Extensions/Replicate Select
ComfyUI Extension

Replicate Select

Kuratierte Replicate-Modelle als ComfyUI-Nodes (Bild, Video, Upscale, TTS, Lipsync) + Custom-Node für beliebige Modell-IDs.

By Pharma-Lobby·Created 2 months ago·Updated 2 months ago· 0
Pharma-Lobby/ComfyUI-Replicate-Select
Nodes22
On cloudLocal install
CategoryReplicate Select/video, Replicate Select/image
Stars0
Updated2 months ago

Nodes (22)

Seedance 2.0 Fast (Replicate)

Seedance 2.0 Fast — ByteDance's video model, audio included, bill included

Replicate Select/video
Seedream 4.5 (Replicate)

Seedream 4.5 in ComfyUI — the ByteDance flagship you can't download

Replicate Select/image
Real-ESRGAN Upscale (Replicate)

Paying to run Real-ESRGAN is usually silly — unless you've got no GPU

Replicate Select/upscale
SUPIR Upscale (Replicate)

SUPIR without the 16GB VRAM bill — but the faces still get rewritten

Replicate Select/upscale
Replicate Custom (beliebige Modell-ID)

Replicate Custom — the escape hatch for the other 400,000 models

Replicate Select
ElevenLabs v3 (Replicate)

ElevenLabs v3 — the TTS everyone else is measured against, in your graph

Replicate Select/tts
Nano Banana Pro (Replicate)

Nano Banana Pro in ComfyUI — the Gemini image model, filter included

Replicate Select/image
Veo 3.1 (Replicate)

Veo 3.1 — the closed video bar, and the native-audio thing nothing open matches

Replicate Select/video
HeyGen Lipsync Precision (Replicate)

HeyGen Lipsync Precision — swap a voice in existing footage, cleanly

Replicate Select/lipsync
Inworld TTS 2 (Replicate)

Inworld TTS 2 — write '[whisper excitedly]' and it just obeys

Replicate Select/tts
Kling v3 Video (Replicate)

Kling v3 video in your graph — including the multi-shot JSON mode

Replicate Select/video
LTX-2 Distilled (Replicate)

LTX-2 Distilled — the speed king of open video, rented for no GPU

Replicate Select/video
MiniMax Speech 2.8 HD (Replicate)

MiniMax Speech 2.8 HD — the TTS with an emotion dial and pause markers

Replicate Select/tts
Pruna Video Avatar (Replicate)

Pruna Video Avatar — a photo, a script, and a talking head walks out

Replicate Select/lipsync
Z-Image Turbo (Replicate)

Z-Image Turbo — the open 6B model the community runs, rented per call

Replicate Select/image
Z-Image Turbo I2I (Replicate)

Z-Image Turbo I2I — img2img with LoRA support, all in the cloud

Replicate Select/image
Qwen Image Edit Plus (Replicate)

Qwen Image Edit Plus — instruction-based image editing, cloud-style

Replicate Select/image
Sync Lipsync 2 Pro (Replicate)

Sync Lipsync 2 Pro — video-to-video lipsync with an actual mismatch mode

Replicate Select/lipsync
Prompt (Replicate Select)

Prompt (Replicate Select) — the world's most honest node

Replicate Select
VEED Fabric 1.0 (Replicate)

VEED Fabric 1.0 — the three-input talking head

Replicate Select/lipsync
Wan 2.2 I2V Fast (Replicate)

Turn a still image into a Wan 2.2 video without a GPU or a 27GB download

Replicate Select/video
Wan 2.2 T2V Fast (Replicate)

Type a prompt, get a Wan 2.2 video — no weights, no VRAM, just a token

Replicate Select/video
Readme

ComfyUI-Replicate-Select

Kuratierte Replicate-Modelle als ComfyUI-Nodes — schlank statt Katalog-Flut. Architektur nach dem Vorbild von ComfyUI-Runware: nodes.json (Katalog) + Generator + ReplicateCustom als Escape-Hatch.

Modelle (20)

| Kategorie | Nodes | |---|---| | image | Seedream 4.5 · Nano Banana Pro · Qwen Image Edit Plus · Z-Image Turbo · Z-Image Turbo I2I | | video | Kling v3 Video · Veo 3.1 · Seedance 2.0 Fast · LTX-2 Distilled · Wan 2.2 T2V Fast · Wan 2.2 I2V Fast | | upscale | SUPIR · Real-ESRGAN | | tts | MiniMax Speech 2.8 HD · Inworld TTS 2 · ElevenLabs v3 | | lipsync | VEED Fabric 1.0 · Pruna Video Avatar · Sync Lipsync 2 Pro · HeyGen Lipsync Precision |

Dazu: Replicate Custom — beliebige Modell-ID + JSON-Input.

Auth

REPLICATE_API_TOKEN als Umgebungsvariable (auf Modal: Secret mcp-keys). Kein Key im Node, keine Key-Dateien.

Outputs

  • image → IMAGE-Tensor (direkt weiterverdrahtbar)
  • audio → AUDIO (ComfyUI-nativ, z.B. → SaveAudio oder → Lipsync-Nodes via Upload)
  • video → MP4 im Output-Ordner, Node gibt den Pfad als STRING zurück

Katalog aktualisieren / Modelle hinzufügen

# Modell in scripts/build_catalog.py → META eintragen, dann:
python scripts/build_catalog.py

Zieht die Input-Schemas von den öffentlichen Replicate-Schema-Seiten — kein Token nötig.

Hinweise

  • Bild-Inputs werden als PNG hochgeladen (klein → data-URI, groß → Replicate Files-API)
  • Audio-Inputs (Lipsync) akzeptieren ComfyUI-AUDIO und werden als WAV hochgeladen
  • Video-Inputs erwarten eine URL (STRING) — Replicate braucht abrufbare Dateien