(Here is the most up-to-date VAE for reference) Bad/Outdated info. Using this model will not fix fp16 issues for all models. You should merge this VAE with the models. SD-XL BASE This is a model designed for generating quality 1024×1024-sized images. It's tested to produce same (...
Extensions and API: api endpoints: /sdapi/v1/server-kill, /sdapi/v1/server-restart, /sdapi/v1/server-stop allow Script to have custom metaclass add model exists status check /sdapi/v1/options rename --add-stop-route to --api-server-stop addbefore_hrscript callback add callbackafter_...
It works fine for non SDXL models, but anything SDXL based fails to load :/ Author mooonwalker1983 commented Jul 27, 2023 @mooonwalker1983 speed should improve if --medvram is used? Also try sdp-no-mem setting in optimization It really works. thank you for help me! can it be ...
Usingpromptsalone can achieve amazing styles, even using a base model like Stable Diffusionv1.5orSDXL. For example, see overa hundred stylesachieved using prompts with the SDXL model. If you prefer a more automated approach to applying styles with prompts, you can use theSDXL Style Selectore...
SD XL support Requires --no-half-vae. See #11757 for more details. user metadata system for custom networks extended Lora metadata editor: set activation text, default weight, view tags, training info Lora extension rework to include other types of networks (all that were previously handled ...
Extremely slow SDXL image generation #12264 Renaldas111 started this conversation in General Renaldas111 Aug 2, 2023 I am using RTX3070Ti Laptop GPU with 8G of VRAM. The speed of image generation is about 10 s/it (10241024 batch size 1), refiner works faster up to 1+ s/it when ...
andypotatoadded thebug-reportReport of a bug, yet to be confirmedlabelJul 27, 2023 akxadded thesdxlRelated to SDXLlabelJul 31, 2023 Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment
delete and rebuild venv - no change deactivate all extensions and reinstall tensorrt extension - no change deactivate all COMMANDLINE_ARGS - Error is gone and it builded the TensorRT engine This were my COMMANDLINE_ARGS before = --api --xformers --medvram-sdxl --opt-sdp-attention --medvr...
First Ever SDXL Training With Kohya LoRA - Stable Diffusion XL Training Will Replace Older Models 46.) Local - PC - Free How To Use SDXL in Automatic1111 Web UI - SD Web UI vs ComfyUI - Easy Local Install Tutorial / Guide 47.) Cloud - RunPod - Paid ...
Remove any VRAM heavy arguments such as--no-half. These arguments can significantly increase VRAM usage and reduce speed. CheckBatch cond/uncondinSettings/Optimizationto improve speed; uncheck it to reduce VRAM usage. Model Zoo mm_sd_v14.ckpt&mm_sd_v15.ckpt&mm_sd_v15_v2.ckpt&mm_sdxl_...