nodes/olivv-cs-ComfyUI-FunPack
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,579 Commits 3 Branches 11 Tags
dev
Commit Graph
64 Commits
Author SHA1 Message Date
Claude 0414df00c9 Diffusers LoRA modules with no place are counted under any wrapper prefix; Watermark hint names the trimmed-clip exception 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjX7o2YfeGQE18MEtPu
 2026-11-08 20:19:39 +00:00
digital-garbageandClaude Sonnet 5.5 75fd0d3885 Leak report: log every parent hand-over and every tracked model's state; test with the node cache keeping the chain 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-08 19:07:10 +02:00
Claude 6ae2247e78 Loader: two loaders of one file in one graph no longer reload every run; a ComfyUI that cannot free the earlier copy is said 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVsBg3ixjnT1Fgdy12
 2026-11-08 16:34:55 +00:00
Claude d8e849f615 Timeline never shorter than its lanes even from a saved height; Diffusers LoRA modules with no place in H3 are counted and alerted 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVsBg3ixjnT1Fgdy12
 2026-11-08 16:32:05 +00:00
digital-garbageandClaude Sonnet 5.5 936da56425 Loader: when the same file comes back with other settings (SLA method, attention...), ComfyUI frees the earlier copy when the run ends, instead of evicting it half way ('memory leak with model') 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-08 18:12:08 +02:00
digital-garbageandClaude Sonnet 5.5 1f27540660 Veda leak test: stage-only LoRAs too 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-08 17:59:47 +02:00
digital-garbageandClaude Sonnet 5.5 77bd136a0b Veda leak test with the r2v predictor and a reference image 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-08 17:57:41 +02:00
digital-garbageandClaude Sonnet 5.5 4ec480bf43 Veda leak tests: bf16 so Veda takes calls, FunUISampler node, two runs, timing on 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-08 17:51:19 +02:00
digital-garbageandClaude Sonnet 5.5 cdcc92ad8c Veda: tests that the model is collectable after a run (real MiniMaxH3 class, real guider, every modifier on top, finished and interrupted) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-08 17:46:05 +02:00
digital-garbage 84a92f3d14 Review round 1: carried last frame is the sampler's own, Interpolate keeps full length at x3/x4, MXFP8 skipped no longer blocks LoRA training, Diffusers lora_down/up spelling, back-up 1.0 step lookup, block map mean, Latent upscaler fallback declared, Story box on project switch 2026-11-08 02:22:54 +02:00
digital-garbageandClaude Sonnet 5.5 25cc6ed0b4 Review round 2: partial Q/K/V LoRAs, Turbo polish no longer read as the last step, cut-short videos refused, NaN-safe block map, bounded block ranges; Common phrases lists words and phrases of any length 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-06 12:23:25 +02:00
digital-garbageandClaude Sonnet 5.5 6249d5342b SLA/Veda: a run cancelled in its first step no longer leaves its stabilize-motion memory or kernel failure to the next run 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-05 22:12:45 +02:00
digital-garbage a5f35ea5b9 Veda: split the kernel call into index, quantize and attend timings; cheaper host prep with equal output 2026-11-05 22:10:34 +02:00
digital-garbage affa3a863e Veda: opt-in per-phase timing, one line naming every size of a Two stages run, fewer device reads 
veda_timing (loader, method veda) logs the time in gather, score, select, kernel and scatter
for a run; off by default and it changes no number. The run line now names the size and tile
plan of each stage, not only the last. Cheap speed-ups that keep the numbers exactly: the
list width of kept tiles comes from the layout instead of a device read, the head groups and
the per-row pattern stay on the device, and the predictor's projections are copied from pinned
memory.
 2026-11-05 21:57:31 +02:00
digital-garbage 1e2ac5ca67 Sparse attention method veda for MiniMax H3 (experimental), with an optional predictor download 
Learned tile-sparse attention (Veda, arXiv 2605.30325): tiles, tile plans, predictor
scoring and selection in plain torch (tested on CPU, including a real tiny H3 with a
stand-in kernel), an INT8 Triton kernel derived from SageAttention (untested on a GPU),
installed through the same override and per-step wrapper as SLA. Runs at the predictor's
trained budget; LoRA, MXFP8, Two stages, dense steps and the attention backend compose.
Settings > Models offers the official Hugging Face download of the predictor on a click,
with its licence beside it; taggers and this share one downloader (core/fetch.py).
 2026-11-05 21:32:39 +02:00
digital-garbage 5f6ed35929 Matrix: every modifier is listed or exempt with a reason, must report active, and must wire in; crossed with samplers and Two stages 
Brownian leaves the stock sampler alone when torchsde internals differ. LoRA: unwrapped refiner layout, absent blocks, LoKr.
 2026-11-05 15:58:29 +02:00
digital-garbage 4b306ae65f Round 3: Brownian noise equals stock noise at any sigma height; every LoRA wrapper reaches every Diffusers module 
Queries are limited as plain numbers inside the sampler call. Tests for 11 wrappers and sigma 14.6.
 2026-11-05 15:44:24 +02:00
digital-garbage 3351fbf503 LoRA: a wrapped Diffusers file reaches the fused qkv rows; a wrong-width qkv pair is dropped, not merged 
README credits Karras et al. for the churn idea in Turbo. Tests for three wrappers and the width check.
 2026-11-05 15:23:43 +02:00
digital-garbage 2f1a0df7a0 Review: only H3 LoRAs are renamed to H3 names (LTX transformer_blocks LoRAs load again) 
Interpolate Always warns once, not per render. README credits the resize kernels; hint and example text corrected.
 2026-11-05 15:13:03 +02:00
digital-garbageandClaude Sonnet 5.5 f7b1da518d Test: the VAE loader stub has a model, as the loader now requires 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjV3UWsHHjJiAXix29B
 2026-11-05 14:48:36 +02:00
Claude 4579d31585 LoRA Loader: a slot's settings and the next slot's picker appear only once a LoRA is chosen 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjV2UVj2u3F3mbnYrQW
 2026-11-05 11:23:35 +00:00
Claude 5eabca5839 LoRA loader: Apply to stage (First/Second/Both) for Two stages, and Diffusers-layout H3 LoRAs now load 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVKTwSL4mCUi3hd811
 2026-11-02 12:56:50 +00:00
Claude f7d17cfb15 Diffusion Model Loader: read the stacked output head count from the weights when the file metadata lacks it 
A few-step H3 file whose metadata keeps explicit head sizes but not the head
count was built with one head and failed on the head biases. The count is now
taken from the head bias and patch projection shapes (shapes only, any device
or dtype), with a test through the real loader at every weight dtype.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUsYDkyEtLCrzqv7jo
 2026-11-02 10:57:56 +00:00
Claude 41559e188b VAE loader: a decode-only VAE this ComfyUI cannot read no longer stops the run; the main VAE decodes and the log says so 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWzZx5QzcqkheSuhsy
 2026-10-30 17:39:37 +00:00
Claude 3862f3ec36 LoRA Loader: up to eight LoRAs in one node, applied in order; slot 1 keeps its inputs 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjU1A5dzqoK4stWcmzk
 2026-10-29 19:23:48 +00:00
Claude 3837d585e0 VAE Loader: optional decode-only VAE (Sol-H3-VAE, X2 Detail) while the main VAE encodes 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-10-29 10:59:06 +00:00
Claude b108d4f4f5 H3 loader: MXFP8 option for the middle blocks (Sol-H3 recipe), credit in README 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-10-29 09:44:49 +00:00
Claude a9f5c9f35d VAE loader: pass the file header to the VAE (audio VAEs need their config) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
 2026-10-27 08:06:34 +00:00
Claude 5bc3ce3f95 SLA: test that the rising-share field is drawn only for the sla method 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0176SHndmQj7T1VtWAWZiNcq
 2026-10-25 16:06:31 +00:00
Claude 527d368c82 SLA: optional rising sparsity (sla_sparsity_start), GSRS idea; CPU test env script 
Skip fewer attention blocks on early steps and more on late ones, in a straight
line up to sla_sparsity. Off at 0, untested on H3. Credit GSRS (arXiv 2610.21129).
tools/test_env.sh and tools/cpuforce.py set up the suite on a GPU-less machine.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0176SHndmQj7T1VtWAWZiNcq
 2026-10-25 16:05:33 +00:00
Claude 3adebb731f Rename FunPack to FunUI (5.0.3 Classy Chopper): /fun endpoint, wink logo, load-time migration of old names 
Old project/workflow names and browser settings migrate on load; /funpack redirects to /fun.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016acRss69eH1235eRdFTZHY
 2026-10-25 13:11:03 +00:00
Claude 156f86e618 fix: checkpoint loader reports a missing VAE; a start picture no pipeline slot takes is named as unused 
Tests: VAE, LoRA (7 key dialects), CLIP and checkpoint loaders; every preset x every kind of picked file is used or named.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WP6HMLLhRYcghAEXK4KLwK
 2026-10-21 04:36:20 +00:00
digital-garbageandClaude Sonnet 5.5 4549ffc2b3 feat: Diffusion Model Loader says when fp32 compute is picked over bf16 weights 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-17 03:19:36 +03:00
digital-garbageandClaude Sonnet 5.5 a88b814b28 fix: modules no longer import each other (shared taste helper is a plain file); UI gates match real ids and are tested; boot cannot stall; empty pipelines refused; truncated .gguf listing says so (attacker round 15) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 22:10:20 +03:00
digital-garbageandClaude Sonnet 5.5 0f86ffd909 fix: .gguf listing walks by folder identity (sibling cycles, root links, case); dangling links not listed (attacker round 14) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 20:26:47 +03:00
digital-garbageandClaude Sonnet 5.5 3042532c0c fix: a symlinked folder aliasing a sibling is listed under both names; an undequantizable gguf tensor type names the file (attacker round 13) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 19:28:02 +03:00
digital-garbageandClaude Sonnet 5.5 76d534adb7 fix: symlink loops no longer stall the .gguf listing; a name with .. is refused after a link too (attacker round 12) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 19:17:23 +03:00
digital-garbageandClaude Sonnet 5.5 6416c1b032 fix: a symlinked .gguf inside the model folder loads again (attacker round 11) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 19:09:22 +03:00
digital-garbageandClaude Sonnet 5.5 b08fba7d58 fix: .gguf loading stays inside the model folder, ignores a Manager-disabled pack, keeps big fp32 values finite; text-encoder picker hides .gguf without the pack; truthful refusal text (attacker round 10) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 19:03:32 +03:00
digital-garbageandClaude Sonnet 5.5 40c3366214 fix: a text encoder with vision tensors beside mapped text loads; clear messages for a pack missing its gguf library and for pack breakage (attacker round 9) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 18:53:45 +03:00
digital-garbageandClaude Sonnet 5.5 dfa8f8edf2 fix: a vision-projector .gguf is not accepted as a text encoder; a pack whose gguf library is missing says how to fix it (attacker round 8) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 18:41:18 +03:00
digital-garbageandClaude Sonnet 5.5 f37a647d85 fix: the ComfyUI-GGUF pack's (state dict, extras) result is unpacked; a text-encoder .gguf with no backend says the pack, not pip; the Enhance picker hides .gguf encoders without the pack; docs name the pack requirement, restart, thresholds (attacker round 7) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 18:33:07 +03:00
digital-garbageandClaude Sonnet 5.5 e5568ec02b fix: a text-encoder .gguf is refused when ComfyUI-GGUF is absent too; docs no longer overclaim Ready to generate, failure behaviour, rating thresholds, Export; Start shots hint shortened (attacker round 6) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 18:22:38 +03:00
digital-garbageandClaude Sonnet 5.5 08550e3569 fix: H3 second-pass preset held back; unsupported .gguf text encoders are refused instead of loading as the wrong model; Start shots hint is true for H3; LTX module titled UNTESTED; docs corrected (failure behaviour, Taste key location, install caution, gguf, second pass) (attacker round 5) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-15 18:10:57 +03:00
digital-garbageandClaude Opus 5.5 8ce237dcdd feat: loader logs the file's real weight format (int8 file at bf16 says int8); warns when a cu12 torch on Blackwell halves int8 speed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-10 18:34:58 +03:00
digital-garbageandClaude Haiku 5.5 77748b7a7e fix: dense steps '0' means none, as the tooltip and the earlier commit say (was flagged as a bad token) 
Co-Authored-By: Claude Haiku 5.5 <noreply@anthropic.com>
 2026-10-10 16:15:51 +03:00
digital-garbageandClaude Haiku 5.5 78a418812b fix: SLA light references on comfy_kitchen pool in plain torch, so they run without Triton 
Co-Authored-By: Claude Haiku 5.5 <noreply@anthropic.com>
 2026-10-10 16:13:15 +03:00
digital-garbageandClaude Opus 5.5 f313ed6ef6 fix: Triton SLA no longer falls back to dense when K arrives in another layout than Q 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-10 01:52:37 +03:00
digital-garbageandClaude Opus 5.5 71892d05fd fix: SLA dense steps count from 1 like a person does ('1' is the first; 0 means none in both fields); the run log names the steps that ran at full attention 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-10 01:49:15 +03:00
digital-garbageandClaude Opus 5.5 8fabfe3b3f feat: the model loader's fields read in order: file, storage, attention, then SLA as its choices narrow it 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-10 01:40:01 +03:00