ls250824

MIniMax H3 video Inference with ComfyUI

ComfyUI base image with CUDA runtime support

ComfyUI base image with CUDA runtime support

Inference WAN 2.x, t2v, i2v, SVI, animate, scail with ComfyUI

LTX 2.x t2v i2v vi2v vt2v inference with ComfyUI

Z-Image, ERNIE-Image, Flux.2, Flux.2 Klein, QWEN image, inference with ComfyUI

Krea-2 Inference with ComfyUI

Base image pytorch CUDA runtime

LLM/VLM inference with oobabooga textgen on runpod

Training Lora’s / models for ComfyUI with AI TOOLKIT user interface.

Training image and video models on runpod.io with diffusion pipe

Python CUDA develop base image

LLM inference with oobabooga text-generation-webui on runpod.io

Pytorch image with cuda for development with code server and jupyter.

Base image pytorch cuda for development

Streamlined setup for running ComfyUI with Ollama.