Spaces:
Running on Zero
Running on Zero
Commit History
-
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
-
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 -
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