[bug]: Flux.2 Klein Img2Img Posterization

### Is there an existing issue for this problem?

- [x] I have searched the existing issues

### Install method

Invoke's Launcher

### Operating system

Windows

### GPU vendor

Nvidia (CUDA)

### GPU model

RTX 4070

### GPU VRAM

12GB

### Version number

v6.12.0rc1

### Browser

Chrome

### System Information

{
"version": "6.12.0rc1",
"dependencies": {
"absl-py" : "2.4.0",
"accelerate" : "1.13.0",
"annotated-types" : "0.7.0",
"anyio" : "4.12.1",
"attrs" : "25.4.0",
"bcrypt" : "3.2.2",
"bidict" : "0.23.1",
"bitsandbytes" : "0.49.2",
"blake3" : "1.0.8",
"certifi" : "2022.12.7",
"cffi" : "2.0.0",
"charset-normalizer" : "2.1.1",
"click" : "8.3.1",
"colorama" : "0.4.6",
"coloredlogs" : "15.0.1",
"compel" : "2.1.1",
"contourpy" : "1.3.3",
"cryptography" : "46.0.5",
"CUDA" : "12.8",
"cycler" : "0.12.1",
"Deprecated" : "1.3.1",
"diffusers" : "0.36.0",
"dnspython" : "2.8.0",
"dynamicprompts" : "0.31.0",
"ecdsa" : "0.19.1",
"einops" : "0.8.2",
"email-validator" : "2.3.0",
"fastapi" : "0.118.3",
"fastapi-events" : "0.12.2",
"filelock" : "3.20.0",
"flatbuffers" : "25.12.19",
"fonttools" : "4.62.0",
"fsspec" : "2025.12.0",
"gguf" : "0.18.0",
"h11" : "0.16.0",
"httpcore" : "1.0.9",
"httptools" : "0.7.1",
"httpx" : "0.28.1",
"huggingface_hub" : "0.36.2",
"humanfriendly" : "10.0",
"idna" : "3.4",
"importlib_metadata" : "7.1.0",
"invisible-watermark" : "0.2.0",
"InvokeAI" : "6.12.0rc1",
"jax" : "0.7.1",
"jaxlib" : "0.7.1",
"Jinja2" : "3.1.6",
"kiwisolver" : "1.5.0",
"MarkupSafe" : "3.0.2",
"matplotlib" : "3.10.8",
"mediapipe" : "0.10.14",
"ml_dtypes" : "0.5.4",
"mpmath" : "1.3.0",
"networkx" : "3.6.1",
"numpy" : "1.26.4",
"onnx" : "1.16.1",
"onnxruntime" : "1.19.2",
"opencv-contrib-python": "4.11.0.86",
"opencv-python" : "4.11.0.86",
"opt_einsum" : "3.4.0",
"packaging" : "24.1",
"passlib" : "1.7.4",
"picklescan" : "1.0.4",
"pillow" : "12.0.0",
"prompt_toolkit" : "3.0.52",
"protobuf" : "4.25.8",
"psutil" : "7.2.2",
"pyasn1" : "0.6.2",
"pycparser" : "3.0",
"pydantic" : "2.12.5",
"pydantic-settings" : "2.13.1",
"pydantic_core" : "2.41.5",
"pyparsing" : "3.3.2",
"PyPatchMatch" : "1.0.2",
"pyreadline3" : "3.5.4",
"python-dateutil" : "2.9.0.post0",
"python-dotenv" : "1.2.2",
"python-engineio" : "4.13.1",
"python-jose" : "3.5.0",
"python-multipart" : "0.0.22",
"python-socketio" : "5.16.1",
"PyWavelets" : "1.9.0",
"PyYAML" : "6.0.3",
"regex" : "2026.2.28",
"requests" : "2.28.1",
"rsa" : "4.9.1",
"safetensors" : "0.7.0",
"scipy" : "1.17.1",
"semver" : "3.0.4",
"sentencepiece" : "0.2.0",
"setuptools" : "70.2.0",
"simple-websocket" : "1.1.0",
"six" : "1.17.0",
"sniffio" : "1.3.1",
"sounddevice" : "0.5.5",
"spandrel" : "0.4.2",
"starlette" : "0.48.0",
"sympy" : "1.14.0",
"tokenizers" : "0.22.2",
"torch" : "2.7.1+cu128",
"torchsde" : "0.2.6",
"torchvision" : "0.22.1+cu128",
"tqdm" : "4.66.5",
"trampoline" : "0.1.2",
"transformers" : "4.57.6",
"typing-inspection" : "0.4.2",
"typing_extensions" : "4.15.0",
"urllib3" : "1.26.13",
"uvicorn" : "0.41.0",
"watchfiles" : "1.1.1",
"wcwidth" : "0.6.0",
"websockets" : "16.0",
"wrapt" : "2.1.2",
"wsproto" : "1.3.2",
"zipp" : "3.19.2"
},
"config": {
"schema_version": "4.0.2",
"legacy_models_yaml_path": null,
"host": "127.0.0.1",
"port": 9090,
"allow_origins": [],
"allow_credentials": true,
"allow_methods": ["*"],
"allow_headers": ["*"],
"ssl_certfile": null,
"ssl_keyfile": null,
"log_tokenization": false,
"patchmatch": true,
"models_dir": "models",
"convert_cache_dir": "models\\.convert_cache",
"download_cache_dir": "models\\.download_cache",
"legacy_conf_dir": "configs",
"db_dir": "databases",
"outputs_dir": "outputs",
"custom_nodes_dir": "nodes",
"style_presets_dir": "style_presets",
"workflow_thumbnails_dir": "workflow_thumbnails",
"log_handlers": ["console"],
"log_format": "color",
"log_level": "info",
"log_sql": false,
"log_level_network": "warning",
"use_memory_db": false,
"dev_reload": false,
"profile_graphs": false,
"profile_prefix": null,
"profiles_dir": "profiles",
"max_cache_ram_gb": null,
"max_cache_vram_gb": null,
"log_memory_usage": false,
"model_cache_keep_alive_min": 0,
"device_working_mem_gb": 3,
"enable_partial_loading": true,
"keep_ram_copy_of_weights": true,
"ram": null,
"vram": null,
"lazy_offload": true,
"pytorch_cuda_alloc_conf": null,
"device": "auto",
"precision": "auto",
"sequential_guidance": false,
"attention_type": "auto",
"attention_slice_size": "auto",
"force_tiled_decode": false,
"pil_compress_level": 1,
"max_queue_size": 10000,
"clear_queue_on_startup": false,
"allow_nodes": null,
"deny_nodes": null,
"node_cache_size": 512,
"hashing_algorithm": "blake3_single",
"remote_api_tokens": [ {"url_regex": "huggingface\\.co|hf\\.co", "token": "REDACTED"} ],
"scan_models_on_startup": false,
"unsafe_disable_picklescan": false,
"allow_unknown_models": true,
"multiuser": false
},
"set_config_fields": ["enable_partial_loading", "legacy_models_yaml_path", "remote_api_tokens"]
}

### What happened

img2img using Flux.2 Klein results in posterization of the image, particularly obvious with photorealism images. The greater the level of denoise, the more "posterization" occurs.

The images attached show:

InvokeA.png - Reference image generated with Flux.2 Klein in Invoke. (Good)
ComfyA.png - An img2img generation in ComfyUI proving it's not a fault of the model. (Good)
InvokeB.png - An img2img generation in Invoke showing significant posterization. (Bad)

Photorealism image generation with Flux.2 Klein in Invoke is excellent, so it's not inherent to the model. It only occurs when applying denoise to an existing raster layer.

### What you expected to happen

I expected a result similar to the ComfyUI result. A photorealistic image with lots of fine detail.

### How to reproduce the problem

- Load Flux.2 Klein.
- Create a new raster layer with a photographic image.
- Increase the denoise setting to around 5+ (the more denoise the worse it gets)
- Hit Invoke.

### Additional context

It's more obvious on photographic images.
It seems to be more obvious with brighter images (in my testing)

### Discord username

Buttered_Both_Sides