stable-diffusion
links
ui
models
extensions
- controlnet 1.1
- Stable Diffusion Dynamic Prompts extension
- Photopea Stable Diffusion WebUI Extension
- Detection Detailer
- Regional Prompter
videos
- ControlNet - Revealing my Workflow to Perfect Images
- Ultra Sharp Upscale
- How to do Stable Diffusion Textual Inversion
- Textual Inversion Tutorial
- ControlNet (Sebastian Kamph)
- Stable Diffusion Tutorial for Prompts
- LORA training in Stable Diffusion
docs
- Well-Researched Comparison of Training Techniques (Lora, Inversion, Dreambooth, Hypernetworks)
- Where do i find LORA training on vlad
- OpenArt prompt book
- Common problems in AI images and how to fix them
- Tutorial: konyconi-style LoRA
- Stable Diffusion Cheat Sheet
- SD Camera Guide
- Lazy ass low effort LORA
- Control lighting
- Train your ControlNet with diffusers
tools
- birme
- hydrus - media tagger
- Lama Cleaner - image inpainting tool
news
containers
hosts
poses
examples
research papers
posts
links
Introducing Stable Diffusion 3.5 - A nice surprise considering the flop of sd3, the emergence of flux models and the non-commercial license on flux-pro. That first image is next level considering the gimped sd3 (censored) and the prompt “woman lying in grass” drama
Stability AI holds on, appointing a new CEO.
ComfyUI author is leaving Stability AI and starting Comfy Org to
continue to develop and improve ComfyUI with a lot more resources. Updates on ComfyUI Blog
SD3 weights dropped last night. I gave it a shot last night myself with their supplied comfyui workflows, as a base model it looks extremely promising, details are next level, though it still doesn’t appear to know jack about hands, faces still need hires fix. Very promising for a base model.
Stable Diffusion 3: Research Paper
Stable Diffusion 3 outperforms state-of-the-art text-to-image generation systems such as DALL·E 3, Midjourney v6, and Ideogram v1 in typography and prompt adherence, based on human preference evaluations.