Skip to content

[bug]: InvokeAI v6.14.0-RC1 Crashed while generating Krea-2 Image #9444

Open
#9469
Open
[bug]: InvokeAI v6.14.0-RC1 Crashed while generating Krea-2 Image#9444
#9469
Assignees
Pfannkuchensack
Labels
bugSomething isn't working

Description

@NiceDragon8066
NiceDragon8066
opened on Aug 2, 2026

Is there an existing issue for this problem?

  • I have searched the existing issues

Install method

Invoke's Launcher

Operating system

Windows

GPU vendor

Nvidia (CUDA)

GPU model

RTX 590 Laptop GPU

GPU VRAM

24GB

Version number

v6.14.0 RC1

Browser

Edge

System Information

{
"version": "6.14.0-rc1",
"dependencies": {
"absl-py" : "2.5.0",
"accelerate" : "1.14.0",
"annotated-doc" : "0.0.5",
"annotated-types" : "0.8.0",
"anyio" : "4.14.2",
"argon2-cffi" : "25.1.0",
"argon2-cffi-bindings" : "25.1.0",
"arrow" : "1.4.0",
"asttokens" : "3.0.2",
"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" : "0.50.0",
"blake3" : "1.0.9",
"bleach" : "6.4.0",
"certifi" : "2022.12.7",
"cffi" : "2.1.0",
"charset-normalizer" : "2.1.1",
"click" : "8.4.2",
"colorama" : "0.4.6",
"coloredlogs" : "15.0.1",
"comm" : "0.2.3",
"compel" : "2.4.0",
"contourpy" : "1.3.3",
"cryptography" : "50.0.0",
"CUDA" : "12.8",
"cycler" : "0.12.1",
"debugpy" : "1.8.21",
"decorator" : "5.3.1",
"defusedxml" : "0.7.1",
"Deprecated" : "1.3.1",
"diffusers" : "0.39.0",
"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" : "2.22.1",
"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" : "1.5.2",
"httpcore" : "1.0.9",
"httptools" : "0.8.0",
"httpx" : "0.28.1",
"huggingface_hub" : "1.26.0",
"humanfriendly" : "10.0",
"idna" : "3.4",
"ImageIO" : "2.37.4",
"imageio-ffmpeg" : "0.6.0",
"importlib_metadata" : "7.1.0",
"InvokeAI" : "6.14.0rc1",
"ipykernel" : "7.3.0",
"ipython" : "9.16.0",
"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" : "3.11.1",
"matplotlib-inline" : "0.2.2",
"mdurl" : "0.1.2",
"mediapipe" : "0.10.14",
"mistune" : "3.3.4",
"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",
"picklescan" : "1.0.5",
"pillow" : "12.2.0",
"platformdirs" : "4.11.0",
"prometheus_client" : "0.26.0",
"prompt_toolkit" : "3.0.53",
"protobuf" : "4.25.9",
"psutil" : "7.2.2",
"pure_eval" : "0.2.3",
"pyasn1" : "0.6.4",
"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",
"pyreadline3" : "3.5.6",
"python-dateutil" : "2.9.0.post0",
"python-dotenv" : "1.2.2",
"python-engineio" : "4.13.4",
"python-jose" : "3.5.0",
"python-json-logger" : "4.1.0",
"python-multipart" : "0.0.32",
"python-socketio" : "5.16.3",
"PyWavelets" : "1.9.0",
"pywinpty" : "3.0.5",
"PyYAML" : "6.0.3",
"pyzmq" : "27.1.0",
"referencing" : "0.37.0",
"regex" : "2026.7.19",
"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" : "78.1.0",
"shellingham" : "1.5.4",
"simple-websocket" : "1.1.0",
"six" : "1.17.0",
"sounddevice" : "0.5.5",
"soupsieve" : "2.9.1",
"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" : "2.11.0+cu128",
"torchsde" : "0.2.6",
"torchvision" : "0.26.0+cu128",
"tornado" : "6.5.7",
"tqdm" : "4.66.5",
"traitlets" : "5.16.0",
"trampoline" : "0.1.2",
"transformers" : "5.5.4",
"typer" : "0.27.0",
"typing-inspection" : "0.4.2",
"typing_extensions" : "4.15.0",
"tzdata" : "2026.3",
"uri-template" : "1.3.0",
"urllib3" : "1.26.13",
"uvicorn" : "0.52.1",
"watchfiles" : "1.2.0",
"wcwidth" : "0.8.2",
"webcolors" : "25.10.0",
"webencodings" : "0.5.1",
"websocket-client" : "1.9.0",
"websockets" : "17.0.1",
"wrapt" : "2.3.0",
"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,
"base_url": null,
"forwarded_allow_ips": "127.0.0.1",
"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": "backend:cudaMallocAsync",
"device": "auto",
"generation_devices": "auto",
"offload_text_encoders_to_idle_gpus": true,
"precision": "auto",
"sequential_guidance": false,
"attention_type": "auto",
"attention_slice_size": "auto",
"force_tiled_decode": false,
"pil_compress_level": 1,
"max_queue_size": 10000,
"session_queue_mode": "round_robin",
"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": [ {"url_regex": "huggingface.co", "token": "**********"} ],
"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": ["remote_api_tokens", "legacy_models_yaml_path", "pytorch_cuda_alloc_conf"]
}

What happened

I was testing the new 6,14.0-RC-1 version Krea-2 implementation. InvokeAI crashed while generating an image with Krea-2 Kreamania_Variant-5_Int8-Convrot.safetensors checkpoint (TE: Qwen3-VL-4B-Instruct-Herectic.safetensors, VAE: Krea2RealVAE_v10.safetensors), resolution:1024x1536, cfg 1, steps 10. It was able to generate an image at 1024x1024 and 768x1024 resolutions using both Int8-Convrot and Q4KM-GGUF versions of Kreamania. But failed at the higher resolution. Also, the resolution slider needs to be expanded to 2048x2048 or higher for modern models such as Krea-2 and Ideogram; right now, it is limited to 1536x1536 only.

Additional observation - With the Int8-Convrot model, the InvokeAI app seemed to struggle a lot (even at the lower resolution) - it filled up my computer's full 64GB RAM, then paged to the SSD, and then while running the transformer, it consumed 21GB VRAM! The GGUF executed with much less overhead, but the output quality was absolutely horrible. Please investigate ComfyUI's and Wan2GP's implementation of int8-convrot and gguf for Krea2, it works smoothly on those platforms with excellent quality output.

Hopefully, these issues will get solved before the stable release. I will now move on to testing image generation with the Ideogram model. For that one I would suggest implementing an automated prompt generator with json and bounding boxes output.

What you expected to happen

Expected it to work without crashing.

How to reproduce the problem

idk

Additional context

Console log:
Preparing first run of this install - may take a minute or two...
Started Invoke process with PID 15944
[2026-08-02 18:47:14,098]::[InvokeAI]::INFO --> PyTorch CUDA memory allocator: cudaMallocAsync
W0802 18:47:16.563000 12760 Lib\site-packages\torch\utils\flop_counter.py:29] triton not found; flop co
unting will not work for triton kernels
[2026-08-02 18:47:28,010]::[InvokeAI]::INFO --> Using torch device: NVIDIA GeForce RTX 5090 Laptop GPU
[2026-08-02 18:47:29,047]::[InvokeAI]::INFO --> cuDNN version: 91900
[2026-08-02 18:47:34,210]::[InvokeAI]::INFO --> Patchmatch initialized
[2026-08-02 18:47:35,638]::[InvokeAI]::INFO --> InvokeAI version 6.14.0-rc1
[2026-08-02 18:47:35,638]::[InvokeAI]::INFO --> Root directory = C:\Users\vidz3\Invoke
[2026-08-02 18:47:35,641]::[InvokeAI]::INFO --> Initializing database at C:\Users\vidz3\Invoke\database
s\invokeai.db
[2026-08-02 18:47:35,681]::[InvokeAI]::INFO --> Backing up database to C:\Users\vidz3\Invoke\databases
invokeai_backup_20260802-184735.db
[2026-08-02 18:47:35,848]::[InvokeAI]::INFO --> Database update needed
[2026-08-02 18:47:35,935]::[InvokeAI]::INFO --> Database updated successfully
[2026-08-02 18:47:35,935]::[InvokeAI]::INFO --> JWT secret loaded from database
[2026-08-02 18:47:36,062]::[ModelManagerService]::INFO --> [MODEL CACHE] Calculated model RAM cache siz
e: 21390.56 MB. Heuristics applied: [1, 2].
[2026-08-02 18:47:36,063]::[ModelManagerService]::INFO --> Model cache global RAM budget: 20.89 GB acro
ss 1 device cache(s).
[2026-08-02 18:47:36,114]::[ModelInstallService]::INFO --> Restoring incomplete installs
[2026-08-02 18:47:36,114]::[ModelInstallService]::INFO --> Finished restoring incomplete installs
[2026-08-02 18:47:36,440]::[InvokeAI]::INFO --> Invoke running on http://127.0.0.1:9090 (Press CTRL+C t
o quit)
[2026-08-02 18:49:11,742]::[InvokeAI]::INFO --> Deleted model: 4f9569e1-3e1a-4b1f-b976-daec5e0eebe0
[2026-08-02 18:49:17,557]::[InvokeAI]::INFO --> Deleted model: 833baf48-021e-4495-b033-5b9c27e1a498
[2026-08-02 18:49:32,415]::[InvokeAI]::INFO --> Deleted model: 918e685d-7c7a-4d4d-a6e7-69a049e360f9
[2026-08-02 18:50:01,350]::[InvokeAI]::INFO --> Deleted model: 6110d932-3d22-42ff-b41b-5ac836b47fff
[2026-08-02 18:50:40,108]::[InvokeAI]::INFO --> Deleted model: 97c8162e-a0e3-4d4f-bc74-aeeaba0e8665
[2026-08-02 18:52:19,222]::[InvokeAI]::INFO --> Deleted model: 6c381b9c-a549-494d-9a36-a78d6690d791
[2026-08-02 18:52:56,655]::[InvokeAI]::INFO --> Deleted model: ff23361a-499f-4ba4-866d-071cf1da2752
[2026-08-02 18:54:41,048]::[InvokeAI]::INFO --> Deleted model: 05d634aa-e893-407e-b5a5-422002e10b1f
[2026-08-02 18:57:31,622]::[InvokeAI]::INFO --> Started installation of "D:\ModelSpace\vae\krea2RealVae
_v10.safetensors"
[2026-08-02 18:57:31,623]::[ModelInstallService]::INFO --> Model install started: D:/ModelSpace/vae/kre
a2RealVae_v10.safetensors
Hashing krea2RealVae_v10.safetensors: 100%|███████████████████████████| 1/1 [00:00<00:00, 1.75file/s]
[2026-08-02 18:57:32,221]::[ModelInstallService]::INFO --> Model install complete: D:/ModelSpace/vae/kr
ea2RealVae_v10.safetensors
[2026-08-02 18:58:45,887]::[InvokeAI]::INFO --> Started installation of "D:\ModelSpace\vae\Qwen_Image_V
AE_ImprovedLiquid1127\qwenimagevae_liquid1127_v10.safetensors"
[2026-08-02 18:58:45,887]::[ModelInstallService]::INFO --> Model install started: D:/ModelSpace/vae/Qwe
n_Image_VAE_ImprovedLiquid1127/qwenimagevae_liquid1127_v10.safetensors
Hashing qwenimagevae_liquid1127_v10.safetensors: 100%|████████████████| 1/1 [00:00<00:00, 3.30file/s]
[2026-08-02 18:58:46,202]::[ModelInstallService]::INFO --> Model install complete: D:/ModelSpace/vae/Qw
en_Image_VAE_ImprovedLiquid1127/qwenimagevae_liquid1127_v10.safetensors
[2026-08-02 19:00:07,539]::[InvokeAI]::INFO --> Started installation of "D:\ModelSpace\vae\Qwen_BetterV
AE\Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors"
[2026-08-02 19:00:07,539]::[ModelInstallService]::INFO --> Model install started: D:/ModelSpace/vae/Qwe
n_BetterVAE/Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors
Hashing Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors: 100%|█████| 1/1 [00:00<00:00, 2.05file/s]
[2026-08-02 19:00:08,048]::[ModelInstallService]::INFO --> Model install complete: D:/ModelSpace/vae/Qw
en_BetterVAE/Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors
[2026-08-02 19:01:19,959]::[InvokeAI]::INFO --> Started installation of "D:\ModelSpace\text_encoders\Qw
en3-VL-4B_Instruct_Heretic_Encoder\qwen3VLInstruct4bHeretic_v10.safetensors"
[2026-08-02 19:01:19,960]::[ModelInstallService]::INFO --> Model install started: D:/ModelSpace/text_en
coders/Qwen3-VL-4B_Instruct_Heretic_Encoder/qwen3VLInstruct4bHeretic_v10.safetensors
Hashing qwen3VLInstruct4bHeretic_v10.safetensors: 100%|███████████████| 1/1 [00:04<00:00, 4.58s/file]
[2026-08-02 19:01:24,861]::[ModelInstallService]::INFO --> Model install complete: D:/ModelSpace/text_e
ncoders/Qwen3-VL-4B_Instruct_Heretic_Encoder/qwen3VLInstruct4bHeretic_v10.safetensors
[2026-08-02 19:02:36,880]::[InvokeAI]::INFO --> Started installation of "D:\ModelSpace\checkpoints_repo
\Krea-2\Krea2_Kreamania_Int8Convrot_GGUF\kreamania_variant5_int8convrot.safetensors"
[2026-08-02 19:02:36,881]::[ModelInstallService]::INFO --> Model install started: D:/ModelSpace/checkpo
ints_repo/Krea-2/Krea2_Kreamania_Int8Convrot_GGUF/kreamania_variant5_int8convrot.safetensors
Hashing kreamania_variant5_int8convrot.safetensors: 100%|█████████████| 1/1 [00:11<00:00, 11.38s/file]
[2026-08-02 19:02:48,422]::[ModelInstallService]::INFO --> Model install complete: D:/ModelSpace/checkp
oints_repo/Krea-2/Krea2_Kreamania_Int8Convrot_GGUF/kreamania_variant5_int8convrot.safetensors
[2026-08-02 19:07:10,599]::[InvokeAI]::INFO --> Executing queue item 1320, session dc3a26a5-8f01-498c-b
033-7c0651c37153 on cuda:0
config.json: 100%|███████████████████████████████████████████████████████| 1.50k/1.50k [00:00<?, ?B/s]
tokenizer_config.json: 100%|█████████████████████████████████████| 10.9k/10.9k [00:00<00:00, 14.5MB/s]
vocab.json: 100%|████████████████████████████████████████████████| 2.78M/2.78M [00:00<00:00, 3.57MB/s]
merges.txt: 100%|████████████████████████████████████████████████| 1.67M/1.67M [00:00<00:00, 2.64MB/s]
tokenizer.json: 100%|████████████████████████████████████████████| 7.03M/7.03M [00:01<00:00, 4.71MB/s]
[2026-08-02 19:07:32,072]::[ModelLoadService]::INFO --> FP8 layerwise casting enabled for Qwen3-VL enco
der 'qwen3VLInstruct4bHeretic_v10' (storage=float8_e4m3fn, compute=torch.bfloat16).
[2026-08-02 19:07:32,099]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'a3299f33-c0db-4d
ed-92f1-bb41f3e6c959:tokenizer' (Qwen2Tokenizer) onto cuda device #0 in 0.00s. Total model size: 0.00MB
, VRAM: 0.00MB (0.0%)
[2026-08-02 19:07:32,932]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'a3299f33-c0db-4d
ed-92f1-bb41f3e6c959:text_encoder' (Qwen3VLModel) onto cuda device #0 in 0.83s. Total model size: 4236.
29MB, VRAM: 4236.29MB (100.0%)
[2026-08-02 19:10:03,768]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '4cb0e15e-6ae0-47
83-91bb-a437d0ad0830:transformer' (Krea2Transformer2DModel) onto cuda device #0 in 12.43s. Total model
size: 24452.35MB, VRAM: 19328.35MB (79.0%)
0%| | 0/10 [00:00<?, ?it/s]C
:\Users\vidz3\Invoke.venv\Lib\site-packages\torch\nn\functional.py:2954: UserWarning: Mismatch dtype b
etween input and weight: input dtype = float, weight dtype = struct c10::BFloat16, Cannot dispatch to f
used implementation. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\pytorch\aten\src
ATen\native\layer_norm.cpp:347.)
return torch.rms_norm(input, normalized_shape, weight, eps)
100%|█████████████████████████████████████████████████████████████████| 10/10 [00:29<00:00, 2.93s/it]
C:\Users\vidz3\Invoke.venv\Lib\site-packages\huggingface_hub\utils_validators.py:205: UserWarning: Th
e local_dir_use_symlinks argument is deprecated and ignored in hf_hub_download. Downloading to a lo
cal directory does not use symlinks anymore.
warnings.warn(
config.json: 100%|███████████████████████████████████████████████████████████| 724/724 [00:00<?, ?B/s]
There are modules in AutoencoderKLWan that should be kept in float32: []. Casting directly with to()
can lead to inconsistent results; set torch_dtype in from_pretrained() instead to keep these module
s in float32.
[2026-08-02 19:10:37,073]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '91b5d698-d9fc-43
f2-8df3-1970ca1fb872:vae' (AutoencoderKLWan) onto cuda device #0 in 0.06s. Total model size: 242.03MB,
VRAM: 242.03MB (100.0%)
[2026-08-02 19:10:38,565]::[InvokeAI]::INFO --> Graph stats: dc3a26a5-8f01-498c-b033-7c0651c37153
Node Calls Seconds VRAM Change
krea2_model_loader 1 0.014s +0.000G
integer 1 0.000s +0.000G
string 1 0.000s +0.000G
core_metadata 1 0.000s +0.000G
krea2_text_encoder 1 22.959s +4.145G
collect 1 0.001s +0.000G
krea2_denoise 1 181.662s -4.136G
qwen_image_l2i 1 3.171s +0.236G
TOTAL GRAPH EXECUTION TIME: 207.807s
TOTAL GRAPH WALL TIME: 207.811s
RAM used by InvokeAI process: 32.21G (+31.182G)
RAM used to load models: 28.25G
VRAM in use: 0.245G
RAM cache statistics:
Model cache hits: 4
Model cache misses: 8
Models cached: 1
Models cleared from cache: 2
Cache high water mark: 23.88/20.89G

[2026-08-02 19:11:37,011]::[InvokeAI]::INFO --> Started installation of "D:\ModelSpace\checkpoints_repo
\Krea-2\Krea2_Kreamania_Int8Convrot_GGUF\kreamania_V4_Q4GGUF_v10.gguf"
[2026-08-02 19:11:37,011]::[ModelInstallService]::INFO --> Model install started: D:/ModelSpace/checkpo
ints_repo/Krea-2/Krea2_Kreamania_Int8Convrot_GGUF/kreamania_V4_Q4GGUF_v10.gguf
Hashing kreamania_V4_Q4GGUF_v10.gguf: 100%|███████████████████████████| 1/1 [00:07<00:00, 7.46s/file]
[2026-08-02 19:11:52,370]::[ModelInstallService]::INFO --> Model install complete: D:/ModelSpace/checkp
oints_repo/Krea-2/Krea2_Kreamania_Int8Convrot_GGUF/kreamania_V4_Q4GGUF_v10.gguf
[2026-08-02 19:12:58,705]::[InvokeAI]::INFO --> Executing queue item 1321, session 9dcb97a2-9eb1-4eb7-8
ea5-3fd1104df21b on cuda:0
[2026-08-02 19:13:09,171]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '4275f9ff-709c-4f
84-9ab0-860f964c5b15:transformer' (Krea2Transformer2DModel) onto cuda device #0 in 2.53s. Total model s
ize: 7926.85MB, VRAM: 7926.85MB (100.0%)
100%|█████████████████████████████████████████████████████████████████| 10/10 [00:21<00:00, 2.13s/it]
[2026-08-02 19:13:30,516]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '91b5d698-d9fc-43
f2-8df3-1970ca1fb872:vae' (AutoencoderKLWan) onto cuda device #0 in 0.02s. Total model size: 242.03MB,
VRAM: 242.03MB (100.0%)
[2026-08-02 19:13:30,908]::[InvokeAI]::INFO --> Graph stats: 9dcb97a2-9eb1-4eb7-8ea5-3fd1104df21b
Node Calls Seconds VRAM Change
krea2_model_loader 1 0.000s +0.000G
integer 1 0.000s +0.000G
string 1 0.013s +0.000G
core_metadata 1 0.000s +0.000G
krea2_text_encoder 1 0.000s +0.000G
collect 1 0.000s +0.000G
krea2_denoise 1 31.767s +7.741G
qwen_image_l2i 1 0.403s +0.000G
TOTAL GRAPH EXECUTION TIME: 32.184s
TOTAL GRAPH WALL TIME: 32.184s
RAM used by InvokeAI process: 37.79G (+7.791G)
RAM used to load models: 7.98G
VRAM in use: 7.986G
RAM cache statistics:
Model cache hits: 2
Model cache misses: 2
Models cached: 2
Models cleared from cache: 0
Cache high water mark: 7.98/20.89G

[2026-08-02 19:14:29,685]::[InvokeAI]::INFO --> Executing queue item 1322, session aae52695-fbfc-428f-a
ec0-d1e18a50a0b9 on cuda:0
[2026-08-02 19:17:10,913]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '4cb0e15e-6ae0-47
83-91bb-a437d0ad0830:transformer' (Krea2Transformer2DModel) onto cuda device #0 in 27.02s. Total model
size: 24452.35MB, VRAM: 19916.35MB (81.4%)
100%|█████████████████████████████████████████████████████████████████| 10/10 [00:23<00:00, 2.30s/it]
C:\Users\vidz3\Invoke.venv\Lib\site-packages\huggingface_hub\utils_validators.py:205: UserWarning: Th
e local_dir_use_symlinks argument is deprecated and ignored in hf_hub_download. Downloading to a lo
cal directory does not use symlinks anymore.
warnings.warn(
There are modules in AutoencoderKLWan that should be kept in float32: []. Casting directly with to()
can lead to inconsistent results; set torch_dtype in from_pretrained() instead to keep these module
s in float32.
[2026-08-02 19:17:37,289]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '91b5d698-d9fc-43
f2-8df3-1970ca1fb872:vae' (AutoencoderKLWan) onto cuda device #0 in 0.05s. Total model size: 242.03MB,
VRAM: 242.03MB (100.0%)
[2026-08-02 19:17:37,902]::[InvokeAI]::INFO --> Graph stats: aae52695-fbfc-428f-aec0-d1e18a50a0b9
Node Calls Seconds VRAM Change
krea2_model_loader 1 0.000s +0.000G
integer 1 0.000s +0.000G
string 1 0.015s +0.000G
core_metadata 1 0.000s +0.000G
krea2_text_encoder 1 0.001s +0.000G
collect 1 0.000s +0.000G
krea2_denoise 1 186.249s -7.977G
qwen_image_l2i 1 1.788s +0.236G
TOTAL GRAPH EXECUTION TIME: 188.054s
TOTAL GRAPH WALL TIME: 188.056s
RAM used by InvokeAI process: 18.68G (-19.114G)
RAM used to load models: 24.12G
VRAM in use: 0.245G
RAM cache statistics:
Model cache hits: 2
Model cache misses: 4
Models cached: 1
Models cleared from cache: 2
Cache high water mark: 23.88/20.89G

[2026-08-02 19:21:31,453]::[InvokeAI]::INFO --> Executing queue item 1323, session 47a97913-7f4e-48ff-8
0d6-b04cd6b9635d on cuda:0
[2026-08-02 19:21:43,074]::[ModelLoadService]::INFO --> FP8 layerwise casting enabled for Qwen3-VL enco
der 'qwen3VLInstruct4bHeretic_v10' (storage=float8_e4m3fn, compute=torch.bfloat16).
[2026-08-02 19:21:43,110]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'a3299f33-c0db-4d
ed-92f1-bb41f3e6c959:tokenizer' (Qwen2Tokenizer) onto cuda device #0 in 0.00s. Total model size: 0.00MB
, VRAM: 0.00MB (0.0%)
[2026-08-02 19:21:44,503]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'a3299f33-c0db-4d
ed-92f1-bb41f3e6c959:text_encoder' (Qwen3VLModel) onto cuda device #0 in 1.39s. Total model size: 4236.
29MB, VRAM: 4236.29MB (100.0%)
Invoke process exited with code 3221225786

Discord username

No response

Metadata

Metadata

Assignees

Labels

bugSomething isn't working

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions