mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-06-05 10:38:00 +02:00
Victor Kuznetsov
d90d5d886a
Add `--pipeline controlnet` (SDXL base + xinsir canny ControlNet via StableDiffusionXLControlNetImg2ImgPipeline): the canny edge map conditions the img2img regeneration so text and face STRUCTURE stay sharp, while the watermark is still removed by the regeneration (`strength`) -- no original pixels are copied or frozen, so SynthID does not survive. Oracle-verified clean on OpenAI with better text/structure fidelity than plain img2img at equal strength. `--controlnet-scale` tunes structure preservation; fp32 on mps/cpu (fp16-fixed VAE on cuda/xpu). Shares the img2img runner (live progress + MPS->CPU fallback) and the fp16-VAE-fix / device-move helpers with the default pipeline. Remove the superseded subsystems -- ctrlregen (SD1.5 clean-noise), text-protection (differential / region-hires) and face-protection: they either destroyed real content or shielded the watermark by re-using original pixels. controlnet replaces them by regenerating everything under edge conditioning. Canny preserves face structure but not identity; face IDENTITY is a separate face-restoration post-pass (CodeFormer/GFPGAN), researched + prototyped but not yet shipped. An IP-Adapter FaceID attempt was built and removed (footgun: needs high strength, corrupts faces at removal strength). Docs: docs/controlnet-removal-pipeline-research.md, scripts/controlnet_sweep.py. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
74 lines
2.9 KiB
Python
74 lines
2.9 KiB
Python
"""Tests for the invisible watermark engine (unit tests, no GPU required)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from remove_ai_watermarks.invisible_engine import InvisibleEngine, _target_size, is_available
|
|
|
|
|
|
class TestIsAvailable:
|
|
"""Tests for dependency checking."""
|
|
|
|
def test_returns_bool(self):
|
|
result = is_available()
|
|
assert isinstance(result, bool)
|
|
|
|
def test_available_reflects_dependencies(self):
|
|
"""is_available() is True iff torch + diffusers (the gpu extra) import.
|
|
|
|
Must not assume the full stack: the core+dev CI env has no diffusers.
|
|
"""
|
|
import importlib.util
|
|
|
|
expected = all(importlib.util.find_spec(m) is not None for m in ("torch", "diffusers"))
|
|
assert is_available() is expected
|
|
|
|
|
|
class TestInvisibleEngineInit:
|
|
"""Tests for InvisibleEngine construction (no GPU required)."""
|
|
|
|
def test_default_model_id(self):
|
|
# SDXL base became the default in May 2026 (defeats SynthID v2).
|
|
assert InvisibleEngine.DEFAULT_MODEL_ID == "stabilityai/stable-diffusion-xl-base-1.0"
|
|
|
|
|
|
class TestTargetSize:
|
|
"""Regression guard for the native-resolution decision (issues #10 / #15).
|
|
|
|
max_resolution=0 must NOT downscale -- the forced downscale->upscale
|
|
round-trip was the quality loss in #10, and downscaling at all let SynthID
|
|
survive in #15 (the native SDXL pass at strength ~0.05 is what defeats it).
|
|
"""
|
|
|
|
def test_native_default_no_downscale(self):
|
|
# The default (0) means native resolution: no resize, regardless of size.
|
|
assert _target_size(4096, 4096, 0) is None
|
|
assert _target_size(123, 456, 0) is None
|
|
|
|
def test_negative_cap_treated_as_native(self):
|
|
assert _target_size(4096, 4096, -1) is None
|
|
|
|
def test_cap_below_long_side_downscales(self):
|
|
# 2000x1000, cap 1024 -> long side scaled to 1024, aspect preserved.
|
|
assert _target_size(2000, 1000, 1024) == (1024, 512)
|
|
|
|
def test_cap_uses_long_side_for_portrait(self):
|
|
# Portrait: height is the long side, so it drives the ratio.
|
|
assert _target_size(1000, 2000, 1024) == (512, 1024)
|
|
|
|
def test_cap_at_or_above_long_side_no_downscale(self):
|
|
# Already within the cap (and exactly equal) -> no resize.
|
|
assert _target_size(800, 600, 1024) is None
|
|
assert _target_size(1024, 768, 1024) is None
|
|
|
|
def test_integer_truncation_matches_pil_call_site(self):
|
|
# 1254x1254 (the gpt-image sample) capped at 1000: int(1254*1000/1254)=1000.
|
|
assert _target_size(1254, 1254, 1000) == (1000, 1000)
|
|
# Non-divisible ratio truncates toward zero like int() at the call site.
|
|
assert _target_size(1000, 333, 500) == (500, 166)
|
|
|
|
def test_extreme_aspect_ratio_clamps_short_side_to_one(self):
|
|
# 5000x3 capped at 1024: int(3 * 1024/5000) = 0 would crash resize();
|
|
# the short side must clamp to 1, never 0.
|
|
assert _target_size(5000, 3, 1024) == (1024, 1)
|
|
assert _target_size(3, 5000, 1024) == (1, 1024)
|