Teriks/dgenerate
dgenerate is a scriptable command line tool (and library) for generating images and animation sequences using stable diffusion and related techniques, with an accompanying GUI scripting environment.
Supports multiple model architectures (SD, SDXL, SD3, Flux, Kolors) with advanced control mechanisms like ControlNets, IP-Adapters, and LoRA, plus frame-by-frame video processing via FFmpeg with memory-efficient streaming. Built-in shell language enables scriptable workflows with intelligent VRAM management and caching, extensible through Python plugins for custom processors and prompt weighters. Integrates HuggingFace and CivitAI model repositories, leverages spandrel for restoration models (ESRGAN, SwinIR), and supports multi-GPU backends including NVIDIA CUDA, AMD ROCm, and Apple Silicon.
Available on PyPI.
Stars
42
Forks
1
Language
Python
License
BSD-3-Clause
Category
Last pushed
Oct 15, 2025
Monthly downloads
242
Commits (30d)
0
Dependencies
52
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Teriks/dgenerate"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sakalond/StableGen
Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
neggles/animatediff-cli
a CLI utility/library for AnimateDiff stable diffusion generation
victordibia/peacasso
UI interface for experimenting with multimodal (text, image) models (stable diffusion).
carefree0910/carefree-drawboard
🎨 Infinite Drawboard in Python
ai-forever/Kandinsky-2
Kandinsky 2 — multilingual text2image latent diffusion model