Extensions/ComfyUI-CloudAPI-worker
ComfyUI Extension

ComfyUI-CloudAPI-worker

A set of PoC ComfyUI cloud API nodes for connecting the cloud API with a local ComfyUI instance

By Dobidop·Created 5 months ago·Updated 5 months ago· 0
Dobidop/ComfyUI-CloudAPI-worker
Nodes48
On cloudLocal install
Categorycloud
Stars0
Updated5 months ago

Nodes (48)

Cloud CFG Guider

Guidance strength, computed a thousand miles away

cloud
Cloud Checkpoint Loader

The loader that loads nothing — and that's the whole point

cloud
Cloud CLIP Loader

The single text encoder, on someone else's GPU

cloud
Cloud CLIP Text Encode

Your prompt, encoded at a datacenter

cloud
Cloud Convert Workflow

Paste a whole workflow in, get a cloud version out

cloud
Cloud Create Video

Mux your frames into a video on the cloud's dime

cloud
Cloud Dual CLIP Loader

Two text encoders, zero local VRAM

cloud
Cloud Empty Image

A blank canvas that only exists in the cloud

cloud
Cloud Empty Latent

The cloud's blank latent, where text-to-image starts

cloud
Cloud Empty Latent Video

A blank video latent, sized for Wan or LTX — you choose

cloud
Cloud Fetch Audio

The node that actually finishes the job and hands you audio

cloud
Cloud Fetch Images

The terminal that turns cloud handles back into pixels

cloud
Cloud Fetch Video

Bring the video home as a VIDEO object, a file, or both

cloud
Cloud Get Image Size

Know a cloud image's size without ever downloading it

cloud
Cloud Image Scale By

Rescale a cloud image by a factor without pulling it home

cloud
Cloud KSampler (Quick)

One node. Checkpoint, prompts, sampler, result. Done.

cloud
Cloud KSampler Advanced

The sampler for two-stage chains, with the advanced dials

cloud
Cloud KSampler

The cloud KSampler that's shaped exactly like the one you know

cloud
Cloud KSampler Select

63 samplers, none of them running on your machine

cloud
Cloud Latent Upscale Model Loader

Load a latent upscaler that lives in the cloud

cloud
Cloud List Models

The refresh button for the cloud's model dropdowns

cloud
Cloud Lora Loader

Slap a LoRA on a cloud model without downloading anything

cloud
Cloud Lora Loader (Model Only)

The LoRA loader for models that skipped the text encoder

cloud
Cloud LTXAV Text Encoder Loader

LTX-2's text encoder, rented instead of downloaded

cloud
Cloud LTXV Audio VAE Decode

Turn LTX-2's audio latents into something you can actually hear

cloud
Cloud LTXV Audio VAE Loader

The audio half of LTX-2's joint latent, loaded cloud-side

cloud
Cloud LTXV Concat AV Latent

Splice video and audio latents into one LTX-2 blob

cloud
Cloud LTXV Conditioning

Tell LTX-2 how fast your clip should play

cloud
Cloud LTXV Crop Guides

Trim the guide frames out of your LTX latent

cloud
Cloud LTXV Empty Latent Audio

A blank canvas for LTX-2 audio

cloud
Cloud LTXV Img To Video Inplace

Start an LTX-2 video from a still image, in place

cloud
Cloud LTXV Latent Upsampler

Upscale the latent, not the pixels

cloud
Cloud LTXV Preprocess

Give LTX-2 an image it can actually start from

cloud
Cloud LTXV Scheduler

The shift knobs that LTX wants, cloud-side

cloud
Cloud LTXV Separate AV Latent

Split LTX-2's joint AV latent back into its halves

cloud
Cloud Manual Sigmas

Type your noise schedule by hand

cloud
Cloud Materialize Latent

Drag a cloud latent back onto your own GPU

cloud
Cloud Model Sampling SD3

The shift dial for flow-matching models

cloud
Cloud Random Noise

A seed for the cloud's noise generator

cloud
Cloud Resize Images By Longer Edge

One number to get your input images cloud-ready

cloud
Cloud Sampler Custom Advanced

Assemble your sampling from noise, guider, sampler, and sigmas

cloud
Cloud Save Video

When you just want the MP4 saved to disk, not a VIDEO tensor to mux

cloud
Cloud UNET Loader

Load a bare diffusion model on the cloud — no checkpoint bundle required

cloud
Cloud Upload Image

The one-way door that gets local images into a cloud workflow

cloud
Cloud VAE Decode

Where the cloud chain finishes decoding — and your GPU genuinely does nothing

cloud
Cloud VAE Encode

Turn a local image into cloud latents — img2img minus the local VRAM

cloud
Cloud VAE Loader

A whole node for one dropdown — but when your model has no bundled VAE, it's the only way

cloud
Cloud Wan Image To Video

Wan 2.2 image-to-video on the cloud — no 24GB card required

cloud
Readme

ComfyUI-CloudAPI-worker

Proof-of-concept ComfyUI custom node pack that runs workflows on the ComfyUI Cloud from inside a local ComfyUI graph. You wire up familiar-looking nodes (Cloud Checkpoint Loader, Cloud KSampler, Cloud VAE Decode, etc.) and they assemble a workflow JSON, ship it to the cloud, poll for completion, and return images as a normal IMAGE tensor.

How it works

The cloud nodes don't run anything locally. Each one returns a lightweight handle (CLOUD_MODEL, CLOUD_CLIP, CLOUD_VAE, CLOUD_CONDITIONING, CLOUD_LATENT) that carries the partial workflow JSON accumulated so far plus a reference to a node-output slot. Only the terminal node — Cloud VAE Decode — actually submits to the cloud, polls, and downloads the results. Whatever shape you wire up locally translates 1:1 into the JSON sent to the cloud, so LoRAs, separate CLIP loaders, dual-text-encoder setups, two-stage samplers, etc. all just work.

Models, LoRAs, VAEs, and text encoders all live cloud-side and never traverse the wire. Local images (e.g. for img2img or Wan I2V) are uploaded once via /api/upload/image and referenced as a LoadImage node in the assembled workflow.

Installation

  1. Clone or copy this folder into ComfyUI/custom_nodes/.
  2. Copy config.json.example to config.json and paste your API key from https://platform.comfy.org/profile/api-keys.
  3. Restart ComfyUI. Model dropdowns populate automatically in the background — checkpoints, loras, vae, diffusion_models, text_encoders, clip_vision are prefetched on startup.

Nodes

All nodes appear under the cloud category.

Loaders: Cloud Checkpoint Loader, Cloud UNET Loader, Cloud VAE Loader, Cloud CLIP Loader, Cloud Dual CLIP Loader, Cloud Lora Loader, Cloud Lora Loader (Model Only)

Conditioning: Cloud CLIP Text Encode, Cloud Model Sampling SD3, Cloud Wan Image To Video

Latents: Cloud Empty Latent, Cloud Empty Latent Video, Cloud VAE Encode

Sampling: Cloud KSampler, Cloud KSampler Advanced, Cloud KSampler (Quick) (monolithic txt2img/img2img all-in-one)

Cloud-side decoding (non-terminal): Cloud VAE Decode (returns CLOUD_IMAGE), Cloud LTXV Audio VAE Decode (returns CLOUD_AUDIO), Cloud Create Video (returns CLOUD_VIDEO)

Terminals (cloud → local bridges):

  • Cloud Fetch Images (CLOUD_IMAGE → IMAGE batch)
  • Cloud Fetch Audio (CLOUD_AUDIO → AUDIO)
  • Cloud Fetch Video (CLOUD_VIDEO → VIDEO + local file path)
  • Cloud Save Video (CLOUD_VIDEO → STRING; saves MP4 to local output dir without wrapping as VIDEO)

Image utilities: Cloud Empty Image, Cloud Get Image Size, Cloud Image Scale By, Cloud Resize Images By Longer Edge

Sampling primitives: Cloud CFG Guider, Cloud KSampler Select, Cloud Sampler Custom Advanced, Cloud Random Noise, Cloud Manual Sigmas

LTX 2.0 video: Cloud LTXV Conditioning, Cloud LTXV Scheduler, Cloud LTXV Preprocess, Cloud LTXV Img To Video Inplace, Cloud LTXV Crop Guides, Cloud LTXV Latent Upsampler

LTX 2.0 audio: Cloud LTXAV Text Encoder Loader, Cloud LTXV Audio VAE Loader, Cloud LTXV Audio VAE Decode, Cloud LTXV Concat AV Latent, Cloud LTXV Separate AV Latent, Cloud LTXV Empty Latent Audio

Misc loaders: Cloud Latent Upscale Model Loader

Bridges:

  • Cloud Materialize Latent (runs the cloud chain so far, downloads the latent as a local LATENT — useful for inserting a local-only operation like a 3rd-party latent upscaler. One-way: comfy-cloud has no LoadLatent support, so a local LATENT can't be pushed back into a cloud chain.)
  • Cloud Upload Image (uploads a local IMAGE to the cloud and returns a CLOUD_IMAGE handle — the bridge from local LoadImage into a graph-style cloud chain.)

Utility: Cloud List Models (refreshes a folder's dropdown cache on demand), Cloud Convert Workflow (translates a local workflow JSON into its cloud equivalent and writes it to ComfyUI's output dir; accepts both editor format and API format — use API format for any workflow with subgraphs, e.g. LTX 2.0 templates)

Notes

  • Polling status updates print to the console (queued_waiting → allocated → preparing → executing → success).
  • Bump the timeout on Cloud VAE Decode for long jobs. Wan 2.2 14B I2V with the 4-step LoRA finishes in ~70-100s; without the LoRA it can take 8-10 minutes.
  • For video workflows, the IMAGE batch returned by Cloud VAE Decode is N frames — wire it into VHS_VideoCombine to mux locally.
  • The dropdown cache lives in config.json and refreshes every 24h on startup. Run a Cloud List Models node to force-refresh a specific folder, then restart ComfyUI.

Status

Proof of concept. Architecture is solid for image and video diffusion workflows; missing pieces include ControlNet, CLIP Vision conditioning, dedicated cloud-side video encoding (SaveVideo/SaveAnimatedWebP), and per-model I2V conditioners other than Wan. Add as needed.

License

MIT — see LICENSE.