This suite of nodes unlocks high-performance parallel processing in ComfyUI by utilizing **Model Replication**. Unlike standard offloading which moves a single model instance between devices, these nodes create independent replicas of the model on each selected GPU/CPU, allowing for true simultaneous batch processing.
active 2026-02-02 → 2026-08-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 193 days from 2026-02-02 to 2026-08-13. Pushes: 23 total, peak 5 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 2 total, peak 1 in a day. Comments: 7 total, peak 4 in a day. Stars: 13 total, peak 5 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Issue comment#1FearL0rd2026-02-22 03:43Requesting clarification on end result
- Issue#1FearL0rd2026-02-16 14:17Requesting clarification on end result
- Issue comment#1q5sys2026-02-14 15:48Requesting clarification on end result
- Issue comment#2shadovv762026-02-13 05:09CLIPTextEncode Can't export tensors on a different CUDA device index. Expected: 0. Current device: 1.
- Issue comment#2shadovv762026-02-13 05:00CLIPTextEncode Can't export tensors on a different CUDA device index. Expected: 0. Current device: 1.
- Issue comment#2FearL0rd2026-02-13 04:32CLIPTextEncode Can't export tensors on a different CUDA device index. Expected: 0. Current device: 1.
- Issue comment#2shadovv762026-02-13 03:57CLIPTextEncode Can't export tensors on a different CUDA device index. Expected: 0. Current device: 1.
- ReleaseFearL0rd2026-02-12 20:10Bug Fixes
- Issue comment#1FearL0rd2026-02-10 23:47Requesting clarification on end result
- ReleaseFearL0rd2026-02-10 23:37Fix dtype compatibility for FP8-converted and native Float models
- Issue#1q5sys2026-02-07 18:41Requesting clarification on end result
- ReleaseFearL0rd2026-02-06 17:30fix: Resolve first-run CUDA OOM and optimize VRAM usage during multi-GPU cloning
- ReleaseFearL0rd2026-02-04 22:25Added VRAM purge toggles to INPUT_TYPES:
- ReleaseFearL0rd2026-02-04 15:46Bug Fixes and improvement
- ReleaseFearL0rd2026-02-03 21:36Bug Fixes / Improvements / Optimizations
- ReleaseFearL0rd2026-02-03 14:42FLUX.1 Support and Intelligent Memory Management
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 13 stars here means stars gained during the window, not the repo's star count.