1b37f259ee
Two stages: test that a planted massive channel is found and steered in both stages
Claude2026-10-29 12:58:45 +00:00
dd80334d11
STAS: the Inactive notice names the strongest channel it found
Claude2026-10-29 12:57:12 +00:00
bd30a9524e
Two stages: wrappers behind it wrap the whole run once; Noise merging, Seed search, Camera move, Shot memory follow the cut
Claude2026-10-29 12:52:25 +00:00
8202caef5f
Resolution hint: name the choice each example belongs to
Claude2026-10-29 11:55:29 +00:00
5df050a7f2
Project settings: Resolution is the Short side / Long side / Pixel count; H3 sizes with FunUIAspectSize, old projects keep Pixel count
Claude2026-10-29 11:47:13 +00:00
c5eeceb42d
Two stages: the whole-schedule copy goes to the stage schedule's device (CPU copy broke SLA and Decisiveness on the GPU)
Claude2026-10-29 11:25:26 +00:00
e439214b76
MXFP8: drop the claim that a forced compute dtype costs the speed (measured: same step times)
Claude2026-10-29 11:21:09 +00:00
f854f64c28
Two stages: both stages see the whole schedule (Decisiveness, SLA ramp, step windows count 8 steps, not 4 + 4)
Claude2026-10-29 11:16:28 +00:00
9278d17f8b
MXFP8: also allowed with weight dtype bf16 (the usual setting for a bf16 file)
Claude2026-10-29 11:10:57 +00:00
51acdb1c12
Diffusion Model Loader: MXFP8 result goes to the log, not only the status output
Claude2026-10-29 11:07:48 +00:00
373f0ea1ab
Two stages: register as a modifier (it was never installed), test that every install() is provided
Claude2026-10-29 11:04:16 +00:00
3837d585e0
VAE Loader: optional decode-only VAE (Sol-H3-VAE, X2 Detail) while the main VAE encodes
Claude2026-10-29 10:59:06 +00:00
a80e58490c
Two stages as a sampling setting (a model wrapper, any sampler) instead of a preset
Claude2026-10-29 10:05:19 +00:00
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
Claude2026-10-29 09:55:37 +00:00
b108d4f4f5
H3 loader: MXFP8 option for the middle blocks (Sol-H3 recipe), credit in README
Claude2026-10-29 09:44:49 +00:00
0f7bbedc60
5.1.0: note for LTX users on picking images and switching presets
Claude2026-10-27 23:24:26 +00:00
6459b144f6
LTX: older Image to Video pipelines get the text to video fallback on load; end-to-end test of the no-input chain
Claude2026-10-27 12:23:29 +00:00
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
Claude2026-10-27 12:17:33 +00:00
61dc98aeb0
Hide unproven enhancements on LTX: a model can hold modules back with hides:<id> traits
Claude2026-10-27 12:10:39 +00:00
048dcd48cf
Blocks settings adapt to the detected model: block count read from the file header, hint and clamp in the panel
Claude2026-10-27 10:56:02 +00:00
92fe909a40
Attention explorer on LTX: depth groups and clip regions (prompt focus stays H3)
Claude2026-10-27 10:48:53 +00:00
eba7c63e9d
Identity bank for LTX: BachVid K/V bank per Taste key with a KV-Lock schedule
Claude2026-10-27 10:41:37 +00:00
8e22f17b00
LTX: Image to Video from References saved before the aspect source is upgraded on load
Claude2026-10-27 10:46:18 +00:00
5d84c71056
LTX Image to Video: the timeline picture is the aspect source (new FunUI Aspect Size node), the project size is the budget
Claude2026-10-27 10:43:44 +00:00
a17484a9aa
Freeze the Guide Frames node's inputs
Claude2026-10-27 10:37:54 +00:00
617dbf2168
Guide frames for LTX (middle frame and memory of the clips before), REINS/Block repeat notes, README thanks JoyAI-Echo
Claude2026-10-27 10:32:30 +00:00
a63bedfd5f
Tests: route tests get stand-in model files so a machine without models still sees a deleted file; optional-slot list follows the two LTX presets
Claude2026-10-27 10:34:48 +00:00
2f4a291b2e
REINS and Block repeat work on LTX's (video, audio) blocks: new block_rows trait
Claude2026-10-27 10:26:44 +00:00
ee56a282d9
Randomizer (attention temperature) now works on LTX: new block_scope trait, LTX blocks counted
Claude2026-10-27 10:23:26 +00:00
478d9d3af7
Temporal style auto picks a style per shot from its words; registry node name back to ComfyUI-FunPack (display name stays FunUI)
Claude2026-10-27 10:20:50 +00:00
cd0ef39cb1
LTX: drop the 'tested' log notice, a working model needs none
Claude2026-10-27 10:09:45 +00:00
c70c74f01f
LTX: two tested presets (Image to Video from References, Video to Video direct) with text to video as the fallback in both; docs say LTX 2.3 is tested
Claude2026-10-27 09:44:54 +00:00
7b9acb5fc1
Shot memory and Camera move: say a start video also counts as a non-empty start
Claude2026-10-27 09:43:55 +00:00
3776c22364
Restoring a saved pipeline no longer lays in another preset's input slots (the identity loader landed in Video to Video, so a picture reference failed with 'identity: no such slot'); Video input card gets a width/height flip
Claude2026-10-27 09:32:34 +00:00
29f7860532
LTX: Image to Video preset that starts from the first reference; a reference feeding a missing node is left unused instead of refusing the run
Claude2026-10-27 09:28:09 +00:00
92ec6c27ce
Project settings: a button that swaps width and height
Claude2026-10-27 09:18:02 +00:00
d4641450c8
Reapply "Direct v2v saved before the video-only flag keeps taking its video from references; render polls survive one unanswered reply; LTX project HTTP test"
Claude2026-10-27 09:14:20 +00:00
975ddf9027
Reapply "API client: a 200 that is not JSON is said plainly instead of failing as 'r is null'"
Claude2026-10-27 09:14:20 +00:00
9d183daf4f
Reapply "LTX image-to-video: the first reference picture is the start when none is picked"
Claude2026-10-27 09:14:20 +00:00
06b467c4ed
Reapply "LTX direct v2v: prompt path proven, start the schedule higher by default (0.909)"
Claude2026-10-27 09:14:20 +00:00
d277ebc76c
Log: a console that cannot print a file name no longer fails the run that mentioned it
Claude2026-10-27 09:12:39 +00:00
3a2d64c792
Load Media: decode only the frames a prepared video keeps, and only the first frame for a picture input
Claude2026-10-27 09:11:17 +00:00
f8955c2ef2
Keep ComfyUI's console on disk (Previous run in the Log window) and log memory at LoRA load and sampler start
Claude2026-10-27 09:03:30 +00:00
f2fcaefa86
Revert "LTX direct v2v: prompt path proven, start the schedule higher by default (0.909)"
Claude2026-10-27 08:53:24 +00:00
5a1da0ce1b
Revert "LTX image-to-video: the first reference picture is the start when none is picked"
Claude2026-10-27 08:52:11 +00:00
4eb2ee2ee2
Revert "API client: a 200 that is not JSON is said plainly instead of failing as 'r is null'"
Claude2026-10-27 08:52:11 +00:00
5a2f9c5999
Revert "Direct v2v saved before the video-only flag keeps taking its video from references; render polls survive one unanswered reply; LTX project HTTP test"
Claude2026-10-27 08:52:11 +00:00
ed4de1e8af
Direct v2v saved before the video-only flag keeps taking its video from references; render polls survive one unanswered reply; LTX project HTTP test
Claude2026-10-27 08:48:01 +00:00
eac7ecd582
API client: a 200 that is not JSON is said plainly instead of failing as 'r is null'
Claude2026-10-27 08:42:42 +00:00
e4111cf74a
LTX image-to-video: the first reference picture is the start when none is picked
Claude2026-10-27 08:39:08 +00:00
859ef99283
LTX direct v2v: prompt path proven, start the schedule higher by default (0.909)
Claude2026-10-27 08:32:10 +00:00
9f8705dd63
Shot camera and SLA need H3-only traits: hidden on LTX (node fields can now require a trait)
Claude2026-10-27 08:29:22 +00:00
11adad2fb4
LTX direct v2v: end-to-end test (real mp4, saved-pipeline upgrade, Load Media, encode, sampler on a real tiny LTXAV)
Claude2026-10-27 08:21:45 +00:00
702aea0f08
LTX video-in pipelines saved with the first-frame wiring are upgraded on run
Claude2026-10-27 08:17:30 +00:00
4ed0685dbc
Video-in presets: wire the frames output statically (a wired input cannot be overridden per run)
Claude2026-10-27 08:13:18 +00:00
1a5d9eab19
Video-to-video presets: the first video among the references is the start when none is picked
Claude2026-10-27 08:09:44 +00:00
a9f5c9f35d
VAE loader: pass the file header to the VAE (audio VAEs need their config)
Claude2026-10-27 08:06:34 +00:00
2a119b76f7
LTX presets: separate model, video VAE, audio VAE and text encoder loaders
Claude2026-10-27 08:01:58 +00:00
2f5a494b0b
LTX 2.3 direct Video to Video preset (encode the video, sample from part-way down the schedule)
Claude2026-10-27 07:47:24 +00:00
36fd60c427
LTX 2.3 Video to Video preset after ComfyUI's IC-LoRA template
Claude2026-10-27 07:31:19 +00:00
1e70272dde
Video input: on LTX a video picked as the scene start feeds its frames, not just the first one
Claude2026-10-27 07:29:40 +00:00
a4eaabc20e
Video input: prepare reference videos (size, crop, rate, skip, cut, every Nth, cap) per project or per scene
Claude2026-10-27 01:04:58 +00:00
9d21739b11
Quick A/B: on the wheel as soon as it is ticked, not only after a run in this page session
Claude2026-10-26 19:42:14 +00:00
677491a18d
Attention explorer: prompt focus at 0.3 of the change size, new levers change less often at first
Claude2026-10-25 22:17:04 +00:00
1b0adbd45c
Quick A/B: ends with the previous clip and the new one, labelled, side by side
Claude2026-10-25 22:16:52 +00:00
5a98b2ed35
Picker wheel: Quick A/B (every enhancement off, last run's seed, generates the picked scene right away, then restores)
Claude2026-10-25 21:54:51 +00:00
089248ea10
Attention explorer: dislikes no longer grow the change size, learned size capped at 0.35
Claude2026-10-25 21:37:21 +00:00
f71407f98e
Attention explorer: the log reports how many attention calls were actually changed, and warns if none
Claude2026-10-25 21:33:33 +00:00
444c65a1de
Attention explorer: the log line counts rated, liked and disliked runs
Claude2026-10-25 20:57:03 +00:00
9699eeea61
Attention explorer: no cap on rated runs
Claude2026-10-25 20:52:51 +00:00
06a8c7948a
Attention explorer keeps up to 200 rated runs, not 64
Claude2026-10-25 20:52:09 +00:00
71b9a1f514
A rating re-runs the same seed for every learner, not only the Attention explorer
Claude2026-10-25 20:44:59 +00:00
0fc20bbc3d
Attention explorer: a rating re-runs the same seed instead of hitting ComfyUI's cache
Claude2026-10-25 20:43:03 +00:00
c8e9a00c86
Save the project when the page is left, and apply the media bin's saved view once the project opens
Claude2026-10-25 20:28:23 +00:00
0599bcc676
Attention explorer: change size learns from ratings, log names exact blocks moved
Claude2026-10-25 20:20:38 +00:00
db46828c99
Attention explorer: per-depth-group attention temperature drawn from ratings
Claude2026-10-25 20:01:23 +00:00
4b48674975
Camera enhancements wheel switch, stable Save video as name, media bin remembers view and sort
Claude2026-10-25 17:51:44 +00:00
db3be87e88
Noise merging: Second run mode, a whole second video from the second seed blended in at the named steps
Claude2026-10-25 17:46:51 +00:00
bc88ac57a7
Noise merging: Second pass new noise, how much of the step's own noise the second pass swaps for the second seed's
Claude2026-10-25 17:29:33 +00:00
e044819db0
Noise merging: optional merge of the starting noise (variance-preserving mix with a second seed)
Claude2026-10-25 17:25:06 +00:00
8d5d6a72b7
Noise merging: Merge sound too option (on by default)
Claude2026-10-25 17:10:49 +00:00
b5656db6b8
Timing: the sampler line gives the time of every step, not just the first two
Claude2026-10-25 17:03:07 +00:00
bc7585cddb
Noise merging: merge the sound too; test that run 2 and 3 on the same cached model still make the extra pass
Claude2026-10-25 17:00:58 +00:00
f44ebc6475
Noise merging: the log line says how long the second pass took
Claude2026-10-25 16:58:36 +00:00
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
Claude2026-10-25 16:53:06 +00:00
53c632d632
Noise merging: say it is on at the start of every run, and say so when no step matched
Claude2026-10-25 16:49:40 +00:00
5ff02e65dd
Noise merging: the log says how far apart the two answers were at each merged step
Claude2026-10-25 16:42:56 +00:00
dc3c580456
Noise merging: second seed is random each run by default (-1)
Claude2026-10-25 16:40:19 +00:00
8a241cf9be
Noise merging: answer chosen steps twice with a second seed and blend the two pictures
Claude2026-10-25 16:35:34 +00:00
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
Claude2026-10-25 16:20:09 +00:00
b903648950
Wheel: Clear references and Disable all guidance enhancements; Guidance switch in Engine settings; branch notes in the branch switcher
Claude2026-10-25 16:16:40 +00:00
2ce29a0998
SLA rising sparsity: note the first real H3 result
Claude2026-10-25 16:16:02 +00:00
5bc3ce3f95
SLA: test that the rising-share field is drawn only for the sla method
Claude2026-10-25 16:06:31 +00:00
527d368c82
SLA: optional rising sparsity (sla_sparsity_start), GSRS idea; CPU test env script
Claude2026-10-25 16:05:33 +00:00
29511f73e8
Registry: real FunUI icon (the wink on dark)
Claude2026-10-25 13:54:48 +00:00
199c39ad98
PTD: the hop notice names the adapter each time it changes
Claude2026-10-25 13:48:17 +00:00
dc4e51563c
5.0.3: stale Decisiveness test, migration tests, changelog folded into the release
Claude2026-10-25 13:44:56 +00:00
3fa2188a97
README: all screenshots retaken with the FunUI name and logo
Claude2026-10-25 13:39:33 +00:00
2e445244df
Test: self-removal refusal names the folder, whatever it is called
Claude2026-10-25 13:28:36 +00:00