Both runners round the requested resolution and the two-stage LTX path derives
its own, so the request never recorded what came out. Read it off the decoded
frames instead.
Add accum configs, value-side stress rows, a recommendation row, block
specs, and a triton-mm variant for the new use_fp16_accum surface. The
unsafe unquantized-pv mode is measured but never starred or recommended;
accum rows skip on sdnq builds without the kwarg. Also move the dequant
compile verdict off the removed sdnq_dequantize_compile option to a note
keyed on SDNQ_USE_TORCH_COMPILE, fixing the crash after 2250d8052.
check_av returned the module on success and False on failure, so the two
callers testing for None treated a failed import as a working av and reached
into it anyway. It now returns None, and the guard that had to test for both
tests for one.
Tiny decode lost its call site when the video vae hijack was replaced by the
shared one, which has no tiny branch, so selecting it on the video tab quietly
decoded through the full vae for every engine. The decode hijack now takes the
tiny path when the run asked for it, falling back to the full vae whenever
there is no tiny counterpart to use.
The class test also spelled Wan in capitals and matched none of the four Wan
pipeline classes. Alongside that:
- the requested type travels on the pipe rather than a module global, so the
hijack reads the same value the run set
- a latent whose channel count taehv cannot take is reported and falls back
instead of failing inside the first convolution
- decode_video already returns the range the pipelines expect, so the second
normalization that followed it is gone
get_model discarded the variant its caller asked for and re-derived one from
the loaded model type. None of the video model types appear in those sets, so
every video caller got None back and no tiny decoder at all, while kandinsky5
matched the flux group and would have been handed an image decoder.
The derivation now runs only when the caller named nothing. Callers that name
nothing are unaffected, and the one video type that resolved before keeps the
same variant and cache key.
Pins the sentinel contract, row uniqueness, and the equivalence between
dispatch_mode and the ladder it replaced. A row that declares neither a name
marker nor a mapped pipeline class now fails here instead of reaching a runner
that would generate it as text to video.
LTX generates 8n+1 frames and floors anything else internally, so a request
for 120 frames on the shared path silently produced 113. The tab has always
snapped the count before requesting it; the shared path now applies the same
rule, next to the width and height rounding it already did.
Both load buttons matched the dropdown value against the raw row list, so the
separators the list uses for grouping resolved to a row with no repo. The
loader returned early on that row without loading or reporting, and the ltx
tab went on to record load and offload timings for a load that never ran.
Selection now goes through models_def.find, which knows a separator names no
model, and both buttons say what happened. The ltx button had no output bound
at all, so its message went nowhere.
Two ladders decided how a model's inputs get wired, and they had drifted: the
api reported an unrecognized row as t2v while run() fell through to a branch
that wires nothing. Eight LTX condition rows sat in that gap, advertised as
text to video and generating without their conditioning.
dispatch_mode answers once from the row, reading name markers before the
pipeline class because one class serves several modes: six LTXConditionPipeline
rows are named T2V or I2V and generate as such. Rows that declare nothing now
resolve as condition, and the api reports that instead of guessing t2v.
Pins the cases that separate a complete slice from a truncated one, including
the zero-argument script whose empty slice is complete, and asserts no hook
runner slices the vector on its own.
The selectable run and after paths sliced the incoming vector behind an
attribute check alone, so a short vector reached the script as too few
positionals and raised a TypeError out of the runner. Both now resolve the
slice the same way the alwayson hooks do and report the mismatch instead.
The alwayson hook runners checked that a script declared an argument range
but never that the processing object's vector could fill it, so a caller
that did not bootstrap script args splatted fewer positionals than the hook
signature takes. Every registered script raised a TypeError per hook, and
postprocess_image runs per image, so one video generation produced a
traceback per script per frame.
resolve_script_args now answers with the slice or None, and each runner
skips on None. A script that declares no arguments still runs, since its
empty slice is complete rather than truncated.
The FP VAE dropdown defaulted to Local, which is not among its choices, so
the control rendered with an out-of-list value. The decode dispatch treats
anything unrecognized as Full, so Full is the value the default already
meant.
The nVidia Cosmos engine carried two byte-identical Predict2 2B I2V rows,
so the dropdown showed the name twice. The surviving row's url now points
at the Video2World repo it loads; it pointed at the Text2Image image model.
The tab held the only code that built video and audio references, sniffed the
file type itself, and dropped anything it did not recognize: an unknown
extension, a file that had gone missing, and any decode failure were all skipped
without a word, leaving a request that generated from fewer references than were
uploaded.
Reference marshalling now goes through the same funnel the api path uses, and
runs before the load, so a rejected file costs nothing and says which file and
why. The workflow comes from the registry row, which is where the loader reads
it from as well.
- a rejected input returns its reason to the output box, since the general
handler only reaches the log
- references uploaded against a keyframe workflow warn instead of vanishing:
the accordion hides on a row change but the files it held do not
- guard p.close() in the finally, which the model-not-loaded return has always
reached before p exists
A sweep only logged how long it took, so a config list holding candidates the
hardware runs badly stayed invisible until someone profiled a run that looked
hung. The completion listener already receives every candidate's timing, so the
spread between worst and best is free to report.
- log the winning config, the spread, and any candidates that could not run
- warn once per config when the selected one spills registers, naming it, since
the sweep line that carries it is debug
The shape branch read axis 1, which held the frame count back when animatediff
returned (batch, channels, frames, height, width). Diffusers now returns
(batch, frames, channels, height, width) and the modular video path puts
channels last, so axis 1 reads channels or height and the line printed a
plausible wrong number: a 124 frame 1024x576 generation logged frames=576.
len() is the frame count under both layouts and is what the sibling call site
in process_decode already uses.
parse_options reads : and , as separators and = as the only assignment, so a
segment without = becomes a valueless flag set to 1. The shipped strings used
ffmpeg command line spelling, which parses without error into other values.
- crf:16 parsed to {'crf': '1', '16': '1'}, encoding every api, framepack and
seedvr video near lossless rather than at crf 16
- crf=23:b:v=0 pinned the generic bitrate option to 1 bit per second on vp8 and
vp9, collapsing their output
- qscale:v=3 reached mpeg4 and mjpeg as nothing at all, replaced by an explicit
quantizer range
- test-video-codecs.py asserts every preset segment carries an assignment
The core took reference images only, so no api caller could send the video and
audio references the ref2va workflow conditions on, and the marshalling that
handles them existed solely in the MiniMax tab.
validate_references now gates on the workflow and hands the entries to the
architecture that owns them, which accepts decoded images and local file paths
in any mix and preserves their order, since order fixes the labels a prompt
addresses. reference_caps exposes the same limits the validation enforces, so a
client reads them instead of mirroring the numbers.
- MAX_IMAGE_REFERENCES is gone: the limits now cover all three kinds and a total
- the run body no longer builds reference objects or knows their class
- an image is converted where it is built rather than at the call site, so a
reference decoded from a file and one posted as base64 arrive the same way
- pipeline args summarize a reference list by kind, since a decoded video would
otherwise print its frames into the per-generation log line
- the video endpoint documents what it actually accepts: images alone, because
video and audio decode from files rather than from the wire, and an upload
reference only where an extension provides the store that resolves one
MiniMax-H3 conditions on image, video and audio references, and the limits it
enforces on them are constructor defaults on a block class the package does not
re-export, so they cannot be imported and are mirrored here instead.
The resolver takes decoded images and local file paths and returns the reference
objects the pipeline reads, checking cheapest first: classification and counts
open no files, container headers are read without decoding, and only then is the
media decoded. Everything runs before the model load, so a rejected request costs
nothing.
- reference limits as a frozen dataclass, keyed by workflow since the rows that
carry ref2va differ only in which repo they load
- media classification and container probing as generic video helpers
- a url is refused before construction: the reference classes fetch one and
decode whatever comes back
- a video is bounded by duration and by what it decodes to, since the pipeline
truncates it to the generated length and the decode is held across the load
- the frame floor is counted on the decoded video at the rate it resamples to,
which is what the conditioner measures
- torchaudio and av are checked up front rather than surfacing as an import
failure once the weights are resident
On ROCm, host-to-device DMA from mmap'd safetensors pages stalls ~1s per
copy, so weights move to the GPU at ~27 MB/s instead of ~28 GB/s. With
offload enabled this re-copies weights every forward, so generation
appears to hang.
Adds `diffusers_disable_mmap` (Settings > Model Loading), off by default,
which makes diffusers read shards into anonymous memory instead. Costs
peak RAM equal to the model size, so it is opt-in.
SD3.5-large on RX 9070 (gfx1201), same prompt and steps:
off: no image after 120s
on: image in 20s
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
CalamitousFelicitousness
Vladimir Mandic
Dity0
Christopher McGee