The ultimate training toolkit for finetuning diffusion models
☆12,189Sep 27, 2026Updated this week
Alternatives and similar repositories for ai-toolkit
Users that are interested in ai-toolkit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆2,077Updated this week
- Dead simple FLUX LoRA training UI with LOW VRAM support☆3,254Jul 28, 2026Updated 2 months ago
- A general fine-tuning kit geared toward image/video/audio diffusion models.☆2,931Updated this week
- A pipeline parallel training script for diffusion models.☆2,027Updated this week
- ☆6,720May 24, 2026Updated 4 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- OneTrainer is a one-stop solution for all your Diffusion training needs.☆3,227Updated this week
- One-click Portable Windows installation of 'AI-Toolkit by Ostris'☆521Sep 12, 2026Updated 3 weeks ago
- The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in th…☆135,980Updated this week
- ☆12,616Aug 1, 2026Updated 2 months ago
- ☆7,243Sep 24, 2026Updated last week
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,958Sep 6, 2026Updated 3 weeks ago
- ComfyUI Plugin of Nunchaku☆2,928Sep 6, 2026Updated 3 weeks ago
- Official SeedVR2 Video Upscaler for ComfyUI☆2,891Dec 24, 2025Updated 9 months ago
- Official repository of In-Context LoRA for Diffusion Transformers☆2,083Dec 20, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆2,227Nov 8, 2024Updated last year
- Various custom nodes for ComfyUI☆3,346Sep 13, 2026Updated 2 weeks ago
- ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable,…☆16,331Updated this week
- ☆1,161Apr 2, 2025Updated last year
- ☆1,348Updated this week
- GGUF Quantization support for native ComfyUI models☆4,115Jan 12, 2026Updated 8 months ago
- LTX-Video Support for ComfyUI☆4,164Updated this week
- Official inference repo for FLUX.1 models☆26,005Jul 31, 2025Updated last year
- Practice Code for text to image trainer☆557Feb 27, 2026Updated 7 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆13,043Jul 31, 2025Updated last year
- ☆6,136Apr 14, 2025Updated last year
- High quality training free inpaint for every stable diffusion model. Supports ComfyUI☆1,420Updated this week
- [NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment☆3,555Jul 31, 2025Updated last year
- Enjoy the magic of Diffusion models!☆13,200Updated this week
- JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for th…☆1,270Feb 24, 2026Updated 7 months ago
- Nodes for image juxtaposition for Flux in ComfyUI☆1,392Jan 9, 2025Updated last year
- In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.☆2,771Updated this week
- ☆12,059Feb 9, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆1,363Apr 21, 2025Updated last year
- A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.☆9,903Updated this week
- ☆1,703Oct 30, 2024Updated last year
- Qwen-Image text to image lora trainer☆766Dec 16, 2025Updated 9 months ago
- Making ComfyUI more comfortable!☆3,527Sep 25, 2026Updated last week
- [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing☆3,959Oct 17, 2025Updated 11 months ago
- ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE), and Qwen3.8-VL, …☆900Sep 14, 2026Updated 2 weeks ago