Open Generative AI, Tested

Illustration of a node-based video generation workflow ending in a film strip

LTX Video: Open AI Video Generation, Models, and ComfyUI Workflows

LTX Video and LTX-2 explained: synchronized audio-video generation, ComfyUI workflows, keyframes, controls, upscaling, hardware and local deployment.

Sep 18, 20265 min read

Read article

Editorial illustration connecting an open geometric structure to text, image, video and audio

Models

Open Source AI Models: A Practical Guide to Choosing and Running Them

Sep 18, 20267 min read

Video

Wan AI Video Models: Open Generation, Workflows, and Local Use

Sep 18, 20268 min read

Latest Articles

Image, audio, text and video inputs passing through a prism into sorted categories

Guides

Clef-omni Tutorial: Multimodal Classification with Workers AI

Build a documentation-based Clef-omni classifier with Python, understand multimodal inputs and pricing, and plan a fair accuracy and…

Oct 19, 20263 min read

Conceptual API gateway connecting to image, video and audio outputs

ComfyUI

Comfy Router API Tutorial: Setup, Routing & Cost Comparison

Set up Comfy Router with a documented Python example, understand provider routing, and compare hosted API costs with…

Oct 19, 20263 min read

Conceptual illustration of a chat bubble connecting to image-generation nodes and a product-video filmstrip

ComfyUI

Comfy Agent Tutorial: Image & Video Workflows in Comfy Cloud

Learn how to use Comfy Agent in Comfy Cloud to build and refine image and video workflows with…

Oct 19, 20264 min read

Conceptual illustration of connected AI workflow nodes flowing from a GPU workstation into cinematic film frames.

News

Comfy Launches $25,000 Open-Source App Challenge: How to Enter

Comfy’s Open Source Higgsfield challenge offers $25,000 in prizes. Explore the deadline, entry requirements, and what open source…

Oct 17, 20263 min read

Illustrated Qwen Image 2.1 Turbo ComfyUI guide showing eight sampling steps and CFG 1

News

Qwen-Image-2.1-Turbo in ComfyUI: Official Setup, Settings & License

Set up Qwen-Image-2.1-Turbo in ComfyUI using official model files. Explore sampling settings, workflow requirements, and licensing.

Oct 15, 20263 min read

AI-generated editorial illustration of an ArtCraft-style 3D filmmaking editor showing character posing, sci-fi scene, timeline, asset library and camera settings.

Video

ArtCraft: Open-Source AI Filmmaking Studio for 2D, 3D and Video

ArtCraft brings 2D/3D scene control to AI filmmaking. Explore its GitHub features, model support, open-source license, costs, and…

Oct 12, 20267 min read

News

All news

Mistral Large 4 Le Chonk AI model with 1T total parameters, 49B active parameters and reasoning capabilities

News

Mistral Large 4 (Le Chonk): What the New 1T Open-Weight Model Means for Local AI

Mistral Large 4, nicknamed Le Chonk, is a 1T-parameter multimodal MoE model in public preview. Here is what is available now, when…

Oct 7, 20264 min read

Kandinsky 6.0 AI video and synchronized audio generation with ComfyUI workflow

News

Kandinsky 6.0 Is Open Source: Video + Audio Generation in ComfyUI

Kandinsky 6.0 is now open source with synchronized video and audio generation, Lite and Pro models, Full-HD super-resolution, and a ComfyUI integration.

Oct 7, 20264 min read

ComfyUI 0.39 update featuring MiniMax H3 workflow improvements

News

ComfyUI 0.39: What Changed for MiniMax H3 Workflows?

ComfyUI 0.39 adds important MiniMax H3 improvements, higher-quality video encoding defaults, Qwen Image 2.1 fixes, and workflow memory optimizations. Here is what…

Oct 7, 20263 min read

News

Wan 3.0: Alibaba’s New AI Video Model

Wan 3.0 explained using Alibaba’s documentation: video generation, native audio, references, API access and the distinction from open-weight Wan releases.

Sep 9, 202615 min read

DeepSeek-V4-Flash-Vision-Exp illustration

News

DeepSeek Ships an Experimental Vision Model, Claims It Rivals Opus 4.8 on Agent Tasks

DeepSeek quietly released DeepSeek-V4-Flash-Vision-Exp, a multimodal variant the company says closes the gap with Anthropic's Opus 4.8 on agent benchmarks that require…

Sep 8, 20262 min read

News

GitHub’s HydraFusion Picks a Different AI Model for Every Coding Task, Automatically

GitHub's new Copilot CLI research preview builds a custom workflow per task instead of running everything through one model, claiming a 67%…

Sep 8, 20262 min read

Guides & Evergreen

All guides

Reference pieces we keep current: models, local setups and the workflows around them.

ComfyUI
ComfyUI Automation Workflows: Automate AI Image & Video Generation
Learn how to automate ComfyUI image and video workflows with its API, workflow JSON, queues, webhooks and n8n—from a simple…
Sep 27, 20267 min read
ComfyUI
Comfy Cloud vs Local GPU: Which Is Better for ComfyUI?
Compare Comfy Cloud with running ComfyUI on a local GPU: setup, cost, VRAM, custom nodes, video workflows, privacy, speed, and…
Sep 25, 20266 min read
ComfyUI
ComfyUI Cloud: How to Run ComfyUI Online Without a Local GPU
Run ComfyUI in the cloud without a local GPU. Learn how Comfy Cloud works, what it costs, when to use…
Sep 25, 20266 min read
ComfyUI
ComfyUI Video Workflows: How AI Video Pipelines Fit Together
Learn how to build a ComfyUI image-to-video workflow step by step, choose Wan or LTX, troubleshoot VRAM, export clips and…
Sep 18, 202610 min read
ComfyUI
How to Install ComfyUI on Windows, macOS, and Linux
Learn how to install ComfyUI on Linux, Windows, and macOS using the official Desktop, portable, or manual setup. Includes GPU…
Sep 18, 202614 min read
Local AI
Local AI: How to Run Generative AI on Your Own Hardware
Local AI explained: run LLMs, image and video models on your own hardware with private inference, self-hosted APIs, Apple Silicon…
Sep 18, 202614 min read

The Signal — Open Generative AI, Tested

Latest Articles

News

Guides & Evergreen

More from the desks

Stay ahead in the AI revolution