Design Tool

Runway, Pika, Magnific, and Promptsref added Seedream 5.0 Pro access. Magnific advertised unlimited 1.5K generations for a month, while Runway highlighted reference images and text in up to 14 languages.

Meng To showed Taste with Codex or Claude Code rebuilding landing pages from screenshots and videos. Voila also launched a tool that inspects UI and turns edits into code, copy, prompts, tasks, or agent handoffs.

Meng To shared workflows that convert screen recordings, assets, and scroll behavior into detailed prompts. The resulting prompts were used for Fable 5, Aura, and Koisei landing-page builds.

Figma Motion demos showed designers prompting animations while retaining manual parameter control and auto-keyframes for shader and button effects. Try it for non-destructive animation edits across videos, frames, and objects.

Magnific published a workflow using Library, MCP, Fable 5, and Seedance 2.0 4K to build branded landing pages with scroll-scrubbed, cursor-reactive product video. Use it if you want product context, motion prompting, and page assembly in one repeatable site-build process.

Google's fast image model moved from Gemini API and AI Studio into Leonardo, Magnific, and Figma Weave within a day, with platforms touting sub-4-second generation, readable text, and quick edits. Use the same model inside design and asset tools if you want rapid image workflows beyond Google's interfaces.

Magnific rolled Gemini Omni Flash into its MCP and Spaces workflow with claims that edits keep the full scene in memory across turns, while Figma Weave also added access in its Google-model bundle. That expands Google’s video-editing model beyond AI Studio into creator tools built for iterative asset work.

MotionSites demoed a Gemini plus Antigravity prompt that generates a multi-section animated dental landing page, then said it will pay designers who publish Figma or Framer sites to the platform. The setup combines prompt templates, hosted motion pages, and a submission marketplace in one web-design workflow.

Figma Weave now exposes 20+ AI tools inside the desktop app and adds reusable node workflows for repeatable pipelines. Creators can use it to standardize illustration work, while full Figma frame embedding still appears to be coming soon.

Creator testing around Figma Motion now shows shader prompts, canvas handles, and keyframe retiming in the beta, alongside a detailed tutorial. Designers can keep more motion polish inside Figma before handing work to separate animation or code tools.

Figma added MCP connectors so the Figma agent can reach apps like GitHub, Slack, Notion, Atlassian, Granola, Hex, and Dovetail. Testers can start trying connected code and video workflows as the beta rolls out.

Figma Motion adds animation editing inside the design file with a collaborative timeline and exports to MP4, WebM, GIF, and code. Use it to keep common UI and launch-film motion work in Figma instead of handing it off to another tool.

Krea 2 Turbo arrived with open weights, commercial rights, ComfyUI workflows, and community GGUF and FP8 ports that users say can run locally on modest hardware. Early benchmarks praise speed and style range, while some testers flag drift toward recognizable IP.

Organizers say Gallery of the Future brought 100+ artists and filmmakers onto one Firefly Board, with 50,000 views and a planned zine and exhibition follow-up. The project turned Boards into a real large-scale co-creation test, while participants flagged desktop-only use, character limits, and heavy-file handling as practical constraints.

Figma expanded its design agent beta to all Pro, Org, and Enterprise plans ahead of Config. Teams on paid tiers can now test the agent more broadly as it moves from a narrow preview to a feature with real workflow coverage.

A workflow thread showed Moda ingesting references through its web app or Claude MCP, then turning plain-language prompts into reusable Instagram carousel templates refined with Brand Kits and art-direction passes. That matters because it shifts carousel production out of Figma and Photoshop into an iterative design-agent loop.

Photoshop AI Assistant was presented as a text-driven editor that targets specific parts of an image, preserves consistency, and names layers automatically. Watch how quickly it speeds selective edits inside Photoshop and whether users trust it for more complex retouching.

Anthropic shipped two-way syncing between Claude Code and Claude Design, letting teams pull a design system into a repo or push built UI back into the canvas. The release connects component libraries to live code; teams should use it to reduce handoff drift between design and implementation.

Creators reported Framer 3.0 generating components, auto layout, and breakpoints through new agent flows. Early reactions also said a single prompt can consume about 1,000 credits, so teams should test cost per task before scaling usage.

Midjourney announced a livestream for its first hardware project on June 17 in San Francisco and teased it in replies. Official hints say it is bigger than an orb, can be entered, and is still a few months from wider availability.

Figma updated its MCP server to generate and edit Slides decks, build FigJam boards from data, and roundtrip code into Figma Make. The release also adds custom font support and image exports, extending MCP into presentation and board workflows.

Multiple creator demos showed Adobe for creativity in Claude handling template swaps, recolors, animation, and asset actions inside a single chat, with a second walkthrough covering skills-based setup. It matters because branded social production can stay inside Claude instead of bouncing between apps, though today’s evidence comes from sponsored creator demos rather than an Adobe launch post.

Forge showed its landing page being designed and choreographed with on-canvas sliders instead of code. The beta tool matters because it edits live routes on one canvas and links that surface to agent-assisted code changes.

Creators published prompt stacks showing Claude Opus 4.8 and Gemini 3.1 Pro building animated hero sections and full landing pages, with Fable-era demos supplying longer asset maps. The workflow pushes AI web design beyond wireframes into motion, media choreography, and inspectable front-end polish.

Magnific rolled five new image, video, and upscaling models into its workspace and added Auto Layers for editable text, subject, and background separation. Designers can now move from layout to layered edits and model switching inside one tool, while MCP generations still use Magnific credits.

Figma shipped a Chrome extension that converts live websites into editable Figma layers and teased design-system-based generation as the next step. It matters because designers can start from real product surfaces instead of rebuilding layouts by hand.

Magnific added a Designer node inside Spaces, letting users place generated images and text directly into layouts with fonts, effects, and multi-page canvases. The update also extends Auto Layers editing across Designer, Spaces, and MCP.

Fable 5 demos moved into landing pages, brand tools, launch-video editing, and scriptwriting with Higgsfield MCP. The pattern matters because design direction is becoming promptable, but creators still need structured prompts and tool chaining to finish work.

Magnific turned its MCP connector live on all paid plans and added a Slack-to-image workflow with auto layers and resize exports. The rollout matters because image generation, editing, and asset reuse can stay inside chat-driven creative workflows, with credits consumed per MCP request.

David Holz said Midjourney has started sending invites for its first hardware launch event in San Francisco, and the company plans to livestream it. Replies suggest the product is cloud-backed rather than a local compute box, so watch for how Midjourney positions the hardware.

Creator demos showed OpenAI Codex building, running, and testing iOS apps through a Mac-only simulator plugin, and a companion thread listed Figma, illustration, video, and local model workflows. Separate posts also showed Codex sessions moving onto iPhone home screens and PM-built internal tools, so developers can test whether the plugin fits their stack.

A creator showed Ideogram 4.0 using structured JSON and drawn bounding boxes in ComfyUI to lock composition and text placement, then extended it through Claude Code and ComfyCloud MCP for exact-pixel variations. The posts say the model needs 12 turbo steps and the Kijai prompt-builder node is still being updated, so users should expect an evolving workflow.

A running thread collects custom AI tools that generate blooms, vector connectors, onboarding badges, atmospheric visuals, and logo variations for brand work. Teams can use these generators to keep brand systems consistent while speeding repetitive design production.

Markproduct shares a long-form spec that Claude 4.8 turns into a live animated hero section, while another creator pairs GPT-5.5 with OpenAI Sites for a password-manager landing page. These posts matter because layout, motion, fonts, and CSS behavior are being packaged into reusable website briefs.

Tran Mau Tri Tam publishes the full editable design from a viral Glass UI post in the Figma community, then follows with a Glass Button 2.0 example. Designers can copy the exact blur, shadow, and opacity setup instead of reverse-engineering it from screenshots.

Figma posted a plugin that turns Codex output into editable canvas designs, and OpenAI also showed an iOS testing loop inside Codex. Watch for Codex to move beyond chat into app-building workflows, with more creator-built tools likely to follow.

Adobe highlighted Object-WIPER and LightMover in its CVPR 2026 slate, while Firefly ambassadors showed AI Assistant retouch, mockup, and Boards workflows. Use this as a cue to expect Adobe to keep pushing edit-first control over existing photos and assets.

Figma opened the Config Makeathon, putting $100,000 in prizes and a June 18 submission deadline behind projects built with its current tools and agent beta access. Enter on Contra and use the public launch to submit before the deadline.

Reve published a technical explanation of Large Layout Models, arguing that image generation works better from structured layouts than prose-only prompts. Try layout-first editing for granular changes to hair, lipstick, and skin tone without rebuilding the whole image.

Higgsfield launched a Claude MCP skill that turns brand kits, generated videos, and business info into scroll-driven motion websites. The rollout also includes a Figma plugin for SVG assets and MCP tools that cut long videos into platform-ready clips.

Vitrine opened a TestFlight beta for turning photos into glass-style wallpapers with live Metal previews, presets, and high-resolution export. Use the plain-text recipes to reuse settings while keeping processing local on the Mac.

Ideogram 4.0 shipped as an open-weight image model with JSON prompting, bounding boxes, stronger text rendering, and native 2048px output. The release targets layout-heavy creative work, and teams can test early fal and Leonardo integrations in production flows.

Reve 2.0 launched with a new architecture, 4K output, and code-like control over image layout and editing. Early Arena results place it near the top of text-to-image rankings, so creators can compare it against other frontier image models.

Figma shipped plan mode, a messaging queue, web search and fetch, and pinned comments for Make. The update adds more guided checkpoints to prompt-driven prototype generation as Figma keeps pushing AI workflows beyond plain chat.

Figma opened preregistration for its first Config Makeathon and tied early signup to access for its new design-agent beta. Register early if you want temporary Figma Pro and 1,500 Weave credits during the event.

Google AI Studio now lets builders connect Gmail, Drive, Sheets, and other Google services without leaving the app builder, and testers can be added in-app. Use the new connections to keep workflows inside Studio, and filter API usage by key for tighter tracking.

Moda says a single prompt can generate editable designs and presentations on a real canvas, with redesign-from-reference support and export to PNG or PDF. The release targets users who need assets they can still tweak after generation instead of a flat image.

Fresh Hacker News comments and user posts report 400 errors tied to modified thinking blocks, short cache TTLs, and behavior some testers call a regression from 4.7. The issue matters because the same model is also powering one-prompt sites and games, so quota burn and client breakage are showing up alongside stronger creative output.

PufferPages went live on the App Store, turning a few spoken moments into comic-book pages and weekly issues. The release matters because it packages AI journaling as a finished visual-storytelling app instead of a manual prompt workflow.

Figma said Make can now connect to a local codebase, apply precise edits, and branch, commit, and ship from the beta desktop app. That moves Make closer to production work, so teams can try it on real code instead of isolated prototypes.