Makes a video larger and sharper with the FlashVSR v1.1 model, from 1x to
4x. The model, the loop and the tiling are the pack's own code in plain
PyTorch, so the node needs one model file and no other pack. A long clip
needs no more graphics memory than a short one, and a result too large for
the free memory is made in tiles.
Comes with a help page, the example workflow FlashVSR Video Upscale, and
tests for the helpers.
A prompt box that changes on every run. Choices in curly brackets are
picked on the server from the wired seed, so the same seed gives the same
prompt again and a randomized seed with a run count of 50 gives 50 mixes.
Brackets without a | are left alone, so JSON prompts pass through.
Auto save off: a run shows its pictures on the node and saves nothing.
SAVE ALL keeps every picture, SAVE keeps the one the arrows picked.
Held pictures wait in the temp folder and are copied to the output
folder under the names the node would have given them.
A new node. Type a list of prompts, one on each line, or wire in a list
another node wrote. Empty lines are skipped, a number or bullet at the
start of a line can be taken off, and a limit stops a list that ran long.
A run that saved several pictures showed one, with arrows to step
through them. They now show side by side, as the core Save Image does.
The arrows go on to each picture by itself and round again to all of
them. The other preview nodes show a batch the same way.
The node locked from the first step, where rain or snow over the whole
picture reads as a small local edit, so the effect was held back.
It now watches the first steps, undoing only the model's zoom and shift,
and decides once the picture has formed. When no place has changed
clearly, or the lock would free a wide part of the picture that holds no
clear change, it puts nothing back and only keeps the picture in place.
Local edits lock from that step on and end on the original as before.
An edit that also changes the light on the face (a new hair color on a
close-up) looks better plain: always keeps the old light on everything it
keeps. The README's chain numbers are from a rerun on a seed where the
model makes all five edits.
Two new nodes. Edit Lock sits between the model and the sampler, reads
what the edit changes from the model's own prediction at every step, and
puts the original back everywhere else. Edit Lock Restore swaps the
original's pixels in for those parts after the decode.
The zoom and shift a model adds to the whole picture are measured and
discounted before anything is compared, and an even tint is taken out.
An edit of the whole picture is left alone.
On MiniMax-H3-Image at 4 megapixels, 18 local edits at two seeds each
moved by up to 14.5 px plain and by 0.12 px or less locked.
Four things people ran into while picking a mask:
- Ctrl-click on a part of a picked thing could take the whole thing
away. With only a sweater picked, a Ctrl-click on the face offered
the person, which holds the sweater, and the pick was gone. From a
spot that is not picked, a piece that holds a whole pick is no longer
offered; the picture says nothing is picked there.
- A name could only be taken away while Erase was chosen. The name
field now has a + / - button, and a name typed with a minus in front
("-face") is taken away whichever tool is chosen.
- SAM 3 answers at the size of the picture it is given, so a look at a
3840 px picture took 53 s and an 8192 px one ran a 32 GB card out of
memory. A picture with a long side over 2048 px is now asked about on
a smaller copy, and the answer comes back at the picture's own size:
31 s and 33 s. Pictures up to 2048 px are asked about as before.
- Each change on the loader in front of the node sent one more look and
left the earlier ones waiting. The node's own waiting looks are now
taken out of the queue before a new one is sent.
The button that pauses the look now says Pause or Look on, and an out
of memory stop says so in plain words.
A MiniMax H3 run that keeps a clip's sound stops with KeyError: 'latent'
when the Muse MiniMax Director pack is installed, and an older ComfyUI
stops on a w6a8 model file. Neither message tells a person what to do,
so the run check now shows one toast for each with the cause and the fix.
A Manager install (custom_nodes/ausboss-nodes) beside a git clone
(custom_nodes/ComfyUI-AusBoss) added every route twice and ComfyUI
stopped while starting. Each copy now looks for the others, one loads
and the rest step aside and name the folder to delete.
The job carried the 0.1.0 note as a fixed string, so every later
version would have shown "Initial release" on the Registry. The note is
now a required input of the manual run, and the publish step refuses a
blank one.
Mask by Touch keeping picks on a new picture is a new feature, so this
release is 2.23.0 rather than 2.22.1. It also brings the stopped-run
message fix and the corrected example notes.
A run that stopped at the node left its message on the face until
something else was said there. The face's own runs cleared it, but a
workflow run's result did not, so the message stayed under a good result.
The stop now marks its message, and the next result that comes in
clears it.
A different picture coming in no longer stops the run with every pick
dropped. The node moves the clicks and paint onto it, in the same places,
scaled from the size in their key to the new picture's size, and sends the
face the moved touches. The face takes them while it still holds the picks
they were moved from. New picture, under More, set to start over keeps the
old behaviour.
- Krea 2 Rotate + Outpaint: the note describes the tone match the
graph runs.
- Qwen Image 2.1 Inpaint: the note says the seed is fixed.
- Qwen Image 2.1 Upscale + Restore: the Megapixels note mentions the
roughly 2 MP minimum redraw.
ausboss