Spaces:
Running on Zero
Running on Zero
Commit History
Today
-
Update README.md Running
Verified signatured9cfb3c
-
Upload lora_loader.py with huggingface_hub
Verified signaturec3d3fe5
-
UI: glass v7 — boosted ambient glow opacity (0.22→0.38 teal, 0.18→0.32 purple), added blue center gradient
Verified signatureebaf191 -
UI: glass v6 — radial-gradient glow on body, correct Gradio 6 selectors ([data-testid=block-info], button.label-wrap), transparent .gradio-container
Verified signatureb44b83f -
UI: glass v5 — body::before/::after for glow, JS glassApply force-styling labels/button/panels, CSS-only fallback, setInterval reapply
Verified signatureac2d590 -
UI: glass v4 — glow via JS injection into body, label specificity fixes, accordion teal, button gradient via CSS vars override
Verified signature452f0d5 -
UI: glass v3 — glow z-index:-1, .gradio-container z-index:1 for stacking, duplicate #input-panel deduped
Verified signature0473d08 -
UI: glass v2 — glow blobs via fixed divs, no backdrop-filter on .block, all labels uppercase teal, generate btn above accordion, status text, glass panel wrapper
Verified signature103b8ea -
UI: glass redesign — dark navy bg with ambient glow, glass panels, gradient button, two-column layout
Verified signaturee87beaf -
UI: fix checkbox color — use checkbox_background_color_selected (checked state) instead of checkbox_background_color
Verified signature54434d0 -
UI: set checkbox_background_color via theme for teal checkboxes
Verified signaturefb842ac -
UI: add gradient generate button + teal checkboxes + gradient header text
Verified signature06d05dd -
UI: remove backdrop-filter from glass cards to fix dropdown clipping and accordion blur shift
Verified signature173c05d -
UI: add overflow:visible to glass blocks to fix dropdown clipping
Verified signature8da975a -
UI: simplified — keep gradient bg + glass cards + teal sliders only, revert other CSS changes
Verified signaturede44604
-
UI: fix theme — primary_hue is constructor arg not .set() kwarg
Verified signaturefc31021 -
UI: add primary_hue=blue to theme (fixes orange generate button) + head= CSS
Verified signature90d6be6 -
UI: fix slider via theme slider_color + move CSS to launch(head=) to bypass prefix_css rewriting
Verified signature27b09f6 -
UI: move slider JS to gr.Blocks(js=...) — gr.HTML sanitizes <script> tags
Verified signature15748f3 -
UI: inject slider styles via JS MutationObserver — bypasses CSS specificity entirely
Verified signaturec80cf4c -
UI: fix slider — use --slider-color + ::-webkit-slider-thumb with appearance:none (accent-color was dead)
Verified signaturef5d4edf -
UI: expanded theme — fixed slider (data-testid selector), added secondary button, upload areas, accordion, file/video output, scrollbar, info text, lora preview
Verified signaturebbcf29a -
UI: minimal gradient theme — elem_id selectors only, no dropdown overrides
Verified signature2f3b407
-
Revert: restore original app.py (undo CSS gradient changes)
Verified signature7970a56 -
UI: full CSS rewrite — data-testid selectors, fix dropdown z-clipping, compact cards
Verified signature42cbeea -
UI: fix dropdown, boost textarea colour, shrink card padding
Verified signatured615d88 -
UI: fix card border-radius, themed textarea+number input, panel spacing
Verified signaturef8ea70a -
UI: fix Gradio 6 selectors — correct .block, .label-wrap, direct element targeting
Verified signature19e5a3a -
UI: blue→green→purple gradient theme with frosted glass panels
Verified signaturef5259fc
-
Smashcut: drop ambiguous 'in-and-out' require (false-positives on fingering)
The bare phrase 'in-and-out' normalized to 'in and out' and matched finger-thrusting scenes (e.g. 'His fingers slide in and out'), causing Smashcut (camera) to inject penis-penetration content into a hands-only fingering scene. Removed it; all doggystyle/bench/machine scenarios still match Smashcut via the remaining specific requires.8f58600 -
Fix cross-LoRA trigger token reuse (BBC-class audit)
Audit of LORA_PROMPT_TRIGGERS against official triggerword docs (rolechar .txt files, lopi999 card, Civitai) found two more LoRAs prepending another LoRA's activation token: - Doggy Front View v2 was prepending iGoon's 'front doggystyle' token; documented trigger is 'Pl0wView'. - Fucked From Behind was prepending sfbehind's 'sex from behind' phrase; its own token is 'fucked from behind' (matches derpfuckedfrombehind filename and reference prompt). All other triggers verified already-correct (facial, sensualBJ, nsfwsks, m0u7hfu11, sensual_fingering, pornmaster bukkake, iGoon doggystyle tokens, FOV slider camera phrase). JFJ Deepthroat stays on 'blowjob, deepthroat' (its published trigger).7fe59f2 -
BBC Deepthroat: use the bbc deepthroat trigger token
The prepended trigger was 'deep throat blowjob' — the generic Ultimate Deepthroat token — so the BBC-specific trigger never reached the prompt even though the BBC LoRA had fired. The trained trigger (per the reference prompt and phrase list) is 'bbc deepthroat'; the combined prompt now opens with 'bbc deepthroat; nsfwsks, ...'. BBC Blowjob Extreme already used its own 'bbc extreme blowjob' token.563c2df -
BBC LoRAs: fire on black-context oral scenes
'black man' previously matched no trigger phrase, so a black-man deepthroat/facefuck scene fell through to the generic Ultimate Deepthroat LoRA instead of the BBC variant. BBC Deepthroat and BBC Blowjob Extreme now share the generic action phrases of their category (supersets), but are gated via LORA_AUTO_REQUIRES on black context (black man/black cock/bbc/ interracial). Because the BBC entries sit after the generic ones in the dict, they win the oral-category tie on black scenes, while the gate keeps them excluded from non-black scenes (plain deepthroat, plain blowjob, kissing scenes mentioning a black man all fall through to the generic LoRA).40bf80e -
Deepthroat: add verb-form facefuck phrases
The blowjob LoRA additions were winning the winner-take-all 'oral' category and replacing Ultimate Deepthroat on full-throat scenes, regressing log behavior (BJ deepthroat scenes fire Booster+Deepthroat). Move the aggressive facefuck verb phrases (fucks her face/mouth, fucking her face/mouth, cock fully into her mouth, fully into her mouth, deep in her mouth) onto Ultimate Deepthroat, where they belong: the dedicated blowjob LoRA stays reserved for generic sucking scenes.6ef364a
-
Consistent Smashcut firing on hard-cut thrusting scenes; fix breast-grope activation
Audit of the production log (07b1e48) exposed two activation gaps: 1. Smashcut fired on only 2 of 6 nearly-identical doggystyle hard-cut scenes. The requires gate matched exact phrase forms only: 'fucking her' fired but 'fucks her quickly' didn't; 'in and out of her pussy' fired but 'fully in and fully out'/'in-and-out strokes' didn't. Added verb-form variants ('fucks her pussy', 'thrusting hard', 'thrusting fast', 'fully in and fully out', 'in-and-out', 'driving his hips forward', 'hips driving forward', 'hips slamming forward'). All 6 doggystyle variants + the bench-penetration scene now fire Smashcut consistently. Mouth-fucking scenes stay clean (no bare 'fucks her'). 2. Pinata/grope scenes ('caresses her breasts... groping, squeezing, and stroking them') fired only the generic booster. Added massage-tits phrase variants ('caresses her breasts', 'groping her breasts', 'groping them', 'groping and squeezing', 'stroking her breasts', 'stroking the…f3a961d -
Fix LoRA load failure for Wan-native diff_b format files
Production log: 'iGoon - Blink_Front_Doggystyle_I2V' and 'Ultimate Deepthroat' failed to load with 'TorchaoLoraLinear does not support lora_bias yet', and generation proceeded WITHOUT their weights while the prompt tags still claimed they were active. Root cause: these LoRAs are saved in the Wan-native diff_b format (447 'diffusion_model.*.diff_b' learned-bias keys per file). diffusers' _convert_non_diffusers_wan_lora_to_diffusers maps each diff_b key to 'lora_B.bias', which flips lora_bias=True, which peft's TorchaoLoraLinear hard-rejects on torchao-quantized layers. The previous strip only removed literal 'lora_B...bias' keys from already-converted dicts, missing the Wan-native form entirely. Fix: _strip_lora_bias now also drops keys ending in '.diff_b'. Verified against the real production files (447/447 bias terms stripped, weights preserved) and added a mock-pipe test case for the Wan-native format. Regression: 5/5 mock-pipe cases, 18/18 auto-activation matrix, py_compile all p…07b1e48 -
Auto-LoRA: fire front doggystyle + Smashcut on hard-cut doggy scene
The surveillance doggystyle prompt (on all fours, facing the camera, roughly fucking her) only activated General NSFW Booster. Added: - iGoon - Blink_Front_Doggystyle_I2V: 'doggystyle position', 'doggystyle rhythm', 'facing toward the camera', 'facing towards the camera' (the prompt's phrasing was 'on all fours in a doggystyle position, facing toward the camera' — no directional variant previously matched) - Smashcut requires gate: 'fucking her' so a hard cut into a fucking scene passes the thrusting-scene gate Verified: prompt now activates Front Doggystyle + Smashcut + General NSFW Booster; full 18-test matrix, previous penetration/creampie prompt, and LoRA-load tests all still pass with no new false positives.429d0f4 -
Extend auto-LoRA coverage for penetration/thrusting/creampie phrasing
The surveillance-basement prompt (hard cut + forced penetration + creampie) only activated General NSFW Booster. Added phrases for the phrasings real prompts use: - Penetration Insert: 'into her pussy', 'thrusting in and out', 'pounding her hard', 'pounding her pussy', 'pounds her pussy' - Smashcut requires gate: 'thrusting in and out', 'pounding her hard' so a hard cut followed by thrusting/pounding fires it - Creampie CRM: 'finishes deep inside her', 'finish deep inside her', 'finishing inside her', 'leaking out of her', 'cum leaking out', 'cum visible leaking' Verified: the reported prompt now activates Penetration Insert + Smashcut + Creampie CRM + General NSFW Booster; 18-test regression matrix still passes with no new false positives (incl. 'no zooming' negation and identity boilerplate cases).15712cb
-
Fix runtime LoRA loading on torchao-quantized pipe (bias + activation + cleanup)
Three bugs seen in production logs after the peft 0.20.0 upgrade: 1. 'TorchaoLoraLinear does not support lora_bias yet, set it to False' — diffusers auto-detects lora_bias=True purely from lora_B.*.bias keys in the LoRA state dict (peft_utils.py), and peft's TorchaoLoraLinear hard-rejects it on torchao-quantized layers. load_lora_to_pipe now loads via the dict path (safetensors.torch.load_file) and strips lora_B bias keys first, so such LoRAs (e.g. Ultimate Deepthroat) load successfully. 2. Adapter-name collision cascade ('Adapter name lora_0_high already in use') — a partial failure left lora_loaded=False so unload_lora was skipped and stale adapters leaked into the next task. load_lora_to_pipe now unloads all adapters on failure and re-raises; app.py also unloads in the except path, keeping adapter names reusable across tasks. 3. Latent multi-LoRA activation bug — each load_lora_weights leaves only the last-loaded adapter active, so multiple auto-acti…bf209fb -
Upgrade peft 0.19.1 -> 0.20.0 to fix LoRA loading on torchao-quantized models
TorchaoLoraLinear.__init__ in peft 0.19.1 requires the kwarg get_apply_tensor_subclass, but PEFT's dispatcher only supplies it when the base model was loaded via transformers' TorchAoConfig. diffusers pipelines quantized directly with torchao.quantization.quantize_() (as app.py does) have no hf_quantizer, so the kwarg is never passed and every LoRA load fails with: TorchaoLoraLinear.__init__() missing 1 required keyword-only argument: 'get_apply_tensor_subclass'. peft 0.20.0 (PR #3234, merged May 2026) makes the kwarg optional (defaults to None) so inference-time LoRA loading works on quantize_()'d models. torchao 0.17.0 / torch 2.11.0 / diffusers 0.38.0 remain valid pairs.7119a13 -
Fix auto-LoRA prompt matching: negation guard, typo fixes, phrase coverage
- Add _is_negated guard so negated camera/zoom phrases ('no zooming', 'no zooms that crop') don't fire FOV, while positive 'zoom-ins' still do - Add _TYPO_FIXES map in _normalize (naaked, nuude, niipples, vaagina, ...) - FOV: drop bare 'zoom', require zoom in/out/zooms in/zooms out - Remove over-broad phrases: 'spreading her' (Pussy Helper), bare 'facial' (iGoon Blink_Facial), 'standing position' (Standing Upright Sex), 'bent over' (sfbehind) - Expand coverage: breast squeeze/cup/caress + pronoun forms, fingering masturbation phrases, deep penetration wording, vulva/labia close-up, nudity phrases mapped to General NSFW Booster - Smashcut requires: add 'into and out of her pussy' so 'thrusts into and out of her pussy' phrasing gates it correctly - Tie-break: last-scored group wins on exact score tie (iGoon Facial over Facesplash on shared 'facial cumshot')57207b5 -
Rebuild auto LoRA activation: ICF-scored prompt matching + live preview
New architecture (not a restore of the prior implementation): - Normalized matching (hyphen/space-insensitive, punctuation-stripped) so 'face-fucking' == 'face fucking' - Inverse-concept-frequency scoring: distinctive phrases (unique to few LoRAs) score high, generic phrases shared across many score low; replaces the old longest-keyword-wins heuristic with a principled signal - Category dedupe by highest score (one LoRA per concept), Smashcut gated on pussy-thrusting scene via LORA_AUTO_REQUIRES - auto_activation_details() returns matched phrases + score for a live, explainable preview panel under the prompt box (checkbox default ON) - Data-completeness: generic sex prompts fire the NSFW Booster; thrusting into pussy fires Penetration Insert - Prompt adaptation ported: trigger-words-only merge (user scene wins), full body kept for camera/booster LoRAsbb9df7f
-
copy of thornmaze/wan2-2-i2v-v3 (byte-1:1)
Verified signature1b93f28 -
initial commit
Verified signature1e46db0