Commit Graph
2230 Commits
Author SHA1 Message Date
Claude 77ccd2016d fix: the reference warning says when the server's preset has no video or audio routing
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:40:46 +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 f4187dc962 fix: Render button was dark with near-black text: the softer button fill in polish.css overrode its teal fill; it now keeps its own
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KnV2MVkfEfRMAehmLkbdwC
2026-10-21 02:30:27 +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 3101632ecf fix: the pipeline refresh note also covers a server preset with nothing to add
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:19:03 +00:00
Claude d5ec828026 fix: the reference warning also says why the pipeline refresh added no media slots
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:15:49 +00:00
Claude 1d4c3a7584 fix: the 'reference did not fit' warning names each reference and why
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:13:10 +00:00
Claude 770962e209 fix: saved pipelines not marked whole also get the media slots their preset gained
Reproduced with the real H3 preset slots: video reference was counted as not fitting.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:08:45 +00:00
Claude 4e770e2046 fix: projects started from a preset get the video/audio reference slots an update added
Without them a saved pipeline reported video references as not fitting.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:04:49 +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 1110194d22 Training: steps instead of tabs, walked with Back and Next; no way on to training with an empty set; Results leads back to the set and its tags
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-20 15:52:22 +00:00
Claude 354ca29e6a Training: a wizard-style modal with numbered steps, a title and line per step, and Back/Next and the run controls in the footer
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-20 15:39:57 +00:00
Claude 1d0e95d94f Centred modals sit in the vertical middle of the screen
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ED1Y4LDd9wWTzrcadwtKVZ
2026-10-20 15:39:08 +00:00
Claude 1b9863c13d Loading window: centred text and title, no address before the feature name
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ED1Y4LDd9wWTzrcadwtKVZ
2026-10-20 15:38:05 +00:00
Claude 8fef71b9ea Loading window: opens at once on start, names the module being loaded (N out of M)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ED1Y4LDd9wWTzrcadwtKVZ
2026-10-20 15:34:22 +00:00
Claude 83f9810500 Training window: one watch loop and one preview at a time; a preview pause found after a reload carries on by itself
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-19 00:31:36 +00:00
Claude e1eedfbb75 Tags: saving an edit no longer redraws the step, so typing keeps its focus and place
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-19 00:30:03 +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
Claude 1139c38cf7 LoRA training: rated results are checked against the file itself, files added without words take the prompt embedded in them, no length limit on prefix and postfix
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 22:14:29 +00:00
Claude 0da95575da LoRA training: preview strength setting, negative allowed
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 21:16:11 +00:00
Claude 107bc05f91 RTX VSR: explain a failed load (missing libnvidia-ngx on rentals) instead of the bare SDK code
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AnqLiHvACqkfhdfsb7qgo5
2026-10-18 00:22:18 +00:00
Claude 797cbcc579 LoRA training: time per step, a graph of it, and the time spent in all (restarts included)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-18 00:15:41 +00:00
Claude dfc8153cb3 Media upload: show percent while sending, read the body in 1MB chunks, write off the event loop
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J6rGxH5eLym2ADye6YDgEW
2026-10-17 23:09:37 +00:00
Claude cd4c576e6e LoRA training: download the saved step copies and the preview as well as the final LoRA
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 22:40:15 +00:00
Claude bfaee07258 LoRA training: Download LoRA on a finished run in Results
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 22:35:32 +00:00
Claude c485c4f5df Training: the preset you pick stays picked when you change a setting after it
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 22:16:13 +00:00
Claude 1b6935af8a Gallery: deleting shows a progress bar and count, and runs four at a time
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015xHQk4XeXzJpBR3HSwnoBZ
2026-10-17 22:04:14 +00:00
Claude 9aa1791ec8 LoRA training: encoded clips and captions are kept on disk and reused by the next run
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 22:00:51 +00:00
Claude fb5c631c69 Training: Pausing and Stopping show beside the controls in Train, not with the graph in Results
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 21:23:04 +00:00
Claude 7421333e2a Gallery: Select mode with one confirmed delete for many files
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015xHQk4XeXzJpBR3HSwnoBZ
2026-10-17 21:21:32 +00:00
Claude 2921ff517b Gallery: saved videos and pictures next to Temp files, with preview and confirmed delete
Settings > Saved & Temp Files now has two tabs. Saved lists what ComfyUI wrote to its output folder; Temp is the old list. Click a file to look at it, open it in a tab, or delete it after a question. Delete only removes media files inside the chosen folder.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015xHQk4XeXzJpBR3HSwnoBZ
2026-10-17 21:17:31 +00:00
Claude 6372f11758 UI kit: a group holding one stack gets the same room from its edges; Training Results and Train breathe
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 21:13:01 +00:00
Claude 06f22c6176 Training Results: air between the rows, Restore and continue hides while a run goes on and returns after a failure
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 21:10:12 +00:00
Claude 40c7480d24 Results: a run going on is not listed a second time from its old record
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:58:26 +00:00
Claude 3c421b2c1d LoRA training: fix resume in inference mode, Restore and continue, live graph in Results
The saved optimizer state was read in ComfyUI's inference mode, so the first optimizer step after a resume failed. It is copied to normal tensors first. A failed or stopped run keeps its saved state and Results offers Restore and continue. The graph, progress and previews of a running training moved from Train to Results; Train says where to look.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:54:49 +00:00
Claude b19f7dec2f Log a line whenever a save changes a project's length
A project length that changed on its own is hard to place; the persisted Log now says when and from what to what.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:28:56 +00:00
Claude 65a731584c LoRA training: save a copy of the LoRA every N steps as name_stepN
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:14:16 +00:00
Claude 2a68e5e4cd LoRA training: previews at chosen steps, Pause and Resume in the window; trains the whole set
Every N steps (Preview every) training waits, the pipeline makes a picture or clip with the LoRA so far
from the picked scene and the project's own settings, and training carries on from its saved state.
Pause and Resume work the same way by hand, with Preview now while paused. The What to learn choice is
gone: the Data step decides what is in the set. UNTESTED on real weights.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:12:09 +00:00
Claude 6603f42ecb LoRA training: pause, resume and a preview LoRA at chosen steps (backend)
A run can wait at a step boundary (Pause, or every N steps for a preview): its state is saved,
the LoRA so far is written as <name>_preview.safetensors, and the card is let go. Resume carries on
from the saved state under the same run. UNTESTED on real weights.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:08:01 +00:00
Claude 919097c732 LoRA training: our own loop for H3, and a Log that survives a crash
The H3 run trains with a loop of our own (LoRA on the attention and feed-forward projections of the
50 blocks, per-block checkpoint, uniform noise levels, musubi-tuner's approach) while ComfyUI carries
the batches. Every Log record is flushed to disk as it is said and reloaded on start; the run
writes each stage and step to it. ComfyUI's own offloading toggle is ignored by the new loop.
UNTESTED on the real weights.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 19:57:06 +00:00
Claude a13f037f72 H3 training: modulate blocks out of place so the backward pass stops keeping every block's recompute alive
Measured on a tiny H3: backward growth was ~75 MB per block, now flat (61-88 MB at 2, 8 and 16 blocks).
The in-place mul_/addcmul_ on slices of the stream in the block helpers were the cause.
UNTESTED on the real weights.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 19:47:34 +00:00
Claude 498eb731b6 feat: training learning rate defaults to musubi-tuner's 0.0001 and the H3 note carries its recipe
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 19:34:17 +00:00