HYDRA-X is a research model that handles images and video through a single shared tokenizer, which turns out to matter quite a bit for how unified multimodal models are actually built.

Kwai's open 30B MoE model can reason over hour-long videos in a single pass, which puts it in rare company among openly released multimodal models.

A custom ComfyUI node that wires LTX 2.3's multi-subject LoRA system into your existing workflow, so you can anchor a video generation to several specific references at once.

An AI inside Pitch that builds presentations from your own templates and design language, not a generic layout with your colors dropped in.

Google's Stitch turns text prompts into editable UI screens on a live canvas, then ships them straight to Figma or your build tool in one click.

Point an AI coding agent at a product URL and get a working Remotion project back, no video-generation model in the loop.

Microsoft's 3.8B-parameter diffusion model punches at FLUX and SD3 levels while costing meaningfully less to train, which matters if you care about what comes next in open image generation.

Paste in a prompt and Hera hands back a finished launch video with pacing, typography, and motion already decided, which matters if you are a one-person team that needs to ship fast.

A design agent that takes a prompt and produces a working prototype using your existing component library, so what you hand to engineering already speaks their language.

Anthropic's design-focused Claude mode lets you talk your way to a working prototype, slide deck, or one-pager without leaving the chat.

An 8B-parameter open-weight image model from Baidu that claims top-of-class quality among open generators, worth a look if you're weighing alternatives to Flux or SD3.

A Figma-built MCP tool that gives AI coding agents direct access to your design system, so what they generate actually matches your components and tokens.

A set of 19 Claude Code skills that wire Claude directly into Higgsfield AI, so you can generate images, kick off Seedance 2.0 video jobs, and run full UGC ad pipelines from a single automated workflow.

A set of structured skills for tools like Cursor or Copilot that steer the AI through a real design process instead of letting it freestyle.

A multimodal open model from GAIR that turns text or images into video with synced audio, tuned specifically for human subjects.

A custom ComfyUI node that takes a reference image and a reference voice and keeps both consistent through a generated clip, so you can build video around a specific identity instead of a generic one.

Chronicle takes your notes or rough prompts and builds a full slide deck, then lets you refine it through conversation rather than endless manual tweaking.

67 ready-to-drop DESIGN.md and SKILL.md files that teach agentic tools your taste before they touch a pixel.

A set of skills that loads Claude Code with working knowledge of ComfyUI's node APIs, so you can describe the node you want and get code that actually fits the system.

Kodo turns a text prompt into a structured, editable design — poster, slide, menu, social graphic — so you are working with real layers instead of a flattened image you cannot touch.

Lightricks' latest open model takes text, images, or existing clips and returns video with audio already attached, skipping the separate sound step that makes most open video pipelines a chore.

Anthropic's Claude now lives inside PowerPoint itself, reading your layouts and slide masters so it can build and edit slides without breaking your template.

An MCP server that connects Claude Code directly to ComfyUI, so you can generate images and video, edit your graph, and manage models without leaving your terminal session.

A Claude Code skill that runs 250-plus checks across your Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads accounts and hands back a weighted score with recommendations.

Anthropic's most capable Claude yet, built for long-running tasks and deep reasoning across large amounts of context.

An open-source MCP server that lets Claude and other AI assistants drive Photoshop directly, so you can describe what you want and watch the layers move.

A custom node suite that brings Alibaba's Qwen3-TTS models into your ComfyUI workflow, letting you generate, design, and clone voices without leaving the graph.

A custom node that gives you an interactive 3D viewport inside ComfyUI so you can set exact camera angles and pipe them straight into your image generation prompts.

A fine-tune on Qwen's image editing model that takes a photo and hands back a version of it from a new camera position, which saves a reshoot for product or object work.

Lightricks' open video model that generates picture and sound together in one pass, saving you the separate audio step that most open models leave behind.