SD XL workload has not been installed

[waynemadsen]

Any help from you guys would be great.

I've been running comfyui locally for about the past 9 months. Krita has been running find for several months. I updated to version 1.22 when it came out and didn't have any issues.

Last night, for no apparent reason, all of my SDXL workloads refused to load. I can see my flux style preset in the dropdown, but it is the only one. I can edit the custom style presets, but the error that 'SD XL workload has not been installed' now shows up under the model. The only change I can think of that I did recently is that I updated comyfui to v.0.1.3-7.

All the files for running SDXL are still in the same places for the install Acly wrote in the wiki. I haven't modified anything. I'm not sure if this even is a krita issue or a comfyui issue. I checked my comfyui manager and it doesn't show that I have any custom nodes installed, even though they are loading in the command prompt when the server starts up.

I've tried restarting comfy multiple times and krita multiple times. Nothing fixed the issue.

Anyone have any suggestions?

[waynemadsen]

also, i recently updated python for comfy to 3.11.8 and pytorch to 2.4.0+cu121.

[Acly]

Please check client.log - it lists all required models and shows which are missing.

[Tonny-gitgub]

Please check client.log - it lists all required models and shows which are missing.

where can I find this file-----client.log

[Acly]

where can I find this file-----client.log

https://github.com/Acly/krita-ai-diffusion/wiki/Common-Issues#log-files

[waynemadsen]

I don't have juggernaut, so it recognizes i'm missing that SDXL model, but it found all the optional alternative models. unless i have to have something for all the extra controlnet models. i skipped installing the xinsir all-in-one controlnet on this upgrade install. client.log entry after loading krita and connecting:

2024-08-29 07:29:33,424 INFO Loaded 11 sampler presets from C:\Users\Decimator\AppData\Roaming\krita\pykrita\ai_diffusion\presets\samplers.json 2024-08-29 07:29:33,430 INFO Loaded 3 sampler presets from C:\Users\Decimator\AppData\Roaming\krita\ai_diffusion\presets\samplers.json 2024-08-29 07:29:33,765 INFO Extension initialized, Version: 1.22.0, Python: 3.10.7 (tags/v3.10.7:6cc6b13, Sep 5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)] 2024-08-29 07:29:33,766 INFO Loading settings from C:\Users\Decimator\AppData\Roaming\krita\ai_diffusion\settings.json 2024-08-29 07:29:37,794 INFO Connecting to http://127.0.0.1:8188 2024-08-29 07:30:15,924 INFO Connecting to http://127.0.0.1:8188 2024-08-29 07:30:17,985 WARNING Missing CLIP model clip_g for SD 3 2024-08-29 07:30:17,986 INFO -> No model matches search paths: clip_g 2024-08-29 07:30:17,986 INFO -> Available models: clip_l.safetensors, t5xxl_fp8_e4m3fn.safetensors 2024-08-29 07:30:17,987 INFO Found CLIP model clip_l for SD 3: clip_l.safetensors 2024-08-29 07:30:17,987 INFO Found ControlNet model inpaint for SD 1.5: control_v11p_sd15_inpaint_fp16.safetensors 2024-08-29 07:30:17,987 INFO Optional ControlNet model universal for SD XL not found (search path: union-sdxl, xinsirunion) 2024-08-29 07:30:17,988 INFO Optional ControlNet model scribble for SD 1.5 not found (search path: control_v11p_sd15_scribble, control_lora_rank128_v11p_sd15_scribble) 2024-08-29 07:30:17,988 INFO Optional ControlNet model scribble for SD XL not found (search path: xinsirscribble, scribble-sdxl, mistoline, control-lora-sketch-rank, sai_xlsketch) 2024-08-29 07:30:17,989 INFO Optional ControlNet model line_art for SD 1.5 not found (search path: control_v11p_sd15_lineart, control_lora_rank128_v11p_sd15_lineart) 2024-08-29 07:30:17,989 INFO Optional ControlNet model line_art for SD XL not found (search path: xinsirscribble, mistoline, scribble-sdxl, control-lora-sketch-rank, sai_xlsketch) 2024-08-29 07:30:17,990 INFO Optional ControlNet model soft_edge for SD 1.5 not found (search path: control_v11p_sd15_softedge, control_lora_rank128_v11p_sd15_softedge) 2024-08-29 07:30:17,990 INFO Optional ControlNet model soft_edge for SD XL not found (search path: mistoline, xinsirscribble, scribble-sdxl) 2024-08-29 07:30:17,990 INFO Optional ControlNet model canny_edge for SD 1.5 not found (search path: control_v11p_sd15_canny, control_lora_rank128_v11p_sd15_canny) 2024-08-29 07:30:17,991 INFO Found ControlNet model canny_edge for SD XL: sai_xl_canny_256lora.safetensors 2024-08-29 07:30:17,991 INFO Optional ControlNet model depth for SD 1.5 not found (search path: control_sd15_depth_anything, control_v11f1p_sd15_depth, control_lora_rank128_v11f1p_sd15_depth) 2024-08-29 07:30:17,992 INFO Found ControlNet model depth for SD XL: control-lora-depth-rank128.safetensors 2024-08-29 07:30:17,992 INFO Optional ControlNet model normal for SD 1.5 not found (search path: control_v11p_sd15_normalbae, control_lora_rank128_v11p_sd15_normalbae) 2024-08-29 07:30:17,993 INFO Found ControlNet model pose for SD 1.5: control_v11p_sd15_openpose.pth 2024-08-29 07:30:17,993 INFO Found ControlNet model pose for SD XL: thibaud_xl_openpose.safetensors 2024-08-29 07:30:17,993 INFO Optional ControlNet model segmentation for SD 1.5 not found (search path: control_v11p_sd15_seg, control_lora_rank128_v11p_sd15_seg) 2024-08-29 07:30:17,994 INFO Optional ControlNet model segmentation for SD XL not found (search path: sdxl_segmentation_ade20k_controlnet) 2024-08-29 07:30:17,994 INFO Found ControlNet model blur for SD 1.5: control_lora_rank128_v11f1e_sd15_tile_fp16.safetensors 2024-08-29 07:30:17,995 INFO Found ControlNet model blur for SD XL: TTPLANET_Controlnet_Tile_realistic_v2_fp16.safetensors 2024-08-29 07:30:17,995 INFO Optional ControlNet model stencil for SD 1.5 not found (search path: control_v1p_sd15_qrcode_monster) 2024-08-29 07:30:17,996 INFO Optional ControlNet model stencil for SD XL not found (search path: sdxl_qrcode_monster) 2024-08-29 07:30:17,996 INFO Optional ControlNet model hands for SD 1.5 not found (search path: control_sd15_inpaint_depth_hand) 2024-08-29 07:30:17,996 INFO Found ControlNet model hands for SD XL: control-lora-depth-rank128.safetensors 2024-08-29 07:30:17,997 INFO Found CLIP Vision model ip_adapter for All: CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors 2024-08-29 07:30:17,997 WARNING Missing IP-Adapter model reference for SD 1.5 2024-08-29 07:30:17,998 INFO -> No model matches search paths: ip-adapter_sd15 2024-08-29 07:30:17,998 INFO -> Available models: ip-adapter-faceid-plusv2_sdxl.bin, ip-adapter-faceid-portrait_sdxl.bin, ip-adapter-faceid_sdxl.bin, ip-adapter-plus_sdxl_vit-h.safetensors, ip-adapter_sdxl.safetensors, ip-adapter_sdxl_vit-h.safetensors, ip_plus_composition_sdxl.safetensors 2024-08-29 07:30:17,998 INFO Found IP-Adapter model reference for SD XL: ip-adapter_sdxl_vit-h.safetensors 2024-08-29 07:30:17,999 INFO Optional IP-Adapter model face for SD 1.5 not found (search path: ip-adapter-faceid-plusv2_sd15, ip-adapter-faceid-plus_sd15) 2024-08-29 07:30:17,999 INFO Found IP-Adapter model face for SD XL: ip-adapter-faceid-plusv2_sdxl.bin 2024-08-29 07:30:18,000 INFO Found Upscale model default for All: 4x_NMKD-Superscale-SP_178000_G.pth 2024-08-29 07:30:18,000 INFO Found Upscale model fast_2x for All: OmniSR_X2_DIV2K.safetensors 2024-08-29 07:30:18,001 INFO Found Upscale model fast_3x for All: OmniSR_X3_DIV2K.safetensors 2024-08-29 07:30:18,001 INFO Found Upscale model fast_4x for All: OmniSR_X4_DIV2K.safetensors 2024-08-29 07:30:18,001 INFO Found Inpaint model default for All: MAT_Places512_G_fp16.safetensors 2024-08-29 07:30:18,002 INFO Found Inpaint model fooocus_head for SD XL: fooocus_inpaint_head.pth 2024-08-29 07:30:18,002 INFO Found Inpaint model fooocus_patch for SD XL: inpaint_v26.fooocus.patch 2024-08-29 07:30:18,003 WARNING Missing LoRA model hyper for SD 1.5 2024-08-29 07:30:18,003 INFO -> No model matches search paths: hyper-sd15-8steps-cfg-lora 2024-08-29 07:30:18,003 INFO -> Available models: flux/flux_realism_lora.safetensors, sd15/drawing.safetensors, sd15/bichu oil painting.safetensors, sdxl/a_graphitecharcoal_style.safetensors, sdxl/chalk_sketch_sdxl_v1.safetensors, sdxl/desolation.safetensors, sdxl/infrared photos.safetensors, sdxl/invert-art.safetensors, sdxl/naturalbodyv2.0.safetensors, sdxl/ryoji ikeda style.safetensors, sdxl/sdxlfaetastic2400.safetensors, sdxl/science_fiction_lens_flares_v1.safetensors, sdxl/simple_ink_drawing.safetensors, sdxl/stop-motion animation.safetensors, sdxl/cyborg_style_xl-off.safetensors, sdxl/extremely_detailed.safetensors, sdxl/faces_v3.safetensors, sdxl/josef_koudelka.safetensors, sdxl/ral-dissolve-sdxl.safetensors, sdxl/tbh35-sdxl.safetensors, sdxl/xl_more_art-full_v1.safetensors, ip-adapter-faceid-plusv2_sdxl_lora.safetensors, ip-adapter-faceid_sdxl_lora.safetensors, lcm-lora-sdv1-5.safetensors, lcm-lora-sdxl.safetensors 2024-08-29 07:30:18,004 WARNING Missing LoRA model hyper for SD XL 2024-08-29 07:30:18,004 INFO -> No model matches search paths: hyper-sdxl-8steps-cfg-lora 2024-08-29 07:30:18,005 INFO -> Available models: flux/flux_realism_lora.safetensors, sd15/drawing.safetensors, sd15/bichu oil painting.safetensors, sdxl/a_graphitecharcoal_style.safetensors, sdxl/chalk_sketch_sdxl_v1.safetensors, sdxl/desolation.safetensors, sdxl/infrared photos.safetensors, sdxl/invert-art.safetensors, sdxl/naturalbodyv2.0.safetensors, sdxl/ryoji ikeda style.safetensors, sdxl/sdxlfaetastic2400.safetensors, sdxl/science_fiction_lens_flares_v1.safetensors, sdxl/simple_ink_drawing.safetensors, sdxl/stop-motion animation.safetensors, sdxl/cyborg_style_xl-off.safetensors, sdxl/extremely_detailed.safetensors, sdxl/faces_v3.safetensors, sdxl/josef_koudelka.safetensors, sdxl/ral-dissolve-sdxl.safetensors, sdxl/tbh35-sdxl.safetensors, sdxl/xl_more_art-full_v1.safetensors, ip-adapter-faceid-plusv2_sdxl_lora.safetensors, ip-adapter-faceid_sdxl_lora.safetensors, lcm-lora-sdv1-5.safetensors, lcm-lora-sdxl.safetensors 2024-08-29 07:30:18,005 INFO Found LoRA model lcm for SD 1.5: lcm-lora-sdv1-5.safetensors 2024-08-29 07:30:18,006 INFO Found LoRA model lcm for SD XL: lcm-lora-sdxl.safetensors 2024-08-29 07:30:18,006 INFO Optional LoRA model face for SD 1.5 not found (search path: ip-adapter-faceid-plusv2_sd15_lora, ip-adapter-faceid-plus_sd15_lora) 2024-08-29 07:30:18,007 INFO Found LoRA model face for SD XL: ip-adapter-faceid-plusv2_sdxl_lora.safetensors 2024-08-29 07:30:18,007 INFO Optional LoRA model lightning for SD XL not found (search path: sdxl_lightning_8step_lora) 2024-08-29 07:30:20,510 INFO SD 1.5: missing 3 models 2024-08-29 07:30:20,510 INFO SD XL: missing 1 models 2024-08-29 07:30:20,511 INFO SD 3: missing 2 models 2024-08-29 07:30:20,511 INFO Flux: supported

[Acly]

It's fine if optional models are missing. But Hyper Lora is required:

2024-08-29 07:30:18,004 WARNING Missing LoRA model hyper for SD XL 2024-08-29 07:30:18,004 INFO -> No model matches search paths: hyper-sdxl-8steps-cfg-lora

It's listed here: https://github.com/Acly/krita-ai-diffusion/wiki/ComfyUI-Setup#sd-xl

[waynemadsen]

I took the nuclear option and completely uninstalled everything and reinstalled it. This was probably a good idea anyway because I had way too many extra comfy custom nodes that I wasn't using and could clean up all my unused model files as well. Using the download_models.py file for custom comfyui required me to run it from comfyui's python directory. Now, my current version of pytorch is 2.3.1 +cu121. This is a shame because the newest pytorch does offer a noticeable 10% decrease in runtime on GGUF.