mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-10 08:00:32 +02:00
cb4590c61fb96b39b559c904d18900943cf2097e
8
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Victor KuznetsovandClaude Opus 5
|
2f72257996 |
Fix what the verification pass found in the knob removal
An adversarial review of |
||
|
Victor KuznetsovandClaude Opus 5
|
52b2c115e8 |
Delete every knob the fixed profiles cannot honor
The CLI still advertised --model, --steps, --guidance-scale, --device and a deprecated --auto. Each pinned a value the two surviving profiles fix -- the model stack, the per-stage distilled schedule, CFG 1.0, CUDA -- so the only outcome any of them had was an error raised several frames below the caller, under a message naming an internal profile. A flag whose sole result is a refusal is worse than no flag: it advertises a capability that does not exist, and it lets a wrapper thread a value that will silently do nothing. They are gone from the parser, from InvisibleEngine, and from WatermarkRemover, so the failure is now a TypeError or a Click "No such option" at the point the caller can act on. The install hint was wrong in the same way. is_available() checked torch and diffusers, then told the user to install [diffusion] -- which contains neither DiffSynth nor the Z-Image face stage both profiles run. Following the advice produced a second, different failure. The module list and the extra name now live once in watermark_profiles (REMOVAL_MODULES, INVISIBLE_EXTRA) and are read by both the CLI gate and the remover's precondition, which cannot drift apart because they are the same tuple. The adaptive-polish default moved out of the argument parser. It was resolved by reading Click's parameter source, which put per-profile data in the CLI layer, left the engine declaring the opposite default (False vs True) so a library caller and a CLI caller on one profile got different output, and lost the polish entirely for anything that supplies the flag non-interactively. The flag is now tri-state (default=None) and resolve_adaptive_polish owns the per-profile answer. The seed follows the same rule: the CLI stopped pre-resolving it. Dead code removed with it: six scan_*_video wrappers and the _scan_video helper none of them had a caller for, PNG_METADATA_KEYS, feather_region_composite and the remover region path that was only reachable from a no-caller convenience wrapper, remove_watermark_batch on both layers, try_empty_device_cache, the _generate/_run_qwen_zimage pass-through pair, self.model_id, and the _internal PEP 562 shim that no caller ever went through. get_device now answers cuda or cpu only: mps and xpu travelled one frame to the same CUDA-only refusal while costing a device probe each, and that refusal now names the resolved device, so device=None on a CUDA-less host says 'cpu' rather than 'None'. The XPU wheel index went with them. Docs: README, cli, installation, python-api, supported-signals, known-limitations and module-internals all still described the removed profiles, the CPU/MPS/XPU ladder, a `default`->`sdxl` alias, and the wrong extra. known-limitations still listed the retired SDXL strength ladder as current. scripts/smoke_matrix.py and real_examples_e2e.py drove --device mps. Next release is 0.25.0, not a patch: this removes public parameters and narrows a published extra on top of the released 0.24.0. pre-commit: 1) maintain.sh - exit 0 (1091 tests, Pyright 0 errors, no vulnerabilities); 2) /simplify - 4 agents, 11 findings applied, 2 skipped (dropping the `device` parameter entirely, which raiw-app pins; folding diffsynth into the `diffusion` extra, which video-only callers do not need); 3) docs sync - grepped every removed identifier across README, docs/, scripts/, .claude/; updated 9 docs; 4) CLAUDE.md - added the no-error-only-knobs rule to .claude/rules/development.md Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
Victor KuznetsovandClaude Opus 5
|
b0ca2054f6 |
Keep only the two-stage profiles and make CUDA a precondition
qwen-zimage becomes the default and sdxl-zimage the only alternative. The
controlnet, sdxl, qwen and default profiles are gone, and with them the CPU and
MPS paths for invisible-watermark removal: neither matched the two-stage
recipe's face preservation, so keeping them advertised a quality this library no
longer delivers. Visible-mark removal and every identify command still run
anywhere.
Retired names are rejected rather than remapped. Silently routing --pipeline
sdxl onward would run an old script at a different strength, on a different
model, at a different quality, and report success.
CUDA is now checked when the remover is constructed instead of when the model
loads. Auto-detection cheerfully returned mps on a Mac, so the failure arrived
several layers down, after the dependency check and the pipeline import, in a
message naming whichever internal pipeline happened to raise. _DEVICES collapses
to {"cuda"} and the cpu/mps float32 branch goes with it.
resolve_strength stays total. It briefly returned None for qwen-zimage, meaning
"ask the resolution curve", which pushed a branch onto both callers and left one
of the two strength policies outside the strength module; the CLI copy had
already grown an `or 0.0` guarding a path its own comment called unreachable. It
now takes the image size and answers for both profiles, so the displayed value
cannot drift from the executed one.
Deletion fallout removed with it: img2img_runner and progress.py (the MPS
recovery path and its progress monitor had no callers left), viable_steps, the
fp16 degenerate-output retry, the fp16 VAE fix, and the Qwen img2img call
builders. try_empty_device_cache moved into watermark_remover rather than
leaving a module whose docstring outlived its code. _HAS_DIFFUSERS routes
through optional_deps.module_available, which is what the rest of the library
uses and what correctly rejects a pruned namespace remnant.
--steps, --guidance-scale and --model now have exactly one legal value each and
are still accepted at parse time, then rejected in remove(). Their help text
says so, but validating them beside the option would be better.
Not addressed, and worth its own decision: invisible_engine forces
min_resolution to 0 for both profiles, so the --min-resolution floor, --upscaler,
_esrgan_upscale, upscaler.py and the esrgan extra are all unreachable.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
|
Victor KuznetsovandClaude Opus 5
|
3d43bac6a5 |
Load the face stage in its own dtype, not the global stage's
The sdxl-zimage profile crashed on every image containing a face. The remover gives it torch.float16, because SDXL ships fp16 weights and an fp16-safe VAE, and that dtype reached the inherited _load_zimage while _zimage_vram_config hardcodes bfloat16 for its offload, onload and computation dtypes. Z-Image was therefore built bf16 and handed fp16 latents, dying in the VAE with "Input type (c10::Half) and bias type (c10::BFloat16) should be the same". Zero-face inputs never enter _run_faces, so the profile passed every timing run it was given, and its tests avoid model downloads, so nothing exercised the loader. Every face-stage loader now reads _face_stage_dtype(), the computation dtype of the VRAM config it is paired with. SAM is routed through it too: it never crashed, since it casts its own inputs and leaves through .float(), but it read the same field and would have re-landed the bug for the next profile with a different global dtype. That field was never the global dtype on this profile anyway - _load_sdxl hardcodes fp16 for its own ControlNet, VAE and pipeline - so its only readers were face-stage code. This also fixes a second instance transitively: the persisted prompt-embedding cache restores payloads at the DiffSynth pipe's dtype, which was fp16 into a bf16 stack before this change. For qwen-zimage the whole change is a strict no-op. The remover already hands it bfloat16, the same value _face_stage_dtype() returns, so production is untouched; verified on an H100 against the deployed pin. The guard asserts the dtype the Z-Image and SAM loaders actually receive rather than comparing the accessor to the config it derives from, which would restate the implementation and pass for any consistently wrong value. Both assertions were mutation-tested against the pre-fix line. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
Victor KuznetsovandClaude Opus 5
|
a9e64b9628 |
Add the sdxl-zimage profile: the same recipe on an SDXL global stage
SdxlZImagePipeline subclasses QwenZImagePipeline and overrides only _run_global and preload, so the face stage is inherited rather than copied and cannot drift between the two profiles. A test asserts the shared methods are the same objects. Four things are architecture-bound and swap with the model: the ControlNet, the four-step distillation LoRA (SDXL-Lightning at its documented 1.0, not the reference graph's 0.8, which belongs to a different LoRA), the sampler (Euler trailing, no AuraFlow shift), and the latent grid at 8 px against Qwen's 16. Strength is architecture-bound too, which is the easy mistake and cost two wrong conclusions before it was caught. An SDXL global pass leaves SynthID at the strength Qwen needs: through the Gemini app on a native 2816x1536 original, 0.154 is FOUND while 0.20, 0.25 and 0.30 are clean. The profile therefore takes a flat vendor policy - OpenAI 0.15, Gemini 0.25, unknown following Gemini - rather than resolution_adaptive_denoise, because flat values are what was measured and no size dependence has been established for this stage. requested_steps exists because the runtimes truncate differently: DiffSynth sets sigma_start = denoising_strength and runs every requested step, while Diffusers img2img truncates the step count, so four steps at 0.15 executes zero and returns a bare VAE round-trip. Also records both measured provider boundaries for the shipped qwen-zimage curve - OpenAI detected at 0.06 and clean from 0.08, Gemini detected at 0.08 and clean from 0.10 - together with the two low-resolution Gemini verdicts that explain why the curve's sub-1 MP rungs are not under-driven despite looking short against a boundary measured at 4.33 MP. The curve is left unchanged; nothing measured fails. The profile is not deployed and not production-ready: every verdict so far comes from one fixture and one seed. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
Victor KuznetsovandClaude Opus 5
|
39523aba09 |
Serve the static prompt embeddings from a persistent cache
Both qwen-zimage stages prompt with module constants, and at CFG 1.0 DiffSynth's PipelineUnitRunner reuses the positive embedding for the negative side rather than encoding it, so exactly one embedding per stage is ever computed. Persist it and neither text encoder has to be loaded at all. Measured on an H100 volume: this drops 15.45 GiB (Qwen2.5-VL) and 7.49 GiB (Z-Image) of an 87.6 GiB per-request read, worth a median 11.76 s and 4.10 s of load time paired within five containers. A nine-face fixture returned sha256 c8567e11077de32a both with and without the cache, so the output is byte-identical and the provider-oracle clearance is untouched. The cache key carries the cache version, model id, pipeline output params and the exact prompt, so a model bump or a prompt edit recomputes instead of reading a stale embedding. The write is atomic because a torn file must never read back as a hit, and a miss after the text encoder was already dropped raises rather than calling a model that is not loaded. _model_cache_dir now prefers HF_HOME: on a scale-to-zero runner that is the only persistently mounted path, so anything below it is re-derived every request. The YuNet download follows the same root. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
Victor KuznetsovandClaude Opus 5
|
36e3743289 |
Keep the qwen-zimage global stack resident on a card that can hold it
Port of the same change made on the v0.20.1 line, reapplied here because the package layout moved under _internal/ in the meantime. The mandatory Qwen stack was configured to offload to disk unconditionally. DiffSynth implements that by dropping the weights to the meta device and re-reading every parameter through its DiskMap on the next onload, and the pipeline moves between text encoder, transformer and VAE on every pass, so each generation paid a full model reload. That is the right trade on a consumer card, where it is what makes a 20B model runnable at all, and pure waste on a card that can simply hold the stack. Residency is now resolved from total VRAM, mirroring how the optional Z-Image face stack is already gated. Above the floor the config passes no "disk" value anywhere, which is what actually disables the behavior: DiffSynth latches disk_offload once from offload_dtype, so pointing every device at CUDA while leaving the sentinel would keep both the meta-drop and the re-read. Measured on an H100: a warm global pass went from 37.3s at 0.8 GiB resident to 2.2s at 28.7 GiB, with both stacks resident peaking at 48.0 GiB of 79.2. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> |
||
|
Victor Kuznetsov
|
a6c0c1c6f0 | Rewrite internal watermark pipeline and preserve behavior |