pony-diffusion

Train LoRAs for Qwen-Image 2.1, FLUX.2 Klein 9B, FLUX.3 Image Klein, Krea 2, Z-Image, MOSS-Image, ERNIE-Image, Ideogram 4, Anima, SDXL (Pony, Illustrious, NoobAI), LTX 2.3, MiniMax-H3, and more on NVIDIA GPUs from 4–8 GB VRAM. One install, one launcher, NF4 models. Windows, Linux and RunPod.

Pony Diffusion V5 / V6 styles collection for A1111 WebUI

Wildcards for Stable Diffusion. A curated collection of high-quality wildcards designed to enhance your scene generation. These wildcards will introduce an element of randomness, and allow for the creation of unique, realistic, and artistic images with ease.

A collection of Stable Diffusion Templates that will allow you to use best UIs with the best checkpoints and significantly reduce the time needed to get started.

Turn a character, style, or concept into a ready-to-train LoRA dataset - consistent multi-angle shots, smart captions (prose / Danbooru / e621 / dedicated taggers), and trainer-ready configs for Flux, SDXL, Krea, Pony & more. Local or cloud, per stage. No training launched, no telemetry.

Serpentnote is a Tauri based prompt manager.

SillyTavern extension for selecting Pony Diffusion V6 XL LoRAs in a dedicated ComfyUI workflow.

SillyTavern extension — route image tag generation to a secondary LLM. Cheaper, faster, uncensored.

A web UI for Stable Diffusion with a modern design similiar to stable-diffusion-ui

A friendly app for your own ComfyUI: compare LoRAs side by side with the same seed, plus characters, tag library, reference images, try-on, upscale and background removal.

Filters gendered Danbooru style tags and natural language to a prefered binary gender for automated workflows.

🚀 Production-grade Google Colab AI Hub: Stable Diffusion Forge SDXL/Pony, W-Okada Realtime Voice Changer, GPT-SoVITS TTS, Applio & KoboldCpp Stheno on Tesla T4 Free Tier.