TheMistoAI/ComfyUI-Anyline: Anyline: A Fast, Accurate, and Detailed Line Detection Preprocessor ( github.com )
DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation ( i.imgur.com )
Abstract...
AI Lighting - Demonstration With Iconic Movie Scenes ( www.youtube.com )
lllyasviel/IC-Light: Imposing Consistent Light - Relight Any Image ( github.com )
TheMistoAI/MistoLine: A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning ( github.com )
Training Loras - Is SDXL still the best?
Hey folks, I've been training Loras now for a while, and have some scripts I really like that I've been working with. However, I realized I haven't been keeping up lately, so, is SDXL still the best for Loras? And by that I mean before with 1.5 and standard SDXL is the most accurate quality I've received....
A Write-Up of Perturbed Attention Guidance ( stable-diffusion-art.com )
PuLID Now Supported in SD WebUI Controlnet ( github.com )
AI Wallpaper Changer for Android ( play.google.com )
Hello there, fellow lemmings!...
PuLID: Pure and Lightning ID Customization via Contrastive Alignment ( i.imgur.com )
Abstract...
Towards Pony Diffusion V7 | Civitai ( civitai.com )
Making a Comic with Consistent Characters Without LoRA Training | Civitai ( civitai.com )
Image composition node/library/checkpoint
This stuff moves so fast I really can't keep up and a lot of the research posted here goes a bit over my head. I'm looking for something that doesn't seem too out of the question given things like CLIPSeg. Is there some tool or library out there that will accept an image and a prompt and then generate a mask within the image...
ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning ( i.imgur.com )
Abstract...
HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models ( i.imgur.com )
Abstract...
xavihart/PDM-Pure: PDM-based Purifier ( github.com )
impactframes/llama3 Ifai SD Prompt Mkr q4km ( ollama.com )
AI-Assisted Reference and Photobashing for Pixel Artists ( pixelparmesan.com )
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis ( hyper-sd.github.io )
Abstract...
s-du/ScribbleArchitect: Transform your simple scribbles into architectural designs using style transfer with Stable Diffusion, LCM, IP Adapters and ControlNet. ( github.com )
https://github.com/s-du/ScribbleArchitect/raw/master/docs/anim5.gif
EdgeFusion: On-Device Text-to-Image Generation ( i.imgur.com )
Abstract...
Mikubill/SD Webui Controlnet Updated With IPAdapter Advanced Weighting [Instant Style] ( github.com )
Factorized Diffusion: Perceptual Illusions by Noise Decomposition ( dangeng.github.io )
tl;dr: We can control components of generated images with a pretrained diffusion model. We use this to generate various perceptual illusions....
Testing Stable Diffusion 3
Tonight I tested out SD3 via the API. I sadly do not have as much time as with my Stable Cascade review, so there will only be four images for most tests (instead of 9), and no SD2 controls....
Stable Diffusion 3 API Now Available — Stability AI ( stability.ai )
