Spaces:
Running on Zero
Running on Zero
Commit History
2 days ago
-
chore: root the deploy branch on the Space head Running
e2b32f1 -
fix: below 1024 px a control reached by Tab stops above the commit bar instead of under it: the page holds back the bar's height when it scrolls (round 4's N5, WCAG 2.4.11) (#20)
Unverified signatureBelow 1024 px the commit bar (the "Needs a prompt" line and Generate) is fixed to the window's bottom, 97 px tall. A browser scrolls a control reached by Tab only as far as the window's bottom edge, so it came to rest under the bar. The round-4 rig caught it at 390 on 1d8deb6: Tab from Advanced to the monitor's Play scrolled the page to 1104, and Play (y 800-844) lay entirely under the bar (y 747-844). That fails WCAG 2.2 SC 2.4.11, Focus Not Obscured (AA). On 25e35b7 the same Tab had left Play clear of the bar, at y 518-562; nothing held back the bar's height when the page scrolled, then or now. One rule in the below-1024 px block: html { scroll-padding-bottom } takes the same room the page already keeps below its content for the bar (var(--mr-bar-h) + the safe area + 16 px). A browser honours a scroll container's padding when it scrolls a focused control into view, so the control stops above the bar (WCAG technique C43). Desktop is untouched: its Generate sticks inside the rail. te…ea5b282 -
fix: the model's own sound reaches the writer unclamped: both runners build LTX-2.5's vocoder with the pinned forward minus its final clamp to [-1, 1], so sound over full scale is turned down as a whole by the writer instead of clipped inside the model (#14)
Unverified signatureThe lead's real-weights repro on the final backend (mode 05, 704x480x49, seed 7, evidence/local_runs/D2_S2_m05_49f/) still wrote a wav with 2 samples at full scale (int -32768) and no turn-down line. LTX-2.5's vocoder is diffusers' LTX2VocoderWithBWE (snapshot vocoder/config.json; final_act_fn and bwe_final_act_fn are null, so nothing earlier bounds it), and its forward ends `waveform = torch.clamp(residual + skip, -1, 1)` (pinned diffusers, pipelines/ltx2/vocoder.py:594). The model clipped its own sound to exactly full scale, so outputs._under_full_scale (peak > 1.0) never saw an over-range track. Deploy 1's 78 pinned samples were this clamp. audio.forward_without_final_clamp is the pinned forward line for line, minus that clamp: the stage-1 vocoder, the pad to the hop, the mel, the bandwidth extender, the resampled skip, the sum and the trim to the output length. audio.unclamp_vocoder sets it as the vocoder instance's forward. It is called right after each runner builds its componen…80f9b11 -
fix: an adapter that passes its check is staged again, and Remove, Remove all and its strength work again: the adapter list carries no change listener, so Gradio no longer hashes the staged adapters, which cannot be hashed; its own events collapse a failure card naming the adapters, when they changed the list (#20)
Unverified signatureSince minor 2's failure-card remedy (7896071), every form field carried a change listener so that a card collapses when a control its step names changes, and the adapter list (the field `loras`, a gr.State) carried one too. Gradio 6.24 hashes a State that has a change listener before and after every event that writes it (Blocks.process_api: get_state_ids_to_track, then utils.deep_hash), and a staged adapter carries the validator's report, a frozen dataclass holding dicts: deep_hash raises "unhashable type: 'dict'". So on the page, once an adapter passed its check, Check and add and the upload failed with "Error" where the accepted card belongs (nothing staged, the file left in the drop zone), and with an adapter staged Remove, Remove all and the strength failed before their handlers ran: on abc9150, 12 events. The handlers' own tests call them directly and never met Gradio's tracking; the round-4 rig's S8 did. The adapter list is the only State among the form fields (images, video, au…1d8deb6 -
docs: every sentence stays true after the deploy: README and the release notes say this is deploy 2's code and point to issue #32 for what the Space shows, and no doc says the Space still runs deploy 1, is not deployed, or has not been redeployed since August (#32)
Unverified signatureThe commit we deploy is also what origin/main is fast-forwarded to, and nothing can be pushed after the deploy without restarting the public Space, so a sentence that a deploy makes false would stay false. README: "Where things stand, 2026-11-17" says the README describes deploy 2's code, which replaces deploy 1 on the Space, points to SPACE_MODE_MATRIX 10.1-10.3 and the release notes, and to issue #32 for deploy 2's own check on the Space. The cold-start time points to #32 instead of "has not been measured"; the longest accepted reservation is "not measured by these runs"; the browser runs of 2026-11-16 "did not finish in that session" instead of "have not been run ... yet". docs/RELEASE_NOTES.md: "Deploy 2 - 2026-11-17", the code of this commit's tree, the Space result on #32 (also under "On the Space"); deploy 1 "ran" as 0cd54f2 until deploy 2, and main "was fast-forwarded" to 1e9fd20 that day. The other docs, the same way: SPACE_MODE_MATRIX's header and 10 intro, 10.2 and 10.3; …abc9150 -
docs: the release notes' Deploy 2 section names its commits as integrated: UI-B's round-4 package (78036d2 ... 7cef5fb) by issue and these docs by issue, and drops the list of what was still to land (#32)
Unverified signatureb5a4494 -
docs: UI_DESIGN quotes mode 11's sentence as the page shows it and as the brief gives it, "With a speech recording and no first-frame picture, some seeds come out as a black-and-white period film ...", instead of paraphrasing it (#28)
Unverified signature1cda206 -
docs: "Where things stand" says the README describes the code on its branch, which has changed since deploy 1, and that the Space still runs deploy 1, so those changes are not on it yet (#32)
Unverified signature8f43118 -
docs: the README names the size button as the page will after the round-4 review, "Snap to values that run", and its hint as naming the nearest values that run (#20)
Unverified signaturee7caf99 -
docs: the release notes open a "Deploy 2 - 2026-11-17 (in preparation)" section: what changed since deploy 1, issue by issue with its commits (all 35 on fix/studio-2026-11), what lands next, what is not in it, and an "On the Space" heading for the result after the deploy (#32)
Unverified signature85c4433 -
docs: the README's local section says the progress bar names "loading the model" while the text encoder and transformer load and "decoding the frames" after the last step, with either decoder (#12)
Unverified signature974496c -
docs: the README says scripts/local_generate.py runs the same MPS numerics self-test as the app and exits refused before loading anything on a PyTorch that fails it (#11)
Unverified signature71e35bc -
docs: the README's watermark row says a bad pair stops an MPS start in the app's own words before the numerics self-test runs, so it is never reported as a PyTorch that computes wrongly (#10)
Unverified signatureed8912d -
docs: the README says an API call's status Markdown now names each attached adapter and gives the run's time split into the progress bar's phases (#18)
Unverified signaturef9bde99 -
docs: the model-picked length's sentence names where it applies, the modes that offer it, instead of "the other modes", two of which take the length from a clip (#16)
Unverified signature58732a9 -
docs: the README says what the note of a model-picked length reports, and that when the model's own figure lies outside the allowed range the note says so and what the range made of it (#16)
Unverified signaturec511137 -
docs: the README says bitsandbytes' int8 cast warning reaches the Space's log once per process, not once per matrix product (#15)
Unverified signaturea0b76da -
docs: the README says sound the model makes over full scale is turned down to a -0.1 dBFS peak instead of clipped, in the video's track and the wav alike, with the diagnostics saying by how much, and that a user's recording is never changed (#14)
Unverified signature3498ce9 -
docs: the README describes the page after the round-4 review where a reader needs it (the line beside Generate names what returns, the monitor keeps a run and offers another mode's sample and the way back, the player answers keyboard and touch, the Done card's length words, the sound download, an adapter's next step, Restore's note), and UI_DESIGN adds the players' access (#20)
Unverified signature4d60faf -
docs: mode 11's black-and-white sentence names the cause the evidence shows, the seed, not the recording: "With a speech recording and no first-frame picture, some seeds come out as a black-and-white period film", with the same two remedies as the page (#28)
Unverified signature8d0b074 -
docs: the diffusion decoder is built once at start-up, beside the pipeline, and packed with it on the Space, with each run building its own only if that build failed: the README's decoder paragraph and two PLAN passages say so (#17)
Unverified signatured8bbbdb -
docs: the handoff's and ZEROGPU_DISK's status boxes no longer say the Space has run nothing since August: it runs deploy 1, whose Space record is SPACE_MODE_MATRIX §10.1, and the handoff points at the release notes (#29)
Unverified signature70ddbf2 -
docs: the weights come from the image: the README, PLAN and the handoff say preload_from_hub fetches the 35 model files (71.92 GB, no temporal upsampler) and the prompt enhancer's 8 (2.49 GB) before the app starts, and start-up downloads only what is missing, if the disk can hold it (#23)
Unverified signature41dcf05, ff62c55 and 72b989d made the preload live: the README's front matter (B3's) fetches the 35 files the int8 Space loads at their pinned commits and the enhancer's 8 at its own, and preflight.ensure_weights checks the cache at start-up, downloads only the missing files after one warning, and refuses a download the disk cannot hold (missing bytes + ZeroGPU's packed copy + a 10 GB margin, under the 150 GB cap) before writing a byte. The docs still said the Space downloads 72 GB at every start because the preload 401s on a private Space. README: the enhancer paragraph says the image brings its weights on the Space and the start-up prefetch (CUDA only, app.py) is the fallback; the ZeroGPU table gets a Weights row. No cold-start time is claimed: none is measured with the preload. docs/PLAN.md: 2.3 notes the 35-file set, the deploy-shape table's Space and Weights rows are corrected in place (public; from the image), 6.2 and 6.2.1 open with a 2026-11-17 correction, and the enhancer-pre…38e36e9 -
docs: the reservation follows size and length: the README's table is the estimator's (the default run 60 s, needing 120 s of quota), the measured envelope is a stated limit, and SPACE_MODE_MATRIX §10.3 records the six size-and-length runs and the answer to the operator's question (#21)
Unverified signatureac68de5 made zerogpu.estimate_duration a fit of the Space's measured runs with a 1.3 margin per term; the docs still said a flat 180 s, x1.5 with Upscale, +60 with an adapter and +180 with Enhance. README: the reservation section says how a run is priced now and gives the estimator's own figures (computed from the code: the default 704x480, 5 s run reserves 60 s and needs 120 s free; +45 s with Upscale at that size, +40 s with adapters, +80 s with Enhance; 1280x704 at 10 s 145 s; 960x544 at 10 s with Upscale 240 s; a sound-only mode 45 s), that LTX25_GPU_DURATION_SECONDS is ignored and LTX25_GPU_DURATION_FLOOR_SECONDS sets a minimum; deploy 1's GPU windows stay as the history they are. The limits section states the envelope the Space refuses past (64,000 tokens per pass, 520 million returned pixel-frames) in the refusal's own words (tests/test_reservation.py). Enhance's "reserves 180 s more" is 80 s, Upscale's x1.5 is 45 s at the default size, and the Upscale paragraph gives what the …ca1f2a8 -
docs: wording in deploy 1's record: the README's adapter-on-the-Space sentence says Validate once, the matrix's 10.1 intro reads as one paragraph, and the release notes' browser runs open with a sentence (#25)
Unverified signaturec8c5965 -
docs: the README's second browser session names the memory check's figure against its 90 GB limit, so the 93.0 GB reads as the check's sum and not as the other jobs' load (#29)
Unverified signature0eb8e93 -
docs: the decoder choices are named by what a user sees: Auto, "Steadier (diffusion decoder)" and "Sharper (standard decoder)" in the README and UI_DESIGN, with what the Space's A/B showed and what the diffusion decode costs (#27)
Unverified signatureOn the Space (deploy 1, the same seed, prompt and size through both decoders; SPACE_MODE_MATRIX 10.1, rows 1 and 7): the same scene (SSIM 0.876); the diffusion decoder a little softer and steadier from frame to frame, the standard decoder sharper frame by frame with more shimmer (fine detail 10.30 vs 11.65, Laplacian variance 421.6 vs 591.6, shimmer 1.471 vs 1.883). So "Best quality" / "Fast" said the opposite of what a user sees; the UI package renames them, Auto stays the vendor's default, and these docs use the new names. The decode step on the Space, from the last sampling progress to "writing the file" in the two calls' events, took 4.4 s with the diffusion decoder and 1.9 s with the standard one, so the README says about 2.5 s more per run (rounded to the second it is the 3 s the issue cites). The labels at this head are still the old ones in ltx25_studio/ui/render.py; these docs follow the UI package's change.360edcc -
docs: the README says audio to video without a first-frame picture can turn an old-sounding recording into a black-and-white period film, and how to get colour: "in colour" in the prompt, or a first-frame picture (#28)
Unverified signatureOn the Space (deploy 1) the same recording and close-up prompt came out black and white at seed 7 (saturation 0.012) and in colour at seed 21 (0.402), and in colour with the captain's portrait as the first frame (SPACE_MODE_MATRIX 10.1, rows 19, 21, 5). The README's description of audio to video now says so where it names the optional first-frame image. The page gets the same sentence from the UI package.d527b6d -
docs: the README's known issues name Gradio 6.24.0's un-awaited get_current_user warning on page loads, say it is Gradio's own and fixed in 6.25.0, and why the Studio stays on 6.24.0 for now (#24)
Unverified signatureDeploy 1's Space log has "RuntimeWarning: coroutine 'App.create_app.<locals>.get_current_user' was never awaited" from Gradio's own route (ruled not ours; note it). The README now has a Known issues section that says so, that 6.25.0 fixes it upstream, and that the Studio stays on 6.24.0 for now because Gradio is pinned in three places (requirements.txt, pyproject.toml, the Space's sdk_version) and a bump touches the whole UI, so it gets a change of its own. No pin changes.7dbfae6 -
docs: the small truths: the Space is public and runs deploy 1, the README says what the page shows about cost on a Mac in place of the comment that asked for it, the browser session on the fixed build is written, and a speaking face gets the page's own words (#29)
Unverified signatureREADME body: - "Deploys to a private Hugging Face Space" now says public: the repo and the Space were made public on 2026-11-16 (the YAML front matter's preload comment, which also explains the 401 in terms of a private Space, belongs to the package editing the front matter and is untouched); - "Where things stand" no longer says the Space runs the August build: it runs deploy 1, on which all eleven modes ran and were looked at, and it points at the matrix (10.1 the Space, 10.2 the Mac) and the release notes; - the HTML comment addressed to the lead is gone; in its place the sentence it asked for: on a Mac the cost panel reads "Runs on this Mac's GPU; nothing is metered" and nothing on the page speaks of quota, reserving, billing or paying (render.py; pinned by test_ui_device_words.py). This is also the README sentence #19 asks for; - the browser runs: the second session, on a build with the memory check fixed, finished text to video with sound through the page with the…da5f47d -
docs: deploy 1's Space run is in the repo: SPACE_MODE_MATRIX §10.1 call by call, PR #1's corrected texts as the release notes' Deploy 1 section, and the README's Space sentences carry what the Space measured (#25)
Unverified signature§10.1 was a placeholder waiting for the post-deploy Space run. It now records deploy 1's 24 calls (2026-11-16, 16:02-16:27 UTC, Space commit 0cd54f2, the tree of 1e9fd20): per call what was sent, what came back, what was seen and measured, and the GPU-s bound (the window x 2), each row named by its label under the run's evidence/space/matrix/, where every figure in the row can be found (checked by script: 245 figures, none missing). With it: the build and the start-up report, how the outputs were judged (and why the client's MISMATCH on the 13 video-with-sound calls was the client's), what the calls settle, the decoder and adapter A/B pairs, mode 11's colour by seed, and the findings the calls left open. The document's header, the never-written-up block and the section 8 follow-ups that waited on the Space (7, 8, 9, 12, 13) now say what deploy 1 showed. PR #1 is merged and stays as it is on GitHub. docs/RELEASE_NOTES.md holds its corrected body and comment as the "Deploy 1 - 2026-11-1…0646770 -
docs: UI_DESIGN gives the figure line and the Upscale line as the reservation now sizes them: the default run's figure reads "704 × 480, 5.0 s, needs 120 s quota", and the Upscale line names its seconds at the default size and length and points to the cost panel (#21)
Unverified signatureThe reservation follows each run's size and length since #21, so a default run needs 120 s of quota to start (a 60 s reservation, times 2), not 360, and the Upscale line reads "Reserves 45 s more at the default size and length; when it is on, the cost panel shows what it adds." The figure-line paragraph, which this branch extended for M1, still quoted the old 360 s, and the cost-words paragraph said only that the Upscale line names its seconds. Both now say what the page says (the figure as handlers.review and render.figure_line give it for the default Text to video with sound on the Space build).7cef5fb -
fix: mode 11's first-frame line names the cause the round-4 verdict found: with a speech recording and no first-frame picture, some seeds come out as a black-and-white period film; add "in colour" to the prompt, or give a first-frame picture (#28)
Unverified signatureThe round-4 verdict found that the black-and-white result depends on the seed (the same recording and prompt gave a period film at seed 7 and colour at seed 21), not on how old the recording sounds, so "An old-sounding recording can come out as a period film" sent the user looking at the wrong cause. The sentence is now exactly: "With a speech recording and no first-frame picture, some seeds come out as a black-and-white period film: add “in colour” to the prompt, or give a first-frame picture." It stays where it was: in Audio to video's first-frame caption only, under the picture and above the prompt, the two remedies it names. UI_DESIGN's paragraph on mode 11's help says the same. Test (tests/test_ui_copy.py, re-pinned through the built page's own switch): in Audio to video exactly one shown component holds the new sentence, between the picture and the prompt, and the caption is "Optional. Used as the first frame. " followed by it, with no "old-sounding"; in every other mode no com…9887158 -
test: the access test pins the sample jump's desktop rules as they stand after M4: hidden beside the monitor at 1024 px and wider, shown there with mr-over-run while the monitor holds a run of another mode, and with no run the jump carries no mr-over-run (#20)
Unverified signaturee4fc218 -
docs: UI_DESIGN's failure-card paragraph, which this branch extended, is rewrapped at the file's width (#20)
Unverified signature67478d3 -
docs: UI_DESIGN's lines this branch added wrap at the file's width (#20)
Unverified signaturee48ebc3 -
style: this branch's new code and tests are laid out as ruff format lays out the files they sit in; no behaviour changes (#20)
Unverified signatureThe lines the earlier commits on this branch added to ui/blocks.py (already formatted at the base) and ui/render.py, and the test files they created, now pass ruff format. Lines of render.py the formatter would change that this branch did not write are left as they were.f16d35d -
fix: Restore settings says what it did, the seed included: a quiet line in Recent runs reads "Settings from 08:06 restored; the seed is random again, as it was for that run. Your current audio stays as it is." until the next run (#20)
Unverified signatureRound 4, minor 10. Restore writes the run's own settings back, its seed setting among them (usually -1, a new seed each run), and keeps the current media. On a desktop nothing moved and nothing said so (S11 and S12 are the same frame), and "Reuse seed" then "Restore settings" on one row silently went back to a random seed. Restore keeps writing the run's seed setting (it is one of that run's settings; Reuse seed is the seed's own button) and now says so, with the media it keeps, in a line under the Recent runs heading (elem_id recent-note, the page's quiet hint style); the next run's start takes it away. Tests (tests/test_ui_restore_says.py, through the built page's own steps): Reuse seed then Restore writes -1 back and says the seed is random again, naming no media in a mode with none; a run at seed 42 in Audio to video is restored with "with that run's seed, 42" and "Your current audio and image stay as they are."; the next run hides the line; the words.6150e0e -
docs: UI_DESIGN says a LoRA rejection gives one next step for its kind and "Nothing was spent." only on ZeroGPU, and gives the idle monitor's line on each platform; it reflows the strength sentence minor 1 added (#20)
Unverified signaturee6f95d8 -
fix: a LoRA rejection gives one next step for its kind ("Use an adapter made for LTX-2.5.", "Download the file again, then upload it.", ...), and off ZeroGPU neither the card nor the idle monitor speaks of spending (#20)
Unverified signatureRound 4, minor 3, without the operator decision. The rejection card read "Rejected: the adapter's shapes don't fit LTX-2.5. <file> was not staged. Nothing was spent." then the validator's words: no next step, against the page's own rule for a failure (what happened, then one step), and "Nothing was spent." on a machine with no meter. Each rejection kind now has its step (render.lora_step): another adapter made for LTX-2.5 for a version, layer-name, shape, target or attach refusal; the Hub id or an upload for a fetch failure; a fresh download for a cut or unreadable file; a standard LoRA for an IC LoRA; a smaller file for one over the limit; a report for an out-of-date layer table or an error the app has never seen. "Nothing was spent." is the Space's sentence alone (the handler words the card for its platform), and the idle monitor's line with no sample reads "Ready. Nothing runs until you press Generate." off ZeroGPU (on the Space it is unchanged). "spent" and "spend" join the meter …1583c93 -
fix: a failure card no longer outlives Show, a Restore or its own remedy within one mode: each turns it into its one line, "Last run: <mode>, <time>. <headline>." (#20)
Unverified signatureRound 4, minor 2 (R4's residue). R4 collapsed a failure card when the mode changed. Within one mode it stayed red and open: in the round-4 captures Enhance was already unticked and "The prompt enhancer is unavailable. Turn Enhance off to run with your own prompt." stood under Generate, through Show, Restore, LoRA staging and Upscale. Now the same line R4 writes replaces the card when Show puts another run on the monitor, when Restore writes a run's settings (in its own mode too), and when a control the card's step names changes: Enhance for the enhancer card; Upscale, Enhance or LoRA for the quota card; Enhance or Upscale for the per-run limit; size, length or Upscale for a timeout or memory card; LoRA for an adapter card; any field for a refused input (its detail names the field); the media for "Your inputs could not be read". A card whose step names no control (press Generate again) stays until the next run. render.step_names holds which fields each card's step names; each field's c…7896071 -
fix: a cost lamp's state is not in colour alone: an unlit lamp is hidden from assistive tech and the lamps' row is a named group, so what is read is the costs that apply (#20)
Unverified signatureRound 4, minor 12, the panel's part (the visual lens's N2). The lamps marked lit and unlit with a class only, and named their row with aria-label on a plain div, which ARIA does not allow and screen readers skip; a screen-reader user heard every lamp as if it applied, and off ZeroGPU a lit and an unlit lamp carry the same words ("Upscale", "LoRA"). WCAG 1.3.1. An unlit lamp now carries aria-hidden="true" and the row role="group" with its name, as the lens proposed. The picture is unchanged. Test (tests/test_ui_lamps_read.py, panels from handlers.review): at the defaults every lamp is unlit and hidden; with Enhance on, the Enhance lamp is lit and read and every unlit lamp is hidden; the row is a named group. tests/test_ui_parked_upscale.py's lamp reader now reads a lamp whatever its attributes.44edefb -
fix: the run summary's time for a run under half a second reads "under 1 s" (on ZeroGPU "under 1 s of GPU time, under 2 s of your quota"), never "Took 0 s" (#20)
Unverified signatureA sub-second run, as on the tiny checkpoint, read "Took 0 s on the CPU" in the Done card, and "It used 0 s" in the card for a result that could not be shown: a run that took no time at all, which is not what happened. took_words rounds as before, and a run that rounds to 0 s says "under 1 s"; on ZeroGPU the quota it drew is "under" the multiplier's seconds rather than "about 0 s". Half a second and more still reads "1 s". Tests: tests/test_ui_report.py adds the sub-second case on the CPU, unlabelled, on ZeroGPU and at 0.6 s; tests/test_ui_run_end.py's check that the card states what the run used now accepts "under 1 s" (its fake run is sub-second).74d0925 -
fix: each sample's caption says it was made earlier by this app from its example, with that example's inputs and seed, and no longer promises the same result from the same prompt and seed (#20)
Unverified signatureRound 4, minor 8. The samples were made on the operator's Mac (Q8 GGUF transformer); on the Space the same prompt and seed give another take (mode 05 at seed 12: two crewmen on deck there, the ship from above in the sample), yet the captions said "Same prompt and seed as “Storm on deck”" or "same seed", inviting a Space visitor to expect the sample from 360 s of free quota. Every caption now reads "Made earlier by this app from “<example>”, with its <prompt / picture / clip / recording> and seed: ...": what the sample is and where it came from, with no promise of a repeat. The words live in examples/manifest.json. Test (tests/test_ui_sample_captions.py): every shipped caption starts "Made earlier by this app from “" and says neither "Same prompt and seed" nor "same seed".b46dfc2 -
fix: the sample captions name the example each was made from, state the samples' real lengths ("4.7 s, the longest that fits the 5.0 s recording") and say "no upscale" in place of "single pass" (#20)
Unverified signatureRound 4, minor 11. Modes 10 and 11 called 4.7 s "the recording's length" for a 5.0 s recording (examples/media/ocean.wav measures 5.000 s; the run is the longest length on the frame grid that fits it, 113 frames), mode 11's "From the example's recording and prompt" did not say which of its two examples, and "single pass" is builder shorthand. Each caption now names its example in quotes ("Made by this app from “Waves, pictured”, with its recording, prompt and seed: LTX-2.5, no upscale."), the video modes say "no upscale", and the settings of modes 10 and 11 read "4.7 s ..., the longest that fits the 5.0 s recording". The words live in examples/manifest.json, beside the samples they describe. Tests (tests/test_ui_sample_captions.py, over the shipped manifest): every caption names exactly one of its mode's examples, whose seed is the sample's, and carries no "single pass" or "the example's"; every video mode's says "no upscale"; every length a sample's settings state is the file's own …9ab0812 -
fix: the Done card says "chosen by the model" only for a length strictly inside the range the user allowed, and at either end which end it is; "How quota works" gives the timeout card's step; no "legal" on the page (#20)
Unverified signatureRound 4, minor 14, three parts. The Length row. With "Let the model pick the length", diffusers clamps the duration head's figure to the shortest and longest the user allowed and snaps it to the frame grid; on the Space the head said 4.47 s, the range made it 5.0 s, and the card said "chosen by the model" (issue #16). The run record carries the frames rendered and the request the range; constraints.duration_head_frame_range gives the frame counts the head returns at each end, exactly as the pipeline clamps. A length strictly between them is the model's own figure, and only there does the card say "chosen by the model". At an end it says "the shortest you allowed" or "the longest you allowed" ("the only length you allowed" when both ends meet): true whether the range moved the figure or the model landed there, and the run's own note (#16) says what the model chose. The record has no field for the head's figure, so the card does not claim more than this. "How quota works" said a timed-…a8bf7a4 -
fix: "Use this prompt" turns Enhance off in the same step and says so ("Copied to your prompt; Enhance is off"), so the next run sends the enhanced prompt as it is; in a mode that takes no prompt it parks both instead of writing a hidden value (#20)
Unverified signatureRound 4, minor 9. After a run with Enhance on, the Done card offers "Use this prompt" with the prompt the model was sent. It wrote that prompt into the box and left Enhance on, so the next run enhanced the enhanced prompt again (on the Space, reserving the enhancer's seconds again): the next run did not use "this prompt". The click now writes the prompt and unticks Enhance together, and the button reads "Copied to your prompt; Enhance is off", disabled, until the next run offers it afresh. Found on the way: in a mode that takes no prompt (Image to video, after a switch) the click wrote into the hidden prompt box, which a run would then send; it now parks the prompt and Enhance, which come back with the prompt box, as a mode switch does. Tests (tests/test_ui_use_prompt.py, a run with a faked enhancer through handlers.run and the real generate(), the real finish step and click): the prompt is written and Enhance turned off, with the button's words; the next run offers the button afresh…8183336 -
fix: off CUDA a parked Upscale promises no size: while this machine cannot run it for the request, its label is the bare "Upscale ×2" and the cost panel shows no Upscale lamp; at a size it can run, both come back (#20)
Unverified signatureRound 4, minor 7. Where this machine cannot run Upscale ×2 for the request, the control is parked (unticked, disabled, the backend's reason as its line), but its label still read "Upscale ×2: returns 1408 × 960" over "Upscale ×2 needs a CUDA GPU; this machine runs on the CPU.", and the panel kept an unlit Upscale lamp. P12's rule, a size only when it will run, now holds here too. The review step, which already decides the parking, now writes the label with it: the bare label while parked, the returned size for a size the model takes otherwise. The size-hints step no longer writes the label, so two steps fired by one change cannot race over it. The panel drops the Upscale lamp while it is parked. Tests (tests/test_ui_parked_upscale.py, on the CPU platform, through the built page with its first paint): parked at the default size with no size in the label and no Upscale lamp; at 64 × 64 × 9 freed with "returns 128 × 128" and the lamp; at 704 parked again with the bare label; only the re…44c216d -
fix: arrow keys on a LoRA strength slider reach the run: the slider's input is wired as well as its release, last value wins, and the value it sends is held to the slider's own range (#20)
Unverified signatureRound 4, minor 1. The strength was wired to the slider's release only, and Gradio 6.24's slider sends release on pointer-up over the range or on leaving its number box; arrow keys on the range send input and change. A keyboard user saw 0.7 on the slider while the LoRA label, the cost panel's LoRA row and the run kept 1.0. Each row's slider now also listens to input (trigger_mode always_last), running the same step and the same label and review after it. Input fires on every keystroke in the number box too, and a typed value passes through numbers outside the range ("0" on the way to "0.7"), which Gradio's own slider preprocessing refuses with an error on screen; so the value input sends is held to the slider's min and max as the page holds them (read off the range element, elem_id lora-strength-N, since the LoRA package sets the range lazily). The pointer path is unchanged. Tests (tests/test_ui_lora_strength_keys.py, through the built page's own steps): an adapter staged through the …d468ab6 -
fix: the line beside Generate names what the run returns: the returned size, with "upscaled" when Upscale ×2 is on ("1408 × 960 upscaled, 5.0 s, needs … quota"), and "Sound" in a sound-only mode ("Sound, 5.0 s, …"), keeping the length and the quota or device words (#20)
Unverified signatureRound 4's M1. The one-line figure beside Generate (the desktop line over the button on a short window, and the phone and tablet bar's ready line) started from the render size: under Upscale ×2 it said "704 × 480, 5.0 s, needs 540 s quota" for a run that returns 1408 × 960, and in the three sound-only modes it named the 256 × 256 picture they render and throw away. The panel's Returns row, a few centimetres above, said otherwise. figure_line now starts from what the run returns, as the Returns row does: the returned size, with a no-break "upscaled" when stage 2 is on, or "Sound" when only sound comes back; then the length (or "the length of your clip" / "the length of your audio" where an input sets it, as the panel says), then the quota needed on ZeroGPU or where it runs elsewhere. commit_line's ready state is the same line. Tests (tests/test_ui_rail.py): the every-mode test that pinned the render size (test_the_mode_names_its_figure_in_every_mode) is rewritten to pin the returned si…05737f6