Commit Graph
328 Commits
Author SHA1 Message Date
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
Claude 24f946f43c release: 5.0.1 changelog, version and training credit
Load Media refuses unreadable files in plain words; gallery delete refuses odd names; stale tests updated.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V9uCRvqd1GDx6PZDZLyovu
2026-10-21 03:40:31 +00:00
Claude 329781499c feat: H3 preset has 15 reference slots (9 pictures, 3 videos, 3 sounds); saved projects get the new ones on open
Pictures are numbered among pictures, so any mix fits R2V's own inputs.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:54:22 +00:00
Claude a36af5f3a1 fix: a video or audio reference is routed from the inputs the model node offers, not from preset data
Works for any H3 Reference to Video pipeline, edited or not. Drops the preset routing data and the refresh that carried it.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:43:47 +00:00
Claude d03ba50216 fix: projects saved while the video/audio Load Media nodes existed drop those slots instead of failing to load
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:37:16 +00:00
Claude bf62683f5a feat: Load Media takes a picture, video or sound and the app wires the output that fits
A video or audio reference now uses an ordinary reference slot, so old projects need no new slots; saved media slots take the preset's current roles.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:22:23 +00:00
Claude 600a4d8050 fix: reference video is no longer cut to 15 seconds
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:02:18 +00:00
Claude 129cc10d0f fix: video and audio references go to R2V's own video/audio inputs; aspect ratio source accepts a video
New Load Media (video) and (audio) nodes; picture loader keeps first frame for the aspect source only.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:01:01 +00:00
Claude f71a055ae0 fix: a video picked as a reference loads as its first frame instead of failing in Load Media
Audio is still refused, with a plainer message.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 01:54:44 +00:00
Claude df5424e0df Sharpness edits the model's answer directly, last step included, as 4.x did
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dy3QqNuYH9NSJgob83xcTX
2026-10-20 16:29:11 +00:00
Claude 0dc605f013 Distilled Flow: three named presets (ord1, ord2, ord2_ab2), no Heun variants
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dy3QqNuYH9NSJgob83xcTX
2026-10-20 16:11:19 +00:00
Claude 73adf3e65d Distilled Flow sampler presets (dflow_*) and a sampler-neutral Sharpness module
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dy3QqNuYH9NSJgob83xcTX
2026-10-20 16:01:27 +00:00
Claude 28d191133b Training: free the card at the start of every run, cached data or not
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 23:48:41 +00:00
Claude ad2157110b Training: the node always runs (a second resume was answered from ComfyUI's cache in 0s); the window adopts the server's pause instead of an older one
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 23:39:55 +00:00
Claude 7ef57ba162 Rated results: caption only from the file's own prompt, never the project's; keep every file listed and mark doubtful ratings
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 22:24:27 +00:00
Claude 63ab3a3ae6 LoRA training: a rated result made in this session takes the prompt embedded in its file; an older rating on a reused name is left out
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 22:17:02 +00:00