Color grading mutated pp.image but never wrote to pp.info, so the
chosen brightness/contrast/gamma/LUT/etc. were invisible in the
saved file's postprocessing/extras chunks and in the live Output
panel — unlike every other postprocessor (Upscale, Rembg, NudeNet,
PixelArt) which all stamp their settings.
Stamp every non-default GradingParams field as 'Grading <name>' so
the trail is consistent with the rest of the Process tab. LUT file
is recorded by basename rather than full path to keep the metadata
string compact.
read_info_from_image had three issues that together corrupted
metadata in the Process tab and img2img batch:
- items aliased image.info, so items.pop('parameters', ...) mutated
the source PIL image's info dict in place
- after popping, parameters was never restored to items, so callers
that re-stamp items onto a downstream image (postprocessing.py,
img2img.py) silently dropped the original generation params for
any input without EXIF UserComment
- synthetic width/height/mode keys were stuffed into items and ended
up persisted as PNG tEXt chunks even though no caller reads them
Result for the Process tab: upscaled outputs lacked the original
parameters chunk and instead had useless width/height/mode chunks
holding the source's pre-upscale dimensions. With this fix items is
a copy, parameters is restored after parsing, and width/height/mode
no longer leak into saved files.
Image.fromarray returns a fresh PIL image with empty .info, so the
source's parameters/UserComment metadata was silently dropped on the
grading roundtrip. In the Process tab this caused upscale + color
grading to save PNGs without the original generation parameters,
while upscale alone (via PIL resize/filter ops that preserve .info)
still worked.
torchvision 0.26 removed the torchvision.io.video submodule entirely
(only image I/O remains). The monkey-patch in install_requirements
(`torchvision.io.video.av = av`) was attempting to swap PyAV into a
torchvision-internal that no longer exists, raising AttributeError on
every FramePack run. The patch is fully vestigial against modern
torchvision; PyAV is still installed by `install('av')`, and the
sdnext save path uses PyAV directly via av.open().
- new autocomplete_translations setting (default off); checkbox in script accordion + locale hint
- get_cached gates companion load on the opt; toggle-flip auto-syncs missing files in a background thread
- list_all_sync, local_names and config_json filter out *.translations.json so companion files never surface as selectable dicts
- one-time per-name warning when opt is on but companion is missing locally
- bare `<` (or partial `<lo`) surfaces full LoRA list; accept overwrites the typed prefix
- empty-query XnIndex.search returns first N items so trigger chars alone yield results
- refocusing a textarea re-fires onInput so a partial tag at the cursor reopens the dropdown
NVIDIA/Cosmos native exports prefix every key with net., including the
bundled llm_adapter half. Add it to KNOWN_PREFIXES so partition_adapter
runs on stripped keys.
Distilled refine ran without the scheduler swap and identity guidance
kwargs prescribed by huggingface/diffusers#13217; only Dev got that
setup via the supports_canonical_stage2 branch. Distilled is already
trained at identity but still needs the recipe applied to avoid the
four-way composition double-dipping on top of the distilled sigma
schedule (oversaturation/striping).
Unify the branches under family == '2.x'; gate only the LoRA load and
unload on supports_canonical_stage2.
Both 2.3-1.1 I2V Distilled entries (full and SDNQ-4Bit) advertised
LTX2Pipeline. ltx_capabilities derives is_i2v partly from the cls_name
check, so I2V code paths (input media UI, supports_input_media, latent
prep) were not engaged for these models.
Conditions were built once at the user's chosen resolution, so condition
variants either ran same-res for both stages (blocked by the previous
gate) or fed base-res conditions to a final-res refine on the manual
upsample+refine path. Build conditions twice when staging is active:
once at base dims for Stage 1, once at final dims for Stage 2. Drop the
condition-class exclusion from supports_two_stage_refine.
auto_refine_upsample gated on supports_canonical_stage2 (Dev-only LoRA
path), so Distilled refine ran same-res for both stages and oversaturated.
Split the gate: supports_two_stage_refine covers any 2.x non-condition
variant and drives the staging plan plus UI Refine default;
supports_canonical_stage2 stays Dev-only for the LoRA branch.
Dispatch anima loras through a dedicated native loader covering kohya,
bfl/ai-toolkit, and hybrid (bfl with alpha plus qwen3 text encoder)
formats. Cosmos 2.0 path rename is mirrored from diffusers in flat
(underscore) form so rewritten paths match network_layer_mapping keys
without further conversion.
Split model_type from cosmos to anima so a future base-cosmos2 lora
path stays separable. Update flow_models, taesd supported list, and the
taesd wanvideo bucket so samplers and preview decoding keep working
after the split.
Extend assign_network_names_to_compvis_modules to walk pipe.llm_adapter
under the lora_llm_adapter_ prefix, and add llm_adapter to
default_components so activate and deactivate include it for anima
models while staying inert elsewhere via the existing getattr guards.
Anima community files bundle the llm_adapter inline alongside the
transformer, so CosmosTransformer3DModel.from_single_file mangles the
118 adapter keys via Cosmos 2.0 substring renames. New helper reads the
safetensors, strips the BFL-style prefix variants, partitions adapter
keys out, runs the rest through diffusers' converter, and loads each
half into its target. SDNQ and layerwise quantization honored; TRT and
GGUF skipped.
Vladimir Mandic
CalamitousFelicitousness
awsr