Chokri Boubakri
Chokri Boubakri is the editor of The Signal. An AI automation strategist and e-commerce growth specialist based in Sfax, Tunisia, he builds AI-powered SaaS tools and runs performance campaigns for clients across the Maghreb, the Gulf and Europe. The Signal is where he files what he finds about open models, local AI setups and the tools built around them.
Rapid-MLX: A Local, OpenAI-Compatible AI Server for Apple Silicon
Rapid-MLX is a local AI server for Apple Silicon that runs LLMs on M-series Macs with OpenAI- and Anthropic-compatible APIs, CLI, desktop app and coding-agent support. License unverified.
llamafile: Run an Open LLM From a Single Executable File
llamafile is a single-file local LLM runtime from Mozilla.ai that bundles llama.cpp into a portable executable for macOS, Linux and Windows, with no installation required. License unverified.
VideoCrafter: Tencent AI Lab’s Open Text- and Image-to-Video Toolbox
VideoCrafter is an open-source AI video generation toolbox with text-to-video and image-to-video models, inference scripts and a Gradio demo, including VideoCrafter1 and VideoCrafter2. License unverified.
DramaClaw: A Self-Hosted Pipeline From Script to AI Short Drama
DramaClaw turns manuscripts into finished AI short dramas: episode planning, storyboards, voice-over and editing, plus a node canvas and agent. License unverified.
HunyuanVideo-1.5: Tencent’s 8.3B Open Video Generation Model
HunyuanVideo-1.5 is an 8.3B-parameter text- and image-to-video model with training code, Diffusers and ComfyUI support. 14GB VRAM minimum. License unverified.
PromptEnhancer: Tencent Hunyuan’s Prompt Rewriter for Image Models
PromptEnhancer (CVPR 2026) rewrites rough prompts into structured ones for text-to-image and image editing. 7B and 32B models, GGUF options. License unverified.
RedInk: Self-Hosted Generator for Xiaohongshu Image Posts
RedInk turns one sentence into a multi-page Xiaohongshu-style image post using Gemini and Nano Banana Pro via your own API keys. Docker install. License unverified.
VTP: MiniMax’s Research on Scalable Visual Tokenizers
VTP explores scalable visual tokenizer pre-training for image generation, combining representation learning and reconstruction to improve generative model scaling. Code and weights available; license unverified.
ReVersion: Teaching Diffusion Models a Relation From Examples
ReVersion is a diffusion-based relation inversion method that learns visual relationships from a few example images and applies the learned relation to new subjects and scenes. License unverified.
Stable Virtual Camera: Stability AI’s Model for New Camera Angles
Stable Virtual Camera is a 1.3B diffusion model for novel view synthesis, generating 3D-consistent camera views from one or more input images with controllable target cameras. License unverified.