[bug]: InvokeAI Crashes with I "Invoke" an image.

[Terry-Rose-Jr]

Is there an existing issue for this problem?

• I have searched the existing issues

Install method

Invoke's Launcher

Operating system

Linux

GPU vendor

AMD (ROCm)

GPU model

R9700 AI Pro

GPU VRAM

32GB

Version number

v6.13.5rc1

Browser

No response

System Information

{
"version": "6.13.5.rc1",
"dependencies": {
"absl-py" : "2.4.0",
"accelerate" : "1.14.0",
"annotated-doc" : "0.0.4",
"annotated-types" : "0.7.0",
"anyio" : "4.14.1",
"argon2-cffi" : "25.1.0",
"argon2-cffi-bindings" : "25.1.0",
"arrow" : "1.4.0",
"asttokens" : "3.0.1",
"async-lru" : "2.3.0",
"attrs" : "26.1.0",
"babel" : "2.18.0",
"bcrypt" : "3.2.2",
"beautifulsoup4" : "4.15.0",
"bidict" : "0.23.1",
"bitsandbytes" : "0.49.2",
"blake3" : "1.0.9",
"bleach" : "6.4.0",
"certifi" : "2022.12.7",
"cffi" : "2.0.0",
"charset-normalizer" : "2.1.1",
"click" : "8.4.2",
"coloredlogs" : "15.0.1",
"comm" : "0.2.3",
"compel" : "2.4.0",
"contourpy" : "1.3.3",
"cryptography" : "49.0.0",
"CUDA" : "N/A",
"cycler" : "0.12.1",
"debugpy" : "1.8.21",
"decorator" : "5.3.1",
"defusedxml" : "0.7.1",
"Deprecated" : "1.3.1",
"diffusers" : "0.37.0",
"dnspython" : "2.8.0",
"dynamicprompts" : "0.31.0",
"ecdsa" : "0.19.2",
"einops" : "0.8.2",
"email-validator" : "2.3.0",
"executing" : "2.2.1",
"fastapi" : "0.118.3",
"fastapi-events" : "0.12.2",
"fastjsonschema" : "2.21.2",
"filelock" : "3.29.0",
"flatbuffers" : "25.12.19",
"fonttools" : "4.63.0",
"fqdn" : "1.5.1",
"fsspec" : "2026.4.0",
"gguf" : "0.19.0",
"h11" : "0.16.0",
"hf-xet" : "1.5.1",
"httpcore" : "1.0.9",
"httptools" : "0.8.0",
"httpx" : "0.28.1",
"huggingface_hub" : "1.21.0",
"humanfriendly" : "10.0",
"idna" : "3.4",
"importlib_metadata" : "7.1.0",
"InvokeAI" : "6.13.5rc1",
"ipykernel" : "7.3.0",
"ipython" : "9.15.0",
"ipython_pygments_lexers" : "1.1.1",
"isoduration" : "20.11.0",
"jax" : "0.7.1",
"jaxlib" : "0.7.1",
"jedi" : "0.20.0",
"Jinja2" : "3.1.6",
"json5" : "0.15.0",
"jsonpointer" : "3.1.1",
"jsonschema" : "4.26.0",
"jsonschema-specifications": "2025.9.1",
"jupyter-events" : "0.12.1",
"jupyter-lsp" : "2.3.1",
"jupyter_client" : "8.9.1",
"jupyter_core" : "5.9.1",
"jupyter_server" : "2.20.0",
"jupyter_server_terminals" : "0.5.4",
"jupyterlab" : "4.1.6",
"jupyterlab_pygments" : "0.3.0",
"jupyterlab_server" : "2.24.0",
"kiwisolver" : "1.5.0",
"lark" : "1.3.1",
"markdown-it-py" : "4.2.0",
"MarkupSafe" : "3.0.3",
"matplotlib" : "3.11.0",
"matplotlib-inline" : "0.2.2",
"mdurl" : "0.1.2",
"mediapipe" : "0.10.14",
"mistune" : "3.3.2",
"ml_dtypes" : "0.5.4",
"mpmath" : "1.3.0",
"nbclient" : "0.11.0",
"nbconvert" : "7.17.1",
"nbformat" : "5.10.4",
"nest-asyncio2" : "1.7.2",
"networkx" : "3.6.1",
"notebook" : "7.1.3",
"notebook_shim" : "0.2.4",
"numpy" : "1.26.4",
"onnx" : "1.16.1",
"onnxruntime" : "1.19.2",
"opencv-contrib-python" : "4.11.0.86",
"opt_einsum" : "3.4.0",
"packaging" : "24.1",
"pandocfilters" : "1.5.1",
"parso" : "0.8.7",
"passlib" : "1.7.4",
"pexpect" : "4.9.0",
"picklescan" : "1.0.4",
"pillow" : "12.2.0",
"platformdirs" : "4.10.0",
"prometheus_client" : "0.25.0",
"prompt_toolkit" : "3.0.52",
"protobuf" : "4.25.9",
"psutil" : "7.2.2",
"ptyprocess" : "0.7.0",
"pure_eval" : "0.2.3",
"pyasn1" : "0.6.3",
"pycparser" : "3.0",
"pydantic" : "2.13.4",
"pydantic-settings" : "2.14.2",
"pydantic_core" : "2.46.4",
"Pygments" : "2.20.0",
"pyparsing" : "3.3.2",
"PyPatchMatch" : "1.0.2",
"python-dateutil" : "2.9.0.post0",
"python-dotenv" : "1.2.2",
"python-engineio" : "4.13.3",
"python-jose" : "3.5.0",
"python-json-logger" : "4.1.0",
"python-multipart" : "0.0.32",
"python-socketio" : "5.16.3",
"pytorch-triton-rocm" : "3.5.1",
"PyWavelets" : "1.9.0",
"PyYAML" : "6.0.3",
"pyzmq" : "27.1.0",
"referencing" : "0.37.0",
"regex" : "2026.6.28",
"requests" : "2.28.1",
"rfc3339-validator" : "0.1.4",
"rfc3986-validator" : "0.1.1",
"rfc3987-syntax" : "1.1.0",
"rich" : "15.0.0",
"rpds-py" : "2026.6.3",
"rsa" : "4.9.1",
"safetensors" : "0.8.0",
"scipy" : "1.17.1",
"semver" : "3.0.4",
"Send2Trash" : "2.1.0",
"sentencepiece" : "0.2.0",
"setuptools" : "70.2.0",
"shellingham" : "1.5.4",
"simple-websocket" : "1.1.0",
"six" : "1.17.0",
"sounddevice" : "0.5.5",
"soupsieve" : "2.8.4",
"spandrel" : "0.4.2",
"stack-data" : "0.6.3",
"starlette" : "0.48.0",
"sympy" : "1.14.0",
"terminado" : "0.18.1",
"tinycss2" : "1.5.1",
"tokenizers" : "0.22.2",
"torch" : "2.9.1+rocm6.3",
"torchsde" : "0.2.6",
"torchvision" : "0.24.1+rocm6.3",
"tornado" : "6.5.7",
"tqdm" : "4.66.5",
"traitlets" : "5.15.1",
"trampoline" : "0.1.2",
"transformers" : "5.5.4",
"typer" : "0.25.1",
"typing-inspection" : "0.4.2",
"typing_extensions" : "4.15.0",
"tzdata" : "2026.2",
"uri-template" : "1.3.0",
"urllib3" : "1.26.13",
"uvicorn" : "0.49.0",
"uvloop" : "0.22.1",
"watchfiles" : "1.2.0",
"wcwidth" : "0.8.2",
"webcolors" : "25.10.0",
"webencodings" : "0.5.1",
"websocket-client" : "1.9.0",
"websockets" : "16.0",
"wrapt" : "2.2.2",
"wsproto" : "1.3.2",
"zipp" : "3.19.2"
},
"config": {
"schema_version": "4.0.3",
"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",
"image_subfolder_strategy": "flat",
"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,
"max_queue_history": null,
"allow_nodes": null,
"deny_nodes": null,
"node_cache_size": 512,
"hashing_algorithm": "blake3_single",
"remote_api_tokens": null,
"scan_models_on_startup": false,
"unsafe_disable_picklescan": false,
"allow_unknown_models": true,
"multiuser": false,
"strict_password_checking": false,
"external_alibabacloud_api_key": null,
"external_alibabacloud_base_url": null,
"external_gemini_api_key": null,
"external_openai_api_key": null,
"external_gemini_base_url": null,
"external_openai_base_url": null,
"external_seedream_api_key": null,
"external_seedream_base_url": null
},
"set_config_fields": ["legacy_models_yaml_path"]
}

What happened

When i try to "invoke" the system crashes, also very very slow.. (slower than my older 3060 12GB GPU)

What you expected to happen

I expected a reasonable "invoke" speed, and no system crash

How to reproduce the problem

hit the "invoke" button: z image turbo, sdxl... system freezes up then black screen.

Additional context

No response

Discord username

No response

[volkkov]

Hit this same issue — the root cause was the missing null check before deserialization. Wrapping in a try/catch fixed it on our end.

[Terry-Rose-Jr]

I am not a programmer!! LOL... so you lost me there!! Thank You!... hopefully it will be a non issue in 6.14 (fingers crossed) I love this app and depend on it for some work... I will have to stick with my old GPU until its figured out!..

[michaelanderson01826-glitch]

Thank you for reporting this. Since you mentioned you aren't a programmer, I wanted to let you know that the team has identified a potential root cause related to a missing null check during deserialization. While we work on a permanent fix for a future release like v6.14, I understand you'll be sticking with your older GPU for now. We appreciate your patience and your support for the app.

…

On Tue, Jun 30, 2026, 4:53 PM Terry-Rose-Jr ***@***.***> wrote: *Terry-Rose-Jr* left a comment (invoke-ai/InvokeAI#9323) <#9323 (comment)> I am not a programmer!! LOL... so you lost me there!! Thank You!... hopefully it will be a non issue in 6.14 (fingers crossed) I love this app and depend on it for some work... I will have to stick with my old GPU until its figured out!.. — Reply to this email directly, view it on GitHub <#9323?email_source=notifications&email_token=B7HTEEJUZLD3G3ZMHVTLFOL5CQZGTA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTIOBUHAZDAOJVGQ4KM4TFMFZW63VKON2WE43DOJUWEZLEUVSXMZLOOSWGM33PORSXEX3DNRUWG2Y#issuecomment-4848209548>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/B7HTEEPKNOYH3DFTCXF25AT5CQZGTAVCNFSNUABFKJSXA33TNF2G64TZHM2TENJVHEZDSOJVHNEXG43VMU5TINZYGA3DIOBYHAY2C5QC> . Triage notifications, keep track of coding agent tasks and review pull requests on the go with GitHub Mobile for iOS <https://github.com/notifications/mobile/ios/B7HTEEOBPVSDLUNUAMZCWG35CQZGTA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTIOBUHAZDAOJVGQ4KM4TFMFZW63VKON2WE43DOJUWEZLEUVSXMZLOOSVGM33PORSXEX3JN5ZQ> and Android <https://github.com/notifications/mobile/android/B7HTEEIZK343GIW4RFVTYFL5CQZGTA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTIOBUHAZDAOJVGQ4KM4TFMFZW63VKON2WE43DOJUWEZLEUVSXMZLOOSXGM33PORSXEX3BNZSHE33JMQ>. Download it today! You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[fishd72]

@Terry-Rose-Jr As of right now, the default install for AMD uses ROCm 6.3 ... which is quite old and not really suitable for the newer RDNA 4 cards like the RX 9070XT on which your R9700 is based.

I've got a 9070XT and have been having a lot of success with SDXL models, I made a post on the Discord about how to set this up, but in case you don't have access I'll add it below:

In case it helps anyone else, here are my updated notes on installing Invoke on a Fedora workstation with an AMD RX9070 XT GPU, using the default open-source AMD drivers.

Install Invoke for AMD using the launcher as normal, then go into the Dev Console and run the following commands:
uv pip uninstall torch torchvision pytorch-triton-rocm to remove these older versions, followed by uv pip install torch==2.11.0 torchvision pytorch-triton-rocm --index-url https://download.pytorch.org/whl/rocm7.2 to install the ROCm7.2 versions, fixing Torch at 2.11 due to an issue I experience with 2.12.

Edit your invokeai.yaml and add the following settings (previously I used attention_type: sliced but setting this to torch-sdp sees an improvement from ~3.2it/s to ~4.5it/s with SDXL models):

attention_type: torch-sdp
force_tiled_decode: true

(I removed some other settings from my previous notes as they don't appear to make any difference to reliability or performance.)

Then, ensure you have the following environment variables set, I do this by modifying the app launcher within the KDE menu but YMMV:

PYTORCH_MIOPEN_SUGGEST_NHWC=0
MIOPEN_DEBUG_CONV_DIRECT_NAIVE_CONV_FWD=0
MIOPEN_FIND_MODE=FAST
PYTORCH_HIP_ALLOC_CONF=expandable_segments:True
TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1
TORCH_BLAS_PREFER_HIPBLASLT=1

PYTORCH_HIP_ALLOC_CONF doesn't appear to work correctly right now & there are some notes online about this being a Torch bug, hopefully resolved soon. The MIOPEN stuff was something I've read in a Github issue somewhere, & it greatly speeds up model loading in certain situations, especially when modifying the bounding box.

Finally, the important bit I forget to add is that you need to ensure that your models are set to FP16 VAE precision, and you may need the fixed 16-bit VAE as well (model dependant). You'll OOM without this.

Now, some of the above might not apply to you as you have a lot more VRAM than I do but try that and see if it helps. I'll be interested to hear how you get on with 16-bit VAE settings and using the newer models like Anima and Flux etc... as I cannot currently use these in Invoke due to limited VRAM.

[fishd72]

Also to note, despite the release notes for this RC stating that ROCm 7.1 has been implemented, it seems that the code for the Invoke Launcher hasn't been updated, so it's still installing the older ROCm 6.3 as before. I've just created an issue for that now.

[Terry-Rose-Jr]

Thank you!.. I dont know programming at all.. LOL!... Im more of a creative and hardware guy... I really need to learn.. but too busy at the moment. I really do appreciate this community.. you all actually listen!... I love this app and am willing to wait, Its worth it..!! Thanks again for listening and responding... you all are amazing people!