A tiny graphical application for local AI generation
-
Updated
Aug 22, 2026 - C++
A tiny graphical application for local AI generation
WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.
Pure MLX port of Baidu ERNIE-Image (8B single-stream DiT) for text-to-image generation on Apple Silicon
Claude Code skill for generating local images with Baidu AI Studio ERNIE-Image models, Chinese prompt support, safe outputs, and validation.
50 curated ERNIE Image prompts collected from the community — preview images, original-author credits, one-click generation at glmimage.app
星河 AI 生图 Skill — 基于百度飞桨 ERNIE-Image,支持封面图、文章配图、信息图、小红书图文
To associate your repository with the ernie-image topic, visit your repo's landing page and select "manage topics."