feat: make GPT-Image-2 nodes async for parallel execution#11
Open
gioOrchid wants to merge 1 commit into
Open
Conversation
ComfyUI's executor (execution.py) detects async node functions via inspect.iscoroutinefunction() and wraps them in asyncio.create_task() instead of awaiting sequentially. This allows multiple API nodes at the same graph depth to fire their HTTP calls simultaneously. Changes: - Add `import asyncio` to nodes.py - KIE_GPTImage2_TextToImage.generate: def → async def - KIE_GPTImage2_ImageToImage.generate: def → async def - Both now use asyncio.to_thread() to run the blocking HTTP job in a thread pool, allowing true concurrent I/O (GIL released for network) Result: N independent GPT-Image-2 nodes in a workflow run in parallel instead of sequentially. For 5 ad generation nodes this yields ~5x wall-clock speedup. KIE API supports 100+ concurrent tasks and 20 requests/10s, so the server side is not a bottleneck. No behaviour change for single-node workflows.
Author
|
@gateway :) nice project! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
ComfyUI's executor (execution.py) detects async node functions via inspect.iscoroutinefunction() and wraps them in asyncio.create_task() instead of awaiting sequentially. This allows multiple API nodes at the same graph depth to fire their HTTP calls simultaneously.
Changes:
import asyncioto nodes.pyResult: N independent GPT-Image-2 nodes in a workflow run in parallel instead of sequentially. For 5 ad generation nodes this yields ~5x wall-clock speedup. KIE API supports 100+ concurrent tasks and 20 requests/10s, so the server side is not a bottleneck.
No behaviour change for single-node workflows.