1. Describe
Tell chat the outcome. We recommend a published workflow.
Chat operates workflows — guided inputs, costs, and outputs — without starting in a node graph. Open the graph when you want power.
Product packshot, soft daylight, white seamless — keep the label sharp.
Using product-packshot. Confirm aspect + reference, then I’ll preflight credits.
Same session — open when you need power.
Aggregators resell access to other people’s models. Wavemaker directs productions — the models are cast; the pipeline, the QC, and the workflows you own are the product.
Same models you’d find anywhere — Kling, Seedance, Veo, Seedream and more — but bound into graphs with quality gates, honest metering, and ownership. Named comparisons stay receipt-backed under Compare.
Prompt → guided inputs → outputs. Graph optional.
Tell chat the outcome. We recommend a published workflow.
Fill promoted fields and review credit preflight.
Iterate in chat. Switch to graph only when you need it.
Curated collections from the bundled catalog — Try deep-links into the app shell.
Outcome-shaped recipes — video, stills, audio, and refine paths.
Explore TreatmentsLook-first stills — packshot, lifestyle, portrait, fashion, food, and architecture.
Explore Look stillsTrain a character, product, style, or motion adapter in Studio.
Explore Training StudioCurated weekly featured workflows — cadence resolved at request time from the weekly-drop schedule (ISO week). Distinct from personal Collections.
Explore Weekly dropClosed residue (runtime-v2): video face-swap (reactor+VHS), character-swap (IPAdapter+inpaint), double-exposure. LivePortrait reenact is a separate showcase under video (not this residue list).
Explore Edit · Video face / character / double-exposureConcept, lookbook, on-model, and try-on workflows.
Explore FashionPackshot, lifestyle, background swap, and 360 product stills.
Explore ProductHeadshot, face detailer, and identity sheet workflows.
Explore PortraitImage-to-video, long-take, foley, upscale, and interpolation.
Explore VideoDirected static/commercial ads, creative packs (multi-AR, carousel, asset-group, vertical-feed), and leaf companions.
Explore AdsInterior and exterior visualization workflows.
Explore ArchitectureHero and process food photography workflows.
Explore FoodHigh-demand commercial shapes: product insert, multi-angle, jewelry, try-on, UGC video, talking avatar, beauty and influencer ads.
Explore Best recipe portsStandard video — directed multi-scene, image-to-video, UGC, and cinema.
Explore Mode · VideoLegacy composer om:i + ip:a — static ad sets with packaging room.
Explore Mode · Images (Ad)Directed stills with a plan and quality check, plus look companions.
Explore Mode · Images (Plain)Legacy composer om:a — Music / Voice / Spot / Podcast artifact paths.
Explore Mode · AudioLegacy Catalog Video + Catalog Stills (DCO) — per-SKU trafficking.
Explore Mode · Catalog / DCOLegacy Quality Mode cinema (qm:c) + cinematic long-take companions.
Explore Mode · CinemaLegacy animate-still / image_to_video — one still → one clip.
Explore Mode · Animate stillLegacy refine treatments (recast / outfit / face). Bind reference images in the editor.
Explore Mode · RefineLegacy fpk: overlays — social_mute_first, product_plate, tv_broadcast (adult_structure under Adult formats).
Explore Format packsAdult pacing formats for entitled accounts — never sold on the marketplace.
Explore Adult formatsCore video, images, audio, catalog, cinema, animate, refine, and format packs.
Explore Core deliverablesLTX motion looks — cinematic, product, portrait, locked-camera, plus CRT, FPV, cinemagraph, transition, and related presets.
Explore LTX look adaptersLTX community looks: CRT, FPV, cinemagraph, transition, and related presets, plus official IC tools and Discover-only novelty looks.
Explore LTX-2.5 looks + IC / Comfy portsAdult stills, video, pacing, and character sheets — entitled accounts only, never sold on the marketplace.
Explore Adult deliverablesDefault image and video companions — Gemini stills and Kling motion, no forced pins.
Explore Gear · DefaultLegacy system:high-quality — 2K images, pro video tiers, writingModel=fable companions.
Explore Gear · High qualityFaster drafts — single-variant and turbo video tiers.
Explore Gear · FastSelf-hosted image and video path — LTX stills and motion on our GPUs.
Explore Gear · In-houseGemini image generation — prompt-faithful stills with strong text.
Explore Model · Gemini ImageGrok Imagine image and video. Adult Imagine uses the adult gateway recipes.
Explore Model · Grok ImagineLegacy imageProvider=openai — gpt-image-1 partner node.
Explore Model · OpenAI ImageIdeogram 3.0 partner image generation.
Explore Model · IdeogramQwen-Image base text-to-image and GGUF quant mirrors (Apache-2.0). Volume residency + GPU verify are ops follow-ups (WAV-877 / WAV-879).
Explore Model · Qwen-ImageKling text-to-video and image-to-video.
Explore Model · KlingLegacy videoProvider=veo — Veo 3.1 standard + fast.
Explore Model · VeoLegacy videoProvider=seedance-direct.
Explore Model · SeedancePartner video models — Seedance, Veo, Runway, Kling, and more. Trying one binds that model; it does not change directed Quality Partner presets.
Explore Model · PartnersLegacy ElevenLabs TTS + music partner nodes (fresh-start eleven_v3 / music_v1).
Explore Model · ElevenLabsSelf-hosted LTX stills and video.
Explore Model · LTX hybridWAN, Hunyuan, Foley, LTX, and MiniMax H3 on our GPUs.
Explore Model · Self-hostedBytePlus Seedream image models.
Explore Model · SeedreamClaude Sonnet planning companions for default gear.
Explore Writing · Claude SonnetLegacy writingModel=opus (claude-opus-4-8). High-craft media companions.
Explore Writing · Claude OpusLegacy writingModel=fable (pinned by High quality gear). Companion HQ media set.
Explore Writing · Claude FableClaude planning, Gemini reviews, Grok Imagine video, and ElevenLabs voice.
Explore LLM stack · StableGemini image, Kling video, ElevenLabs voice, and a Gemini/Claude planner.
Explore LLM stack · Fresh StartMiniMax Hailuo API twins, native H3 self-host, and Speech voiceover.
Explore Model · MiniMaxVidu Q3 Pro text-to-video at 1080p.
Explore Model · ViduPixVerse v6 text-to-video at 720p.
Explore Model · PixVerseLuma Ray text-to-video and Modify restyle.
Explore Model · Luma Dream MachineRunway Gen-4.5 text-to-video, Aleph video edit, and Act-Two performance transfer.
Explore Model · RunwayAlibaba WAN 2.7 text-to-video at 720p.
Explore Model · WAN APILip-sync lanes — Sync partner (sync-3) and open LatentSync 1.6.
Explore Capability · Lip-syncFLUX.1-schnell and FLUX.2-klein-4B commercial-safe open image lanes (runtime-v4).
Explore Model · FLUX (Apache)HiDream-O1 MIT text-to-image (runtime-v4).
Explore Model · HiDreamSkyReels V3 reference-to-video, extend, and avatar scaffolds.
Explore Model · SkyReels V3ACE-Step 1.5 open music (native ComfyUI ACE nodes, runtime-v4).
Explore Model · ACE-StepOpen BiRefNet background matting lane.
Explore Capability · MattingClean-room recreations of the strongest non-Comfy competitor deliverables (2026-08 replication sweep): UGC actor ads, dubbing, viral effects, camera-move packs, article/doc-to-video, upscalers, icon sets, audiobooks, jingles, SFX packs.
Explore Market · Competitor parity portsLicensed looks ported from community harvests — our graphs, not copied workflows.
Explore Community shapesNative Comfy graphs on Modal GPUs — curated packs + partner nodes. Compose, remix, Copy API curl from Simple or Graph, and publish when you’re ready. Public share still requires a verified run. The split above is the thesis: chat operates; graph is the same session.
Product-shape pages vs Floyo-class hosts, managed Comfy clouds, and Hub import — receipt claims only; no “beats legacy” until bakeoffs unlock it. Browse comparisons.
One-click Copy API for POST /runs. Dual-meter preflight (GPU + partner APIs).
Agents use POST /mcp — ~50 tools (search, apply, edit graph, run,
files, wallet, partner nodes). OpenAPI: 57 operations.
Docs: /developers#platform · node library · api-mcp guide · billing rates.
Verified Private hosting and commercial-use honesty live in the Trust Center. Claims never exceed the public registry.
Before Confirm you see GPU class and Partner API meters for the bound leaf (e.g. Kling video-seconds, ElevenLabs characters). Edit the graph for free; generation reserves credits and refunds the unused remainder. Purchased credits never expire.
See pricing and the billing rates guide.
No. Aggregators resell prompt boxes to partner models. Wavemaker directs productions: one prompt becomes a multi-scene run with script, scenes, voiceover, music, QC gates on every clip, and a final assembled cut. The models are cast — the pipeline, the QC, and the workflows you own are the product.
Purchased credit packs never expire. Monthly plan credits roll forward by your plan's rollover percentage (up to 40%) at each renewal.
Yes. Partner marketing pages under /platform/ai-models deep-link Try into catalog leaves. Directed ads may also meter partners under Quality presets.
Dual-meter preflight shows GPU class and Partner API units before Confirm. Partner seconds/characters are priced in billing-rates; unused reserve refunds automatically.
Image face-swap only (refine-face-swap) with likeness consent. Video face-swap is not offered.