shootthesound/comfyUI-Realtime-Lora
Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5
Integrates three modular training backends (sd-scripts, Musubi Tuner, AI-Toolkit) supporting 8 model architectures through a unified ComfyUI interface with 34 specialized nodes. Beyond training, it provides GPU-accelerated LoRA merging/compression via model diffing, block-level selective loading with strength scheduling across 25-32 architecture-specific blocks, and layer-scale model editing. Handles multiple LoRA formats (standard, LoKR, LoHa, GLoRA) with automatic detection and proper decomposition handling.
429 stars.
Stars
429
Forks
35
Language
Python
License
MIT
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/shootthesound/comfyUI-Realtime-Lora"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Comfy-Org/comfy-cli
Command Line Interface for Managing ComfyUI
runpod-workers/worker-comfyui
ComfyUI as a serverless API on RunPod
YanWenKun/ComfyUI-Docker
🐳Dockerfile for 🎨ComfyUI. | 容器镜像与启动脚本
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Acly/comfyui-tooling-nodes
Nodes for using ComfyUI as a backend for external tools. Send and receive images directly...