Hellow guys, Welcome to my website, and you are watching Kasucast #21 - Improving Stable Diffusion images with FreeU (SDXL, LCM, Turbo) and ComfyUI API. and this vIdeo is uploaded by kasukanra at 2023-12-08T10:45:19-08:00. We are pramote this video only for entertainment and educational perpose only. So, I hop you like our website.
| Name | Kasucast #21 - Improving Stable Diffusion images with FreeU (SDXL, LCM, Turbo) and ComfyUI API |
| Video Uploader | Video From kasukanra |
| Upload Date | This Video Uploaded At 08-12-2023 18:45:19 |
| Video Discription | #sdxl #ComfyUI #comfyui #api #LoRA #LCM #sdxlturbo #freeu #stablediffusion This is a video about tuning FreeU hyperparameters for Stable Diffusion. I show how to use both the ComfyRoll custom nodes and the ComfyUI API to grid search for the ideal b1, b2, s1, s2 parameters. TEMPORARY FIX FOR XY GRID GENERATION BY @SakuraSuzie (CREATOR OF COMFYROLL NODES): https://discord.com/channels/1085650148106981418/1085699721089273897/1183398350935052379 Wiki pages will be updated soonTM: https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki Watch this video for in-depth training on SDXL: https://youtu.be/QpWacUWeqbE My github repository for this project: https://github.com/kasukanra/comfy_api_tune_freeu ComfyRoll Custom Nodes: https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes ComfyUI Script Examples for API: https://github.com/comfyanonymous/ComfyUI/tree/master/script_examples Models: SDXL Turbo: https://huggingface.co/stabilityai/sdxl-turbo/tree/main SDXL LCM LoRA: https://huggingface.co/latent-consistency/lcm-lora-sdxl 📳Links to my models/LoRAs: https://pastebin.com/x5tMpe2h Final hyperparameters: Normal SDXL kasukanra style finetune: b1: 1.5 b2: 1.3 s1: 1.1 s2: 0.2 SDXL kasukanra style finetune + LCM LoRA: b1: 1.6 b2: 1.1 s1: 1.3 s2: 1.1 SDXL kasukanra style finetune + Turbo LoRA: b1: 1.8 b2: 1.3 s1: 1.6 s2: 1.4 Resources: FreeU paper: https://arxiv.org/abs/2309.11497 ComfyRoll XY From Folder github issue: https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/issues/22 @GrocksterRox YT video on ComfyRoll nodes: https://www.youtube.com/watch?v=81R8mgYhq_k CivitAI XY grid demos: https://civitai.com/models/159165/comfyui-xy-grid-demos-xy-anything bmaltais kohya_ss: https://github.com/bmaltais/kohya_ss Timestamps: 00:00 Introduction 00:56 FreeU paper 03:43 How do b and s value interact 04:52 ComfyRoll nodes 05:47 CivitAI workflows downloads 06:30 ComfyRoll workflows 08:41 ComfyRoll Grid error 09:06 Debugging the grid error 11:07 Trying out ComfyRoll XY list 14:16 Finding a fix for grid error 15:54 ComfyUI API 16:36 ComfyUI API JSON 18:45 How to request ComfyUI API 20:13 Re-evaluating the API JSON file 20:54 Code overview 22:59 Selecting baseline freeU s values 23:46 Handling asynchronous calls as ComfyUI API doesn't have callbacks 24:52 Setting up code environment 26:44 Executing the code 28:01 Analyzing the dynamic b values for normal FreeU 32:23 Narrowing the search window 36:04 Why choose static s values of 1.1 and 0.2? Why not use 0, 0 or 1, 1? 38:14 Dynamic s values 41:52 Getting original seed value 43:22 Pointing out my mistake with my seed value wasn't working 44:57 Comparing with original generations as a sanity check 45:32 Comparing results so far 46:30 Workflow for kohya deep shrink 47:00 LCM workflow 47:31 Dynamic b values for LCM 48:48 Dynamic s values for LCM 50:51 Updated comparison of all results so far 51:22 Extracting SDXL turbo LoRA 52:58 SDXL Turbo LoRA workflow 54:30 Dynamic b values for SDXL Turbo 55:37 Comparing different b1, b2 values for SDXL Turbo 56:11 Dynamic s values for SDXL Turbo 57:00 Final comparison of all results so far 📳My Training Settings and ComfyUI workflows: https://github.com/kudou-reira/SDXL_training_settings/tree/main/training_settings 📳Links to my models/LoRAs: https://pastebin.com/x5tMpe2h 💬 Discord channel: https://discord.gg/ZKX3Zym8FQ 🎭 Patreon: https://patreon.com/kasukanra 🎁 Tips/Donations: https://streamlabs.com/kasukanra/tip 🎉 Social Media: 📷 Instagram: https://www.instagram.com/kasukanra/ 🎨 Artstation: https://www.artstation.com/kasukanra 🐦 Twitter: https://twitter.com/kasukanra 🐀 Twitch: https://twitch.tv/kasukanra 📩 art enquiries: kagurazaka@protonmail.com Images/processes may be fabricated and therefore not real. I am unaware of any illegal activities. Documentation will not be taken as admission of guilt. |
| Category | Howto & Style |
| Tags | ai art | stable diffusion | digital art | machine learning | midjourney | photoshop | character art | concept art | character design | textual inversion | automatic1111 | webui | how to make ai art | kasukanra | workflow | dreambooth | style | dreambooth style | training dreambooth for style | anime art | artstyle | controlnet | LoRA | digital sculpting | training LoRA for style | convolutional layer | vtuber | SDXL | SDXL1.0 | style training | freeU | sdxl turbo | LCM |
