sdnext

apg

fix(pipelines): restore clip-skip text encoding for transformers 5.6+

2026-06-25 02:25:33 +01:00

api

update allowed paths handling and document torch versions

2026-10-04 13:52:24 +02:00

attention

add minimax-nunchaku-lite

2026-09-13 12:49:57 +02:00

caption

fix(caption): let qwen vlm processors size their own input

2026-09-30 02:14:47 +01:00

cfgzero

strict ruff without exclude

2026-05-11 08:36:49 +02:00

civitai

fix(civitai): name files from the /models payload

2026-09-30 03:48:49 +01:00

control

fix(control): warn about a separate init image only when one is given

2026-10-06 08:12:30 +01:00

detailer

fix(detailer): class-only prompt fields fall back to the main prompt

2026-09-30 10:41:01 +00:00

dlss

lint

2026-09-28 19:06:05 +02:00

face

refactor(lora): remove the lora_apply_te setting

2026-08-28 13:09:26 +01:00

flash_attn_triton_amd

full codespell coverage

2026-06-04 12:36:10 +02:00

framepack

fp remove custom receipes

2026-09-28 08:04:18 +02:00

ggml

full codespell coverage

2026-06-04 12:36:10 +02:00

hidiffusion

fix(control): release the device cache through devices.torch_gc()

2026-10-05 22:11:42 +08:00

image

update watermarking, add api and cli

2026-10-01 10:20:00 +02:00

intel

fix model-recompile keep state

2026-09-04 09:49:12 +02:00

linfusion

cleanup logger

2026-02-19 11:09:13 +01:00

lora

fix sdnq lora loading

2026-10-04 13:07:30 +03:00

ltx

lora: keep parsed network data through pipeline

2026-09-13 16:31:16 +02:00

merging

linting

2026-07-03 22:05:33 +02:00

minimax

Merge pull request #5091 from CalamitousFelicitousness/feat/lora-pdd

2026-09-16 07:45:57 +02:00

onnx_impl

fix(control): run rtmlib pose on the configured ONNX execution provider

2026-09-26 00:12:04 +00:00

openai

add experimental openai interface

2026-07-02 14:36:44 +02:00

pag

fix(pag): match the loaded pipeline instance when applying attention guidance

2026-09-27 20:44:09 +01:00

postprocess

fix(seedvr): draw the progress bar on the live logger console

2026-09-30 02:14:47 +01:00

ras

strict typechecking

2026-08-16 12:45:50 +02:00

rembg

installer handler for numpy

2026-09-05 22:54:56 +02:00

res4lyf

update schedulers init signature

2026-10-04 09:23:45 +02:00

rife

chore(rife): drop the two vendored v3 modules the v4.25 upgrade orphaned

2026-08-30 18:17:13 -07:00

schedulers

update schedulers init signature

2026-10-04 09:23:45 +02:00

seedvr

fix(seedvr): stitch overlapping video batches into a full-length output

2026-09-30 02:14:47 +01:00

sharpfin

update ruff and lint

2026-07-24 18:20:41 +02:00

taesd

live preview refactoring

2026-09-26 11:08:16 +02:00

teacache

strict typechecking

2026-08-16 12:45:50 +02:00

todo

fix(todo): drop the unreachable duplicate branch in init_generator

2026-09-05 21:22:27 -07:00

vae

more work on microdecoder

2026-09-28 10:36:02 +02:00

video_models

more work on microdecoder

2026-09-28 10:36:02 +02:00

__init__.py

refactor imports

2026-02-19 15:28:24 +01:00

cachedit.py

cleanup logger

2026-02-19 11:09:13 +01:00

call_queue.py

fix(queue): stop the queue lock from suppressing exceptions

2026-08-26 03:36:15 +01:00

cmd_args.py

remove directml

2026-08-10 13:43:45 +02:00

devices_mac.py

mps install torchsde

2026-06-20 08:15:35 +02:00

devices.py

lint: avoid redefining the module-level args name in the offload stream stub

2026-09-27 22:20:21 +08:00

enso.py

run enso extension installer after clone and update

2026-03-20 21:43:44 +00:00

errorlimiter.py

Typing cleanup

2026-05-17 10:41:09 -07:00

errors.py

profiling updates

2026-07-26 19:35:56 +02:00

extensions.py

refactor theme loading

2026-09-15 08:17:27 +02:00

extra_networks.py

lora: keep parsed network data through pipeline

2026-09-13 16:31:16 +02:00

extras.py

fix ui/misc: None desc crash, ratio/tile/lora split guards, parse_metadtaa typo, moondream type guard

2026-06-12 13:00:50 -04:00

files_cache.py

strict typechecking

2026-08-16 12:45:50 +02:00

generation_parameters_copypaste.py

fix lint for shared module import

2026-09-08 22:33:23 -07:00

gr_hijack.py

gradio temp file error handling

2026-09-19 10:11:47 +02:00

gr_tempdir.py

gradio temp file error handling

2026-09-19 10:11:47 +02:00

hashes.py

fix(hashes): snapshot the stores under a lock before saving the cache

2026-09-13 20:35:37 +01:00

history.py

fix model-recompile keep state

2026-09-04 09:49:12 +02:00

images.py

add heif/heic support

2026-08-26 10:24:17 +02:00

img2img.py

feat(ui): filter generated sampler and upscaler lists

2026-09-07 08:29:37 -07:00

infotext_utils.py

ruff lint

2026-02-19 11:13:44 +01:00

infotext.py

samplers expose base/max seq len, improve sampler options save, copy defaults

2026-09-30 18:37:05 +02:00

ipadapter.py

gradio temp file error handling

2026-09-19 10:11:47 +02:00

json_helpers.py

fix(json_helpers): write atomically by default and warn on empty reads

2026-09-13 19:20:10 +01:00

lama.py

unified logger

2026-02-19 09:46:42 +01:00

loader.py

reorder startup

2026-09-05 09:49:28 +02:00

localization.py

cleanup logger

2026-02-19 11:09:13 +01:00

logger.py

fix(logger): keep one console across setup_logging calls

2026-09-30 02:14:47 +01:00

masking.py

installer handler for numpy

2026-09-05 22:54:56 +02:00

memmon.py

torch reset dynamo cache on model reload

2026-08-04 10:58:32 +02:00

memstats.py

improve memory reporting, explicit interpolation and minimax tracking

2026-08-25 09:11:46 +02:00

migrate.py

unified logger

2026-02-19 09:46:42 +01:00

mit_nunchaku.py

experimental microdecoder

2026-09-24 20:53:42 +02:00

model_probe.py

feat(qwen21): add Qwen-Image 2.1

2026-09-21 05:41:32 +01:00

model_quant.py

expose double quant setting

2026-10-03 01:32:39 +03:00

model_te.py

fix: honor offline mode in model loaders

2026-09-06 10:10:36 -04:00

model_tools.py

strict typechecking

2026-08-16 12:45:50 +02:00

modeldata.py

add objectclear model support

2026-09-29 09:41:34 +02:00

modelloader.py

fix(civitai): pass the checkpoint type for reference downloads

2026-09-30 19:37:07 +01:00

models_hf.py

fix(hub): install the token header hijack at startup

2026-08-14 03:39:01 +01:00

modelstats.py

add storage analyzer

2026-08-02 11:22:12 +02:00

modular_guiders.py

refactor transformers hooks

2026-08-31 13:06:02 +02:00

modular_load.py

add minimax-nunchaku-lite

2026-09-13 12:49:57 +02:00

modular.py

update all google stuff

2026-09-05 21:53:29 +02:00

olive_script.py

modernize typing

2026-02-19 09:15:37 +01:00

options_handler.py

refactor(lora): remove the lora_apply_te setting

2026-08-28 13:09:26 +01:00

options.py

samplers expose base/max seq len, improve sampler options save, copy defaults

2026-09-30 18:37:05 +02:00

para_attention.py

cleanup logger

2026-02-19 11:09:13 +01:00

patches.py

add wildcards to image metadata and note separate template from prompt field

2026-05-19 09:45:20 +02:00

paths_internal.py

ruff lint

2026-02-19 11:13:44 +01:00

paths.py

update allowed paths handling and document torch versions

2026-10-04 13:52:24 +02:00

platform_linux.py

strict typechecking

2026-08-16 12:45:50 +02:00

platform.py

optimize sdnq quant-on-load and add platform stats

2026-06-07 11:43:46 +02:00

postprocessing.py

add lint full script

2026-08-16 12:45:50 +02:00

processing_args.py

fix(control): skip the size source check when the input sets the size

2026-10-04 18:27:23 +01:00

processing_callbacks.py

fix(callbacks): take only a pil image in step callback kwargs as a preview

2026-10-06 08:12:30 +01:00

processing_class.py

samplers expose base/max seq len, improve sampler options save, copy defaults

2026-09-30 18:37:05 +02:00

processing_correction.py

live preview refactoring

2026-09-26 11:08:16 +02:00

processing_diffusers.py

more work on microdecoder

2026-09-28 10:36:02 +02:00

processing_grading.py

fix lut

2026-05-07 07:20:20 +02:00

processing_helpers.py

fix(processing): treat init images as one set for multi-image models

2026-09-26 18:47:37 +01:00

processing_info.py

metadata fix wildcard info

2026-09-12 20:36:28 +02:00

processing_prompt.py

fix(processing): treat init images as one set for multi-image models

2026-09-26 18:47:37 +01:00

processing_vae.py

fix(preview): collapse near-opaque alpha in preview frames

2026-09-26 18:47:20 +01:00

processing_video.py

improve memory reporting, explicit interpolation and minimax tracking

2026-08-25 09:11:46 +02:00

processing.py

lora: keep parsed network data through pipeline

2026-09-13 16:31:16 +02:00

progress.py

live preview refactoring

2026-09-26 11:08:16 +02:00

prompt_parser_diffusers.py

safe-check embedding_db

2026-09-30 11:05:47 +02:00

prompt_parser_xhinker.py

fix(prompt): restore textual inversion on clip-skip>=2

2026-06-25 02:25:33 +01:00

prompt_parser.py

fix processing: init_images hasattr typo, empty-list guards, dead timer profile branch

2026-06-12 13:00:31 -04:00

rocm_triton_windows.py

refactor imports

2026-02-19 15:28:24 +01:00

rocm.py

fix lint

2026-09-04 09:54:19 +02:00

safe.py

modular guiders and other stuff

2026-08-30 11:51:19 +02:00

script_callbacks.py

Move functions to match new execution order

2026-04-27 17:15:05 -07:00

script_loading.py

cleanup logging

2026-06-02 08:03:27 +02:00

scripts_auto_postprocessing.py

modernize typing

2026-02-19 09:15:37 +01:00

scripts_manager.py

dlss initial stable

2026-09-09 14:29:41 +02:00

scripts_postprocessing.py

add process video

2026-07-20 21:44:43 +02:00

scripts.py

video: support for scripts/extensions

2026-07-28 10:43:58 +02:00

sd_checkpoint.py

fix(civitai): pass the checkpoint type for reference downloads

2026-09-30 19:37:07 +01:00

sd_detect.py

add objectclear model support

2026-09-29 09:41:34 +02:00

sd_hijack_accelerate.py

minimax native lora handler

2026-09-01 17:38:49 +02:00

sd_hijack_compile.py

refactor modular

2026-08-12 14:24:09 +02:00

sd_hijack_dynamic_atten.py

chore(settings): remove the bmm attention methods

2026-08-24 19:59:41 +01:00

sd_hijack_freeu.py

remove directml

2026-08-10 13:43:45 +02:00

sd_hijack_hfhub.py

refactor modular

2026-08-12 14:24:09 +02:00

sd_hijack_hypertile.py

chore(settings): remove dead attention options

2026-08-23 08:21:28 +01:00

sd_hijack_modular.py

fix second path for video preview, better detect decode path

2026-09-30 21:16:12 +02:00

sd_hijack_safetensors.py

unified logger

2026-02-19 09:46:42 +01:00

sd_hijack_schedulers.py

add ideogram prequant and set default schedule

2026-06-08 17:20:12 +02:00

sd_hijack_te.py

feat(te): add an option to run encoder calls without torch.compile

2026-10-04 19:17:34 +01:00

sd_hijack_transformers.py

complete refactor javascript to typescript and reorg frontend files and folders

2026-05-20 18:08:10 +02:00

sd_hijack_triton.py

fix(triton): seed the first pruned config when skipping autotune

2026-10-04 19:17:34 +01:00

sd_hijack_utils.py

modernize typing

2026-02-19 09:15:37 +01:00

sd_hijack_vae.py

feat(attention): generation context

2026-08-23 08:20:46 +01:00

sd_hijack.py

initial pyright lint

2026-02-21 09:32:36 +01:00

sd_models_compile.py

fix model-recompile keep state

2026-09-04 09:49:12 +02:00

sd_models_utils.py

add storage analyzer

2026-08-02 11:22:12 +02:00

sd_models.py

add objectclear model support

2026-09-29 09:41:34 +02:00

sd_modules.py

full ui-settings refactor

2025-03-30 15:04:17 -04:00

sd_offload_aux.py

fix(offload): create the move stream on the active device instead of hardcoding cuda

2026-09-27 22:15:12 +08:00

sd_offload_balanced.py

fix(offload): create the move stream on the active device instead of hardcoding cuda

2026-09-27 22:15:12 +08:00

sd_offload_group.py

fix(offload): name the reason when streams clamp the group offload blocks

2026-09-27 00:52:15 +01:00

sd_offload_state.py

fix(offload): key the group stats report by component

2026-09-07 22:35:38 +01:00

sd_offload_utils.py

fix dtype inspect

2026-09-11 10:24:34 +02:00

sd_offload.py

update openvino, refactor compile overrides, fix lora load

2026-09-02 10:58:59 +02:00

sd_samplers_common.py

fix second path for video preview, better detect decode path

2026-09-30 21:16:12 +02:00

sd_samplers_diffusers.py

samplers expose base/max seq len, improve sampler options save, copy defaults

2026-09-30 18:37:05 +02:00

sd_samplers.py

when creating sampler, copy all valid options from default sampler

2026-09-30 13:32:08 +02:00

sd_te_remote.py

RUF013 updates and typing update

2026-03-24 05:19:51 -07:00

sd_unet.py

feat(model): secondary unet override slot and ideogram4 native loading

2026-07-11 06:40:07 +01:00

sd_vae.py

fix(vae): read a None patch size as absent in the size multiple

2026-09-27 14:45:35 +01:00

server.py

switch to internally managed uvicorn

2026-08-06 13:24:48 +02:00

shared_defaults.py

fix list vs str

2026-09-10 12:29:46 +02:00

shared_helpers.py

unified logger

2026-02-19 09:46:42 +01:00

shared_items.py

live preview refactoring

2026-09-26 11:08:16 +02:00

shared_legacy.py

update offloading codepaths for non-balanced

2026-08-11 22:09:12 +02:00

shared_state.py

fix second path for video preview, better detect decode path

2026-09-30 21:16:12 +02:00

shared.py

fix circular imports changing theme back to default

2026-09-13 10:28:22 +02:00

storage.py

live preview refactoring

2026-09-26 11:08:16 +02:00

styles.py

fix(styles): recover unrecognized keys swallowed by infotext.parse in style extra

2026-09-26 17:40:03 -06:00

sub_quadratic_attention.py

modernize typing

2026-02-19 09:15:37 +01:00

textual_inversion.py

fix(embeddings): restore multi-vector textual inversion expansion

2026-06-25 02:25:33 +01:00

theme.py

theme handle cli

2026-09-15 09:34:10 +02:00

timer_sdnq.py

Move SDNQ to upstream SDNQ repo

2026-08-10 12:13:10 +03:00

timer.py

modular pipelines intercepts and profiling

2026-08-28 13:32:14 +02:00

token_merge.py

cleanup logging and update requirements

2026-03-13 13:02:41 +01:00

transformer_cache.py

improve network type/version mapping

2026-09-01 09:58:24 +02:00

txt2img.py

fix hires strength handling in txt2img

2026-09-25 07:50:50 +02:00

ui_caption.py

css updates

2026-07-13 15:52:55 +02:00

ui_common.py

address selection filter review feedback

2026-09-12 00:08:08 -07:00

ui_components.py

full codespell coverage

2026-06-04 12:36:10 +02:00

ui_control_elements.py

fix(control): lay out DWPose and RTMW settings panels in grouped rows

2026-09-24 20:24:28 +00:00

ui_control_helpers.py

update masking

2026-05-19 11:56:20 +02:00

ui_control.py

refactor transformers hooks

2026-08-31 13:06:02 +02:00

ui_definitions.py

feat(te): add an option to run encoder calls without torch.compile

2026-10-04 19:17:34 +01:00

ui_docs.py

strict typechecking

2026-08-16 12:45:50 +02:00

ui_extensions.py

handle invalid extension

2026-07-01 18:59:20 +02:00

ui_extra_networks_checkpoints.py

feat(qwen21): add Qwen-Image 2.1

2026-09-21 05:41:32 +01:00

ui_extra_networks_history.py

networks avoid slow yield

2026-08-01 09:10:15 +02:00

ui_extra_networks_lora.py

networks cosmetics and dlss logging

2026-09-18 10:56:39 +02:00

ui_extra_networks_styles.py

networks avoid slow yield

2026-08-01 09:10:15 +02:00

ui_extra_networks_textual_inversion.py

cleanup references to p.sd_model

2026-02-19 20:48:42 +01:00

ui_extra_networks_unet.py

networks avoid slow yield

2026-08-01 09:10:15 +02:00

ui_extra_networks_vae.py

networks avoid slow yield

2026-08-01 09:10:15 +02:00

ui_extra_networks_wildcards.py

cleanup

2026-07-27 21:30:40 +02:00

ui_extra_networks.py

api filepath hardening

2026-09-23 10:47:13 +02:00

ui_gallery.py

ui fixes

2026-05-21 09:23:10 +02:00

ui_guidance.py

fix list vs str

2026-09-10 12:29:46 +02:00

ui_history.py

show_progress requires "full", "minimal", or "hidden"

2025-11-28 02:27:19 -08:00

ui_img2img.py

Fix img2img refiner prompt restoration

2026-09-24 21:57:16 -04:00

ui_javascript.py

theme handle cli

2026-09-15 09:34:10 +02:00

ui_loadsave.py

refactor imports

2026-02-19 15:28:24 +01:00

ui_models_load.py

strict typechecking

2026-08-16 12:45:50 +02:00

ui_models.py

feat(civitai): choose download file names server-side

2026-09-30 03:01:02 +01:00

ui_postprocessing.py

process button busy tracking

2026-07-22 09:39:55 +02:00

ui_prompt_styles.py

fix save style without name

2024-06-17 11:03:24 -04:00

ui_sections.py

samplers expose base/max seq len, improve sampler options save, copy defaults

2026-09-30 18:37:05 +02:00

ui_settings.py

cleanup

2026-09-10 18:33:47 +02:00

ui_storage.py

add storage analyzer

2026-08-02 11:22:12 +02:00

ui_symbols.py

dlss initial stable

2026-09-09 14:29:41 +02:00

ui_txt2img.py

Fix txt2img refiner prompt restoration

2026-09-24 21:56:16 -04:00

ui_video_vlm.py

video: support for scripts/extensions

2026-07-28 10:43:58 +02:00

ui_video.py

placeholder video upscale

2026-08-21 10:26:17 +02:00

ui.py

networks load/download model track progress

2026-05-08 14:43:39 +02:00

update.py

update handle git errors

2026-09-10 21:36:41 +02:00

upscaler_algo.py

prepare queue mgmt

2026-08-22 11:24:41 +02:00

upscaler_nvvfx.py

prepare queue mgmt

2026-08-22 11:24:41 +02:00

upscaler_simple.py

prepare queue mgmt

2026-08-22 11:24:41 +02:00

upscaler_spandrel.py

update upscaler workflow

2026-08-22 20:10:02 +02:00

upscaler_vae.py

update upscaler workflow

2026-08-22 20:10:02 +02:00

upscaler.py

update upscaler workflow

2026-08-22 20:10:02 +02:00

video.py

dlss rewrite

2026-09-27 18:34:38 +02:00

zluda_installer.py

Revert "Avoid using args as a variable name"

2026-03-05 20:17:44 -08:00

zluda.py

unified logger

2026-02-19 09:46:42 +01:00