I've been reading more into training (mostly for wan2.1) lately and noticed this optimizer as an option in ai-toolkit as well as in diffusion-pipe. ...
It's been a while since I've updated my Stable Diffusion kit, and the technology moves so fast that I should probably figure out what new tech is out there. ...
Context: Pony Diffusion v6 is one of the most popular SD models, and the upcoming v7 has the potential for similar popularity. An interesting aspect is their controversial decision to use AuraFlow as a base model, rather than Flux or SD3 The creator of Pony Diffusion (AstraliteHeart) was interviewed on a Civit.ai stream two ...
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Abstract ...
Is there a way to create art for a book with consistent theme and characters using AI?
I'm interested in creating art for a book, like art that goes alongside the text. ...
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
Abstract ...
Um if I upload a pic of my dog can someone cartoonize it like smoking a blunt or cigar or cig?? Don't really know how it works here because the mods post shhoow. Any help will help??
CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models
Abstract ...
OmniGen: Unified Image Generation
Abstract ...
Automagic optimizer?
I've been reading more into training (mostly for wan2.1) lately and noticed this optimizer as an option in ai-toolkit as well as in diffusion-pipe. ...
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Abstract ...
rupeshs/fastsdcpu Release v1.0.0-beta.250 SANA sprint CPU support(OpenVINO)
Release : https://github.com/rupeshs/fastsdcpu/releases/tag/v1.0.0-beta.250
From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
Abstract ...
DDT: Decoupled Diffusion Transformer
Abstract ...
InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework
Abstract ...
mcmonkeyprojects/SwarmUI: SwarmUI Beta 0.9.6 Release
Release: https://github.com/mcmonkeyprojects/SwarmUI/releases/tag/0.9.6-Beta
What's everybody using for AI art and video generation nowadays?
It's been a while since I've updated my Stable Diffusion kit, and the technology moves so fast that I should probably figure out what new tech is out there. ...
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Abstract ...
Single Image Iterative Subject-driven Generation and Editing
Abstract ...
Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models
Abstract ...
ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer
Abstract ...
CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
Abstract ...
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Abstract ...
DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
Abstract ...
1.58-bit FLUX
Abstract ...
Some thoughts on Pony v7 deciding to use AuraFlow (PonyFlow)
Context: Pony Diffusion v6 is one of the most popular SD models, and the upcoming v7 has the potential for similar popularity. An interesting aspect is their controversial decision to use AuraFlow as a base model, rather than Flux or SD3 The creator of Pony Diffusion (AstraliteHeart) was interviewed on a Civit.ai stream two ...
Anyone know of a good QR code generation service for high-res images?
Basically, I want to make an artistic QR code of a website I made for my girlfriend, and then ship her a jigsaw puzzle of the QR code art. ...
What are some tools for organizing Stable Diffusion-generated images?
The megathread mentions Diffusion Toolkit, although this is a Windows-only tool. ...