nodes/olivv-cs-ComfyUI-FunPack
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,481 Commits 3 Branches 11 Tags
3dbcc8a4e8fada32db8f7be62357ef385ce18dab
Commit Graph
188 Commits
Author SHA1 Message Date
digital-garbageandClaude Sonnet 5.5 6a67c85a8e Test: a cached model gives the same answer after other runs and after a run cut short, for every modifier alone and all together, one stage and two 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-05 22:00:00 +02:00
digital-garbage 702cbe3960 Test: the Nth run of a model equals the first, for every modifier on the tiny H3 
Each modifier alone, same inputs four times: identical numbers, weights untouched, and feeding
the loader's output back into the loader installs nothing twice. Guards against state left on a
cached model making later generations different (the quality loss once suspected on LTX).
 2026-11-05 21:51:22 +02:00
digital-garbageandClaude Sonnet 5.5 0ed59f06d2 Two stages: Trilinear removed (migrated to Bicubic via renamed_options); Save Video: opt-in edge smoothing 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-11-05 20:19:14 +02:00
Claude 25216188ad Run meter: per-step grain and settling of the model's answer, compared with the previous run of the same seed (no extra model call) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjXySkmNCh7j6UXrFYR
 2026-11-05 18:06:09 +00:00
digital-garbage 8c35c4b2ff Matrix: Block repeat, Block influence and Phrase probe join it (recording switched on, valid block range) 
PTD stays out: it replaces the sampler by its adapter's own hops.
 2026-11-05 16:55:38 +02:00
digital-garbage d792d7f5e9 Matrix: LTX file, LoRA slots across stages, stale KJNodes skips removed 
Every modifier alone, in pairs and all together on tiny H3 and tiny LTX; the H3 preset build tests run again.
 2026-11-05 16:01:20 +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 d510cf0116 Combination test: Turbo, Camera move and Seed search join the feature matrix (they were missing) 
Every feature alone, in every pair and all together, with and without Two stages: 218 runs.
 2026-11-05 15:49:41 +02:00
digital-garbage 23a89ca4c5 Test: noise merging follows the first noise's device (meta stand-in) 2026-11-05 15:30:20 +02:00
digital-garbage 478fb835dd Round 2: Brownian clamp survives the CPU tree's float32 cast; Stop per module; block map handles a paired input 
Stop only reaches jobs that check for it; a failure landing with Stop counts as a stop. Hint for imported workflows corrected.
 2026-11-05 15:29:32 +02:00
digital-garbage 7d3baca3c6 Noise merging: the mix uses plain numbers and brings the other noise to the first one's device and dtype 
Test: the mixed noise keeps the dtype and device it meets.
 2026-11-05 15:13:29 +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-garbage 1b9f1cb6aa Review: Brownian noise is the stock noise again; block map profile survives audio+video blocks and cancel 
Queries are clamped into torchsde's span instead of moving the span. A cancelled profile saves nothing.
Attention explorer temperature stays above zero under the map; unmeasured groups are not given 3x.
 2026-11-05 15:10:18 +02:00
digital-garbageandClaude Sonnet 5.5 e3e2f5829a Test: Q steer's push is made visible in the tiny model by sharpening its attention (the video moved by rounding only) 
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 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 7c26a30015 Combination test: every feature alone, in every pair and all together, with and without Two stages 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjU9jGrByQHYf6UYMVV
 2026-11-01 13:06:56 +00:00
Claude 37cdd70e75 Two stages: noise at the hand-over defaults to 0.5, and the schedule the model sees holds the backed-up start so step windows still find their step 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjU9jGrByQHYf6UYMVV
 2026-11-01 12:59:36 +00:00
Claude 12d41311d1 Two stages: optional noise added at the hand-over 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjU9jGrByQHYf6UYMVV
 2026-11-01 12:49:07 +00:00
Claude dc9e430cc1 Block map: the Log says when a run follows a saved map 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 12:30:51 +00:00
Claude 8053b8bb90 Block map: the profile switch turns itself off once a map is saved 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 12:16:04 +00:00
Claude f32aaac550 Block map: a profile of how much each block can take; REINS, Q steer, Attention temperature and Attention explorer nudge their strength by it, a big setting is kept up to what the block takes 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 11:59:10 +00:00
Claude a5c74d0065 Turbo on top of a sampler: describe the churn honestly and test the real relation 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 11:46:20 +00:00
Claude 42d88d8f0b Turbo: 'Keep the chosen sampler' puts the fresh noise and the polish step on top of any sampler 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 11:31:10 +00:00
Claude a12abb45c9 Turbo: test that the switch takes over every sampler 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 11:29:00 +00:00
Claude 6f6e3a730e Video quality: Save Video gets a quality setting (default high, cq/crf 16 instead of 23); clip trims and the final render re-encode at crf 16, not libx264's 23 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-11-01 11:11:01 +00:00
Claude ae230fe31d Attention explorer: option to leave the sound out of the changes 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWYz4aExHqfYnaZAXH
 2026-10-31 00:51:10 +00:00
Claude ccd0edfae0 Turbo sampler: hints describe the setting, not where it was tested 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 17:45:45 +00:00
Claude 78d05035a8 Turbo sampler: drop the scheduler (it was sgm_uniform); the sampler stays registered 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 16:51:35 +00:00
Claude 8e7430577e Turbo sampler: remove step spacing 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 16:46:42 +00:00
Claude ec408a2966 Turbo sampler: polish step is on by default at 0.25 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 16:43:33 +00:00
Claude 2d39641a1f Turbo sampler: polish step slider goes to 0.6 (0.3 was the old ceiling) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 16:40:25 +00:00
Claude 1ddca16f51 Turbo sampler: second order late is off by default (no safe value on a rental) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 16:38:00 +00:00
Claude a351ca712a Turbo sampler: stage-aware flow step, step spacing per stage, optional polish step; funui_turbo sampler and scheduler registered in Comfy 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUCoaPNZ8uLoL2xACR
 2026-10-29 16:25:19 +00:00
Claude aacab8cb7e Two stages: first stage keeps the full picture's shape; the upscaler leaves memory when the method is switched away or Two stages is off 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVWCMpMsh4XkZmnKnh
 2026-10-29 15:37:01 +00:00
Claude 11ddb681ce Two stages: remove Keep the latent's spread (worked badly on a rental) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVWCMpMsh4XkZmnKnh
 2026-10-29 14:24:00 +00:00
Claude 21bd247aaa Two stages: Mitchell and Catmull-Rom resize, Keep the latent's spread switch 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVWCMpMsh4XkZmnKnh
 2026-10-29 14:16:43 +00:00
Claude 00878ae985 Two stages: plain resize choices (lanczos, bislerp, bilinear, trilinear, area, nearest-exact) beside bicubic and the latent upscaler 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVWCMpMsh4XkZmnKnh
 2026-10-29 14:13:28 +00:00
Claude b84e0ea78f Two stages: the latent upscaler list is read again when Settings open 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVWCMpMsh4XkZmnKnh
 2026-10-29 14:05:17 +00:00
Claude f66df804fe Two stages: optional latent upscaler for the hand-over (bicubic stays the default); upscaler file loaded once and kept; credit upscaler authors 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVWCMpMsh4XkZmnKnh
 2026-10-29 13:49:44 +00:00
Claude 1b37f259ee Two stages: test that a planted massive channel is found and steered in both stages 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjXkZ7WjhgGdsdUwPsc
 2026-10-29 12:58:45 +00:00
Claude dd80334d11 STAS: the Inactive notice names the strongest channel it found 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjXkZ7WjhgGdsdUwPsc
 2026-10-29 12:57:12 +00:00
Claude bd30a9524e Two stages: wrappers behind it wrap the whole run once; Noise merging, Seed search, Camera move, Shot memory follow the cut 
Noise merging's per-run start ran once per stage, so it reported no matching step in the stage without the named step,
and the Second run restarted from zero at the cut. Two stages now moves the OUTER_SAMPLE wrappers behind it around the
staged run, and exposes the stage on the guider for the per-stage sampler wrappers.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjXkZ7WjhgGdsdUwPsc
 2026-10-29 12:52:25 +00:00
Claude c5eeceb42d Two stages: the whole-schedule copy goes to the stage schedule's device (CPU copy broke SLA and Decisiveness on the GPU) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWwkXVabCNSQ53xaW1
 2026-10-29 11:25:26 +00:00
Claude f854f64c28 Two stages: both stages see the whole schedule (Decisiveness, SLA ramp, step windows count 8 steps, not 4 + 4) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWwkXVabCNSQ53xaW1
 2026-10-29 11:16:28 +00:00
Claude 373f0ea1ab Two stages: register as a modifier (it was never installed), test that every install() is provided 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWwkXVabCNSQ53xaW1
 2026-10-29 11:04:16 +00:00
Claude a80e58490c Two stages as a sampling setting (a model wrapper, any sampler) instead of a preset 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-10-29 10:05:19 +00:00
Claude 791bb6ca48 H3: two-stage preset (first steps on a smaller picture), Sampler denoised output, Resample to an exact size without an upscaler file, Stage Size node 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
 2026-10-29 09:55:37 +00:00
Claude 3549907a6a 5.1.0: review fixes (interrupt in Noise merging, identity bank probe passes, explorer ratings per model family, NaN guide position), version and changelog 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjYZhHqk196LykrWy3T
 2026-10-27 12:17:33 +00:00
Claude 048dcd48cf Blocks settings adapt to the detected model: block count read from the file header, hint and clamp in the panel 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjYZhHqk196LykrWy3T
 2026-10-27 10:56:02 +00:00
Claude 92fe909a40 Attention explorer on LTX: depth groups and clip regions (prompt focus stays H3) 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjYZhHqk196LykrWy3T
 2026-10-27 10:48:53 +00:00