Claude
01b8a37dff
Attention explorer: prompt weighting, prompt focus, per-prompt recipes, clip regions
...
Regions rescale rows of q on a copy; checked against SLA's override contract.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 22:10:19 +00:00
Claude
089248ea10
Attention explorer: dislikes no longer grow the change size, learned size capped at 0.35
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 21:37:21 +00:00
Claude
f71407f98e
Attention explorer: the log reports how many attention calls were actually changed, and warns if none
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 21:33:33 +00:00
Claude
444c65a1de
Attention explorer: the log line counts rated, liked and disliked runs
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:57:03 +00:00
Claude
9699eeea61
Attention explorer: no cap on rated runs
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:52:51 +00:00
Claude
06a8c7948a
Attention explorer keeps up to 200 rated runs, not 64
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:52:09 +00:00
Claude
71b9a1f514
A rating re-runs the same seed for every learner, not only the Attention explorer
...
The taste module now fingerprints rated rows into the load node's cache key.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:44:59 +00:00
Claude
0fc20bbc3d
Attention explorer: a rating re-runs the same seed instead of hitting ComfyUI's cache
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:43:03 +00:00
Claude
0599bcc676
Attention explorer: change size learns from ratings, log names exact blocks moved
...
Manual size stays as an option. Unchanged groups are not listed.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:20:38 +00:00
Claude
db46828c99
Attention explorer: per-depth-group attention temperature drawn from ratings
...
New sampling module, needs a Taste key. Tests on the tiny H3 fixture.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01RnrTBt9b8CdJwub5roffF3
2026-10-25 20:01:23 +00:00
Claude
4b48674975
Camera enhancements wheel switch, stable Save video as name, media bin remembers view and sort
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01N4wvFjWRL177UGwPSYfy9s
2026-10-25 17:51:44 +00:00
Claude
db3be87e88
Noise merging: Second run mode, a whole second video from the second seed blended in at the named steps
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 17:46:51 +00:00
Claude
bc88ac57a7
Noise merging: Second pass new noise, how much of the step's own noise the second pass swaps for the second seed's
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 17:29:33 +00:00
Claude
e044819db0
Noise merging: optional merge of the starting noise (variance-preserving mix with a second seed)
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 17:25:06 +00:00
Claude
8d5d6a72b7
Noise merging: Merge sound too option (on by default)
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 17:10:49 +00:00
Claude
bc7585cddb
Noise merging: merge the sound too; test that run 2 and 3 on the same cached model still make the extra pass
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 17:00:58 +00:00
Claude
f44ebc6475
Noise merging: the log line says how long the second pass took
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 16:58:36 +00:00
Claude
db291b8c4b
Noise merging: end-to-end test from the app's saved settings through the pipeline route to a 4-step lcm run on the real H3 model class
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 16:53:06 +00:00
Claude
53c632d632
Noise merging: say it is on at the start of every run, and say so when no step matched
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 16:49:40 +00:00
Claude
5ff02e65dd
Noise merging: the log says how far apart the two answers were at each merged step
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 16:42:56 +00:00
Claude
dc3c580456
Noise merging: second seed is random each run by default (-1)
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 16:40:19 +00:00
Claude
8a241cf9be
Noise merging: answer chosen steps twice with a second seed and blend the two pictures
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 16:35:34 +00:00
Claude
cce20f136a
Shot Camera: spaCy model failed to load with preshed 3.0.14 (OverflowError); pin preshed<3.0.14, repair on start, name the real cause in the log
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01T81dXrsAyE9Uu8UvYzKvGt
2026-10-25 16:20:14 +00:00
Claude
2ce29a0998
SLA rising sparsity: note the first real H3 result
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_0176SHndmQj7T1VtWAWZiNcq
2026-10-25 16:16:02 +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
199c39ad98
PTD: the hop notice names the adapter each time it changes
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_016acRss69eH1235eRdFTZHY
2026-10-25 13:48:17 +00:00
Claude
dc4e51563c
5.0.3: stale Decisiveness test, migration tests, changelog folded into the release
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_016acRss69eH1235eRdFTZHY
2026-10-25 13:44:56 +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
c853c9fccc
Decisiveness: slider ends at k 0.96 and 1.04, the largest value found stable by eye
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01GiiQgYH1z4SgQNuNNAgQCV
2026-10-23 18:57:01 +00:00
Claude
103fb5c9b2
Decisiveness: slider range cut again (-10 = k 0.95, +10 = k 1.05); eye test found k 1.06 already overkill
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01GiiQgYH1z4SgQNuNNAgQCV
2026-10-23 18:56:50 +00:00
Claude
152896d1f4
Decisiveness: slider range made gentle (-10 = k 0.85, +10 = k 1.2); 3 was overkill and 6 mostly noise
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01GiiQgYH1z4SgQNuNNAgQCV
2026-10-23 18:53:21 +00:00
Claude
deadf920cf
Decisiveness: slider -10..+10 now balanced (-10 = k 0.5, +10 = k 3) and takes hold earlier (s 6) so positive values are felt on few steps
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01GiiQgYH1z4SgQNuNNAgQCV
2026-10-23 18:44:30 +00:00
Claude
3f8a007da2
fix: PTD hop schedule keeps the sampler's device and dtype
...
The schedule handed to step-aware code (SLA, H3's head bank) was a CPU copy while the call's sigma sits on the GPU, which fails with "Expected all tensors to be on the same device". It now matches the schedule the sampler was given. Test uses the meta device as a stand-in for CUDA.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_0164nckPWA2L2ugVqiDcXzc3
2026-10-23 18:12:38 +00:00
Claude
a271331210
Decisiveness: manual slider is now -10..+10 (0 off, +-10 = 4x / quarter)
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01GiiQgYH1z4SgQNuNNAgQCV
2026-10-23 17:46:20 +00:00
Claude
1ce23bf6d3
Decisiveness: widen limits (manual k 0.25..4, learned k 0.5..2) so the effect is visible
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01GiiQgYH1z4SgQNuNNAgQCV
2026-10-23 17:45:19 +00:00
Claude
e16a236a05
feat: Camera move marked Experimental with a plain-language warning
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01Pto9ujtMpq3Ff4rYuEW1p1
2026-10-23 17:45:05 +00:00
Claude
a3031cf630
feat: one switch in Settings > Conditioning turns off automatic camera prompt enhancement
...
Shot camera's moves, cuts, views, reframes and their chances sit out;
liked details and every other enhancement are untouched.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_014xY2qM34KgJ8yHLsTQEou1
2026-10-22 15:38:39 +00:00
Claude
019d496fab
feat: warn beside Generate when PTD is on with SLA or other enhancements
...
A chip names what else is switched on, since PTD was trained without them; the PTD toggle's hint says the same.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_0164nckPWA2L2ugVqiDcXzc3
2026-10-22 15:31:59 +00:00
Claude
30d499697c
fix: PTD adapter list is read again each time Engine settings open
...
A setting can now read its choices from disk: a module answers setting_options and the module list asks it on every request; Engine settings reload the list when they open. A file added after ComfyUI started shows without a restart.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_0164nckPWA2L2ugVqiDcXzc3
2026-10-22 15:18:13 +00:00
Claude
b067255295
fix: PTD gives step-aware modules its own hop schedule
...
SLA, momentum, velocity bias and the like read sample_sigmas from the run; with PTD on they saw the chosen 20-step schedule instead of the 4 hops. Test added.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_0164nckPWA2L2ugVqiDcXzc3
2026-10-22 15:13:40 +00:00
Claude
d1d83ebd8e
feat: PTD few-step support for MiniMax H3 as a module
...
Settings > Engine > Sampling: pick a PTD adapter file from models/ptd and the run samples the file's own 4 to 8 hops with no CFG, whatever sampler and steps are chosen. Reads the EPFL fl2va and taobao-content-ai Ref2VA releases (bf16 or int8, full or pruned base); ordinary LoRAs stack. Ported from ComfyUI-PTD-Compact (Nynxz), ComfyUI-PTD (EPFL VITA Lab) and ComfyUI-MiniMaxH3-PTD (taobao-content-ai), all Apache-2.0: README Thank you plus NOTICE and licence text in the module. Proven on a tiny real H3 on CPU only.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_0164nckPWA2L2ugVqiDcXzc3
2026-10-22 14:58:06 +00:00
Claude
f0e4a20524
Block influence recording is off until the user turns it on
...
Default was on when no switch file existed. Now off; the Settings toggle stays.
Tests pin the new default.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01HsiMULvrCeUuixnkGAABVU
2026-10-22 08:48:21 +00:00
Claude
49d69aa394
test: a picked H3 file keeps Shadow negative and Video detail on screen
...
Fake safetensors header through the probe and the real manifest; fails on the
code before 9b4b559 , passes after.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_011av2BXzE4UT5HfXpnhTNJQ
2026-10-22 08:37:09 +00:00
Claude
9b4b559d19
fix: H3 file probe now shows Shadow negative and Video detail
...
The pre-load probe left out adaln_modalities, so picking an H3 file hid every
setting that needs it. Run time still checks the loaded model.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_011av2BXzE4UT5HfXpnhTNJQ
2026-10-22 08:17:55 +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
Claude
c089fe3a9a
test: every diffusion loader option loads a tiny H3 file; every reference kind reaches its H3 socket and passes ComfyUI validation
...
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_01WP6HMLLhRYcghAEXK4KLwK
2026-10-21 04:29:20 +00:00
Claude
4069a6f59a
test: every file type the Media bin accepts is made, uploaded, thumbnailed and loaded
2026-10-21 04:29:19 +00:00
Claude
4c677b984d
test: every sampler and scheduler on offer finishes a real tiny H3 sample
2026-10-21 04:29:19 +00:00
Claude
88f4cc2986
test: every modifier setting walked through its choices on the real tiny H3 and LTX models
2026-10-21 04:29:19 +00:00