Commit Graph
9 Commits
Author SHA1 Message Date
Robert Wojciechowski 59ccbabe79 Merge main into feat/runpod-serverless-workers
Resolve nodes/collector.py: keep the serverless manager accessor and
main's compressed result transfer. Update test stubs for the merged
code: fetch_worker_has_node (#99) in the serverless integration test,
and the real aiohttp.web in the transfer integration test.
2026-10-13 22:16:16 +00:00
6edd3fda38 feat(collector): optional compressed worker → master result transfer (#97)
* feat(collector): compressed worker -> master result transfer

Workers sent every frame as an uncompressed PNG (compress_level=0),
base64-encoded inside a JSON request, one request per frame. For cloud
workers this makes result download (egress) the dominant transfer cost:
a 121-frame 720p batch is ~446 MB per worker.

Add `transfer_format` / `transfer_quality` optional widgets to
Distributed Collector:

- legacy_png (default): unchanged behaviour
- png, ffv1: lossless, bit-identical master tensors to legacy_png
- jpeg, webp: lossy stills
- h264, h265, av1: lossy video of the whole batch

Compressed results are posted as multipart/form-data chunks (binary, no
base64, ~32 MB soft cap per request, configurable with
COMFYUI_DISTRIBUTED_TRANSFER_CHUNK_BYTES). The master decodes each chunk
off the event loop and enqueues one item per frame, so collection,
ordering and audio handling are unchanged. Encoding also runs in an
executor on the worker.

Compatibility:
- /distributed/job_complete still accepts the legacy JSON envelope.
- A worker talking to an older master gets a 400 on the first chunk and
  resends everything as legacy_png.
- Missing video encoders fall back to h264 (lossy) or png (ffv1).

Measured on 121 frames at 1280x720: png 163 MB (2.7x), ffv1 128 MB
(3.5x), h264 q90 2.4 MB (186x, 40.2 dB), av1 q90 0.4 MB.

Also clips IMAGE values before 8-bit quantization on the new path so
out-of-range values no longer wrap around.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0166t8T3CVaxZkJbP2RtSpo6

* fix(collector): wire transfer options through V3 node; bound finalized payload size

Addresses review on #97.

V3 integration
- Add optional `transfer_format` / `transfer_quality` inputs to the
  registered nodes/v3.py DistributedCollector schema (legacy defaults) and
  accept/forward them in execute() to the runtime helper.
- tests/test_v3_collector_transfer.py checks the registered node's public
  schema and argument forwarding without a ComfyUI checkout; the opt-in
  real-runtime acceptance (tests/helpers/v3_runtime_check.py) now allows
  exactly these appended optional inputs, verifies their contract, and
  checks forwarding through the real executor.

Payload size bound
- encode_chunks() enforces limits on finalized bytes (after encoder flush
  and muxer finalization). Encoder lookahead kept the pre-flush buffer
  near zero, so a chunk could hold the whole batch and finalize far above
  the limit. Oversized video chunks are re-encoded with proportionally
  fewer frames; the next chunk is sized from observed bytes/frame.
- Multi-frame chunks stay within TRANSFER_MAX_CHUNK_BYTES (32 MiB); a
  single frame may use up to TRANSFER_MAX_REQUEST_BYTES (96 MiB, new,
  COMFYUI_DISTRIBUTED_TRANSFER_MAX_REQUEST_BYTES) minus envelope reserve.
  A frame that cannot fit raises FrameTooLargeError.
- The worker encodes all chunks before sending, so an unfittable frame
  fails before anything is delivered (no partial batch on the master).
- Audio rides on the last chunk only when the request stays in bounds;
  otherwise it is sent as a final audio-only completion.
- Legacy fallback triggers only on an older master's rejection
  ("Invalid JSON payload"); other errors, e.g. size limits, raise with a
  pointer to the limit settings instead of resending as legacy_png.
- The master returns 413 when a request exceeds --max-upload-size.

Tests: codec flush-overshoot and single-frame cases, worker fallback /
nothing-sent / audio placement, and real aiohttp server tests with
client_max_size covering bounded high-entropy video, 413 reporting, and
unfittable frames.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0166t8T3CVaxZkJbP2RtSpo6

---------

Co-authored-by: ymiyad <ymiyad@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 20:50:23 +00:00
Robert Wojciechowski 1093818327 feat: add Runpod serverless image collector pools 2026-10-11 04:55:01 +00:00
Robert Wojciechowski cedc8d4591 feat: support audio-only distributed workflows (#87)
Support image, audio, or combined distributed collection with guarded audio-only worker, master, endpoint, preview, and delegate-only paths.
2026-07-12 20:36:43 +10:00
Robert Wojciechowski 41f9e44945 fix: return native prompt queue metadata 2026-04-07 23:19:37 +00:00
Robert Wojciechowski 487f5b9c85 refactor: centralize audio payload codec and harden worker dispatch compatibility 2026-02-28 04:53:20 +00:00
Robert Wojciechowski 04169ac651 fix: correct divider chunking and improve distributed validation/audio transport 2026-02-28 04:53:20 +00:00
Robert Wojciechowski e4c945e536 chore: commit all pending distributed changes 2026-02-28 04:53:20 +00:00
Robert Wojciechowski f0fe702f80 Commit all current refactor changes 2026-02-23 23:47:23 +00:00