Treatments
Outcome-shaped workflows — legacy treatments/skills as catalog graphs. Not 1:1 with all 213 skillTypes (spines + aliases only; see legacy-deliverable-parity.md).
13 workflows
Open TreatmentsUse cases
Intent-shaped collections. Each page links Try into the platform shell with a workflow slug.
Look stills
Look-first still workflows (packshot, lifestyle, portrait, fashion, food, architecture) — catalog graphs, not the Style Catalog (ims_*).
8 workflows
Open Look stillsTraining Studio
Train character LoRAs and manage Datasets → Train → Evaluate → Library. Primary CTA opens /platform/studio?recipe=character (not a dead workflow stub). Catalog slug training-studio is a reference still companion.
1 workflow
Open Training StudioWeekly drop
Curated weekly featured workflows — cadence resolved at request time from the weekly-drop schedule (ISO week). Distinct from personal Collections.
6 workflows
Open Weekly dropEdit · Video face / character / double-exposure
Closed 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).
3 workflows
Open Edit · Video face / character / double-exposureFashion
Concept, lookbook, on-model, and try-on workflows.
11 workflows
Open FashionProduct
Packshot, lifestyle, background swap, and 360 product stills.
16 workflows
Open ProductPortrait
Headshot, face detailer, and identity sheet workflows.
7 workflows
Open PortraitVideo
I2V, long-take, foley, and upscale/interpolation clips.
17 workflows
Open VideoAds
Directed static/commercial ads, creative packs (multi-AR, carousel, asset-group, vertical-feed), and leaf companions.
36 workflows
Open AdsArchitecture
Interior and exterior visualization workflows.
2 workflows
Open ArchitectureFood
Hero and process food photography workflows.
2 workflows
Open FoodFloyo · Best recipe ports
Highest-ICP Floyo commercial cookbook shapes recreated clean-room (ADR-023). Product insert, multi-angle, jewelry, try-on/UGC video, talking avatar, SeedVR2, beauty/influencer ads.
37 workflows
Open Floyo · Best recipe portsAdult / permissive
NSFW-entitled plain, ad-set, I2V/video, adult pacing, Grok gateway rail, and identity mint (never on commerce; dual-rail LTX + gateway).
16 workflows
Open Adult / permissiveMode · Video
Legacy composer om:v — standard video spines (general + I2V + UGC + cinema seed).
17 workflows
Open Mode · VideoMode · Images (Ad)
Legacy composer om:i + ip:a — static ad sets with packaging room.
10 workflows
Open Mode · Images (Ad)Mode · Images (Plain)
Legacy composer om:i + ip:p — directed plain stills (plan+QC+finalize) plus look leaves.
8 workflows
Open Mode · Images (Plain)Mode · Audio
Legacy composer om:a — Music / Voice / Spot / Podcast artifact paths.
10 workflows
Open Mode · AudioMode · Catalog / DCO
Legacy Catalog Video + Catalog Stills (DCO) — per-SKU trafficking.
5 workflows
Open Mode · Catalog / DCOMode · Cinema
Legacy Quality Mode cinema (qm:c) + cinematic long-take companions.
4 workflows
Open Mode · CinemaMode · Animate still
Legacy animate-still / image_to_video — one still → one clip.
4 workflows
Open Mode · Animate stillMode · Refine
Legacy refine treatments (recast / outfit / face). Bind reference images in the editor.
8 workflows
Open Mode · RefineFormat packs
Legacy fpk: overlays — social_mute_first, product_plate, tv_broadcast (adult_structure under Adult formats).
5 workflows
Open Format packsAdult formats
Legacy system-only adult_* pacing formats + adult_structure — re-expressed as hybrid NSFW graphs (never commerce).
10 workflows
Open Adult formatsParity · Core deliverables
Umbrella set covering legacy non-permissive product modes (video, images, audio, catalog, cinema, animate, refine, format packs).
37 workflows
Open Parity · Core deliverablesSFW adapters (LTX LoRA presets)
Non-permissive LTX adapter demo graphs — phys-ltx floor, cinematic/product/portrait/locked-camera plus CRT/FPV/cinemagraph/transition/audio-reactive/3dreal community presets. See docs/platform/sfw-adapters.md. IC-LoRAs remain lab-path leaves in adapters-ltx-looks.
12 workflows
Open SFW adapters (LTX LoRA presets)LTX-2.5 looks + IC / Comfy ports
LTX-2.5 community productization leaves: SFW CRT/FPV/cinemagraph/transition/audio-reactive/3dreal presets, IC capability demos, eros25 eval, and T-08 Comfy bridge ports. See docs/research/ltx-lora-workflow-audit-2026-08-12.md.
25 workflows
Open LTX-2.5 looks + IC / Comfy portsParity · Permissive deliverables
Umbrella set covering legacy NSFW product surfaces — plain/ad-set stills, I2V/video, adult pacing, Grok gateway rail, identity mint (dual-rail LTX + gateway).
18 workflows
Open Parity · Permissive deliverablesGear · Default
Legacy system:default — environment defaults. Companion RealVisXL + Gemini + Kling I2V workflows (no forced provider pins).
5 workflows
Open Gear · DefaultGear · High quality
Legacy system:high-quality — 2K images, pro video tiers, writingModel=fable companions.
5 workflows
Open Gear · High qualityGear · Fast & efficient
Legacy system:fast — single-variant / fast video tiers (veoFast, Kling turbo draft).
5 workflows
Open Gear · Fast & efficientGear · In-house
Legacy system:in-house (WAN+Krea2). Platform maps to hybrid LTX /best_seed + LTX distilled video + RealVisXL — not CheckpointLoader krea2 (D-02).
5 workflows
Open Gear · In-houseModel · Gemini Image
Legacy imageProvider=gemini-image (Nano Banana / gemini-3-pro-image).
5 workflows
Open Model · Gemini ImageModel · Grok Imagine
Official api.x.ai Grok Imagine image + video. Adult Imagine uses WavemakerGrokGateway* / permissive-gateway-* (consumer gateway), not these leaves.
7 workflows
Open Model · Grok ImagineModel · OpenAI Image
Legacy imageProvider=openai — gpt-image-1 partner node.
2 workflows
Open Model · OpenAI ImageModel · Ideogram
Ideogram 3.0 partner image generation.
1 workflow
Open Model · IdeogramModel · Qwen-Image
Qwen-Image base T2I and GGUF quant mirrors (Apache-2.0). Volume residency + GPU verify are ops follow-ups (WAV-877 / WAV-879).
4 workflows
Open Model · Qwen-ImageModel · Kling
Legacy videoProvider=kling-direct — T2V + I2V (fresh-start default video).
5 workflows
Open Model · KlingModel · Veo
Legacy videoProvider=veo — Veo 3.1 standard + fast.
3 workflows
Open Model · VeoModel · Seedance
Legacy videoProvider=seedance-direct.
7 workflows
Open Model · SeedanceModel · Partners
Partner video model leaf workflows (Seedance, Veo, Runway, Kling, and more). Trying one binds that leaf graph — it does not change directed SFW Quality Partner presets (Kling/Grok Materialize stacks).
44 workflows
Open Model · PartnersModel · ElevenLabs
Legacy ElevenLabs TTS + music partner nodes (fresh-start eleven_v3 / music_v1).
8 workflows
Open Model · ElevenLabsModel · LTX hybrid
Self-hosted / experimental LTX path — hybrid /best_seed + catalog LTX video (covers legacy ltx + in-house krea2 image pin).
7 workflows
Open Model · LTX hybridModel · Self-hosted Modal
WAN / Hunyuan / Foley / LTX best_seed with LoRA pin strings exposable in-graph.
28 workflows
Open Model · Self-hosted ModalModel · Seedream
BytePlus Seedream image models.
4 workflows
Open Model · SeedreamWriting · Claude Sonnet
Legacy writingModel=sonnet (claude-sonnet-4-6 on strategize/write_script). Media companions for default gear — Claude is agent-side, not a Comfy node.
4 workflows
Open Writing · Claude SonnetWriting · Claude Opus
Legacy writingModel=opus (claude-opus-4-8). High-craft media companions.
4 workflows
Open Writing · Claude OpusWriting · Claude Fable
Legacy writingModel=fable (pinned by High quality gear). Companion HQ media set.
4 workflows
Open Writing · Claude FableLLM stack · Stable
Legacy admin ModelConfig presets stable-v0.2/v0.3/v0.4 — Claude Sonnet planning + Gemini Flash reviews + Grok Imagine video + ElevenLabs multilingual.
5 workflows
Open LLM stack · StableLLM stack · Fresh Start
Legacy admin ModelConfig fresh-start — Gemini image + Kling video + ElevenLabs v3 + Gemini/Claude orchestrator stack.
7 workflows
Open LLM stack · Fresh StartModel · MiniMax Hailuo
First-party MiniMax partner nodes — Hailuo MiniMax-H3 T2V + speech-2.5 voiceover.
4 workflows
Open Model · MiniMax HailuoModel · Vidu
First-party Vidu partner node — viduq3-pro 1080p T2V.
3 workflows
Open Model · ViduModel · PixVerse
First-party PixVerse partner node — v6 720p T2V.
2 workflows
Open Model · PixVerseModel · Luma Dream Machine
First-party Luma partner nodes — Ray 3.2 T2V + Modify video restyle.
3 workflows
Open Model · Luma Dream MachineModel · Runway
First-party Runway partner nodes — Gen-4.5 T2V, Aleph video edit, Act-Two performance transfer.
3 workflows
Open Model · RunwayModel · WAN API
First-party Alibaba WAN API partner node — wan2.7-t2v 720p T2V.
2 workflows
Open Model · WAN APICapability · Lip-sync
Lip-sync lanes — Sync partner (sync-3) and open LatentSync 1.6.
2 workflows
Open Capability · Lip-syncModel · FLUX (Apache)
FLUX.1-schnell and FLUX.2-klein-4B commercial-safe open image lanes (runtime-v4).
2 workflows
Open Model · FLUX (Apache)Model · HiDream
HiDream-O1 MIT text-to-image (runtime-v4).
1 workflow
Open Model · HiDreamModel · SkyReels V3
SkyReels V3 R2V / extend / avatar scaffolds on WanVideoWrapper (runtime-v4). Skywork Community License pass-through.
3 workflows
Open Model · SkyReels V3Model · ACE-Step
ACE-Step 1.5 open music (native ComfyUI ACE nodes, runtime-v4).
1 workflow
Open Model · ACE-StepCapability · Matting
Open BiRefNet background matting lane.
1 workflow
Open Capability · MattingMarket · Competitor parity ports
Clean-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.
31 workflows
Open Market · Competitor parity ports