ComfyUI Extension
comfy_remote_run
Nodes to run nodes on remote ComfyUI instances.
LatentRat/comfy_remote_run
Nodes10
On cloudLocal install
CategoryRemote Run, Remote Run/__Internal__/
Stars12
Updated9 months ago
Nodes (10)
RemRun Add Remote Node Definitions
Use Your Second Machine's Nodes Like They're Installed Locally
Remote Run
RemRun Deserializer Output (Internal)
The Invisible Inbox on the Far Side
Remote Run/__Internal__/
RemRun Input Graph(s)
Run Half Your ComfyUI Graph on Another Machine
Remote Run
RemRun Input Graph(s) Output
The Same Node, But as a Destination
Remote Run
RemRun JSON
Fire a Whole Workflow at the Remote Machine
Remote Run
RemRun JSON Sync
The Same Trick, Without the Async
Remote Run
RemRun Serializer Output (Internal)
How Results Get Back to Your Machine
Remote Run/__Internal__/
RemRun Set Num Outputs
Give Every Remote Run Node More Sockets
Remote Run
RemRun Start From Here ->
Ship Only the Expensive Middle to the Other Machine
Remote Run
RemRun Toggle
Flip a Subgraph Between Local and Remote
Remote Run
Readme
Nodes to run nodes on remote ComfyUI instances.
Included Nodes:
- Remote Run Input Graph: Runs everything going to its inputs on the specified remote instance
- Remote Run Start From Here ->: Used together with above node, makes it only run its input nodes up to hitting a start node
- Remote Run JSON: Runs the JSON on the specified remote instance
- Remote Run Lazy Toggle: Simple toggle switch that runs parts of the graph either only locally or only remotely
Serialization:
- Safetensors: default, uses safetensors, fine for serializing latents and conditionings but may not support more complex types
- Torch Unsafe: normal torch pt, should have widest compatibility, probably best if you have full control or trust of the remote instance.
- Torch Safe: minimal safe implementation of torch pt, safe but only supports a small subset of types
Offloaded text encoder and VAE to remote instances
Same but with lora and toggles to avoid loading unnecessary models:
