schedulers seem to work best.All credits go to <a target="_blank" rel="ugc" href="https://civarchive.com/user/G_U_N">https://civarchive.com/user/G_U_N</a> for this great resource.Project page: <a target="_blank" rel="ugc" href="https://g-u-n.github.io/projects/pcm/">https://g-u-n.github.io/projects/pcm/</a>Original repository: <a target="_blank" rel="ugc" href="https://huggingface.co/wangfuyun/PCM_Weights">https://huggingface.co/wangfuyun/PCM_Weights</a>

PCM Acceleration LoRAs - SD 1.5

4-step normal CFG (use CFG 2-9 for generation, depending on the number of steps), and DDIM or Euler for sampling

Files with SHA256: fa6acb94f11dba3bf4120af5a12e3c88cd2b9572d43ec1a6fb04eede9f32829e