CCalamitousFelicitousnessfeat(video): absolute per-request minimax shift on every path
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
linting Signed-off-by: Vladimir Mandic <mandic00@live.com> | 2 个月前 | |
explicit init api limiter Signed-off-by: Vladimir Mandic <mandic00@live.com> | 23 天前 | |
feat(autocomplete): translations opt-in + companion skip filters - 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 | 5 个月前 | |
strict typechecking Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
pipeline init reordering Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
update openvino, refactor compile overrides, fix lora load Signed-off-by: Vladimir Mandic <mandic00@live.com> | 26 天前 | |
add heif/heic support Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
more api cleanup Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
krea2 optional dense masking Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
server info handle multi-gpu Signed-off-by: Vladimir Mandic <mandic00@live.com> | 2 个月前 | |
fix prompt enhance api with vision Signed-off-by: Vladimir Mandic <mandic00@live.com> | 18 天前 | |
add loaded-loras api endpoint Signed-off-by: Vladimir Mandic <mandic00@live.com> | 2 个月前 | |
detailer.next Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
feat(api): add video generation endpoint Add POST /sdapi/v1/video plus GET /sdapi/v1/video/models and GET /sdapi/v1/video/file. The generation body is extracted from the gradio handler into a keyword-only core, video_run.run, which returns a structured result and raises typed errors; the positional generate signature is unchanged and now adapts to the core. Omitting engine and model drives the currently loaded checkpoint when it is video-capable, which covers models loaded from local folders without a registry entry. - registry helpers in models_def (find, engines, pipeline_classes, workflow_for_class); validate_pipeline reuses the shared class set - modular pipes stamp their workflow so out-of-registry loads dispatch onto the modular branch - disk switches (mp4_*) and wire switches (send_*) are independent; artifacts above the base64 cap fall back to path plus the file route, which is jailed to the video output directory and serves video/mp4 with range support - always-on video scripts get bootstrapped default args, matching the txt2img handler; missing bootstrap raised a TypeError per frame - checkpoint overrides are rejected with a pointer to the checkpoint endpoint; unknown engine, model and sampler names return 404 with the valid choices - cli/api-video.py client, test/test-video-api.py suite and a full-test.sh entry; video mimetypes registered; rate-limit cost set - remove the unreferenced video_ui.run_video dispatcher | 1 个月前 | |
fix prompt enhance api with vision Signed-off-by: Vladimir Mandic <mandic00@live.com> | 18 天前 | |
fixes from check-api Signed-off-by: vladmandic <mandic00@live.com> | 5 个月前 | |
Type enforcement for ResGPU Only tuples support typing a specific number of entries. | 5 个月前 | |
fixes from check-api Signed-off-by: vladmandic <mandic00@live.com> | 5 个月前 | |
fix prompt enhance api with vision Signed-off-by: Vladimir Mandic <mandic00@live.com> | 18 天前 | |
Type enforcement for ResGPU Only tuples support typing a specific number of entries. | 5 个月前 | |
multiple cleanups Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
feat(monitor): report model placement in the memory monitor Move the per-component placement walk from the api server into memstats next to ram and gpu stats, and add it to the --monitor tick so offload placement is visible in a log rather than only over the api. - guard the walk internally: the supervisor loop logs its monitor line unguarded, and the walk can race a reload or an offload rewrap - monitor reports gb and merges into a fresh dict, since memory_stats returns a module global that the per-generation log also prints - endpoint keeps reporting raw bytes | 1 个月前 | |
cleanup Signed-off-by: Vladimir Mandic <mandic00@live.com> | 1 个月前 | |
autocomplete dont fetch disabled networks Signed-off-by: Vladimir Mandic <mandic00@live.com> | 15 天前 | |
feat(video): absolute per-request minimax shift on every path Shift is a property of the trained schedule, not of the step count, so the tab sliders take absolute values, defaulting to the shipped 12 and 3. video_minimax resolves each request from the request value or the scheduler config inside apply_overrides, which the tab, the api and the still path all call, so a request without values lands on the shipped schedule. The api maps sampler_shift onto the video schedule and gains audio_shift. Applied values are recorded as Video shift and Audio shift; the PDD pin records what it enforces. | 13 天前 | |
Type enforcement for ResGPU Only tuples support typing a specific number of entries. | 5 个月前 | |
fixes from check-api Signed-off-by: vladmandic <mandic00@live.com> | 5 个月前 |