invoke-ai
[bug]: Unknown LORA Type
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 3080
GPU VRAM
10 GB
Version number
6.3.0
Browser
Chrome
System Information
{ "version": "6.3.0", "dependencies": { "absl-py" : "2.3.1", "accelerate" : "1.10.0", "annotated-types" : "0.7.0", "anyio" : "4.10.0", "attrs" : "25.3.0", "bidict" : "0.23.1", "bitsandbytes" : "0.46.1", "blake3" : "1.0.5", "certifi" : "2022.12.7", "cffi" : "1.17.1", "charset-normalizer" : "2.1.1", "click" : "8.2.1", "colorama" : "0.4.6", "coloredlogs" : "15.0.1", "compel" : "2.1.1", "contourpy" : "1.3.3", "CUDA" : "12.8", "cycler" : "0.12.1", "Deprecated" : "1.2.18", "diffusers" : "0.33.0", "dnspython" : "2.7.0", "dynamicprompts" : "0.31.0", "einops" : "0.8.1", "fastapi" : "0.116.1", "fastapi-events" : "0.12.2", "filelock" : "3.13.1", "flatbuffers" : "25.2.10", "fonttools" : "4.59.0", "fsspec" : "2024.6.1", "gguf" : "0.17.1", "h11" : "0.16.0", "httptools" : "0.6.4", "huggingface-hub" : "0.34.3", "humanfriendly" : "10.0", "idna" : "3.4", "importlib_metadata" : "7.1.0", "invisible-watermark" : "0.2.0", "InvokeAI" : "6.3.0", "jax" : "0.7.0", "jaxlib" : "0.7.0", "Jinja2" : "3.1.4", "kiwisolver" : "1.4.8", "MarkupSafe" : "2.1.5", "matplotlib" : "3.10.5", "mediapipe" : "0.10.14", "ml_dtypes" : "0.5.3", "mpmath" : "1.3.0", "networkx" : "3.3", "numpy" : "1.26.3", "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", "picklescan" : "0.0.26", "pillow" : "11.0.0", "prompt_toolkit" : "3.0.51", "protobuf" : "4.25.8", "psutil" : "7.0.0", "pycparser" : "2.22", "pydantic" : "2.11.7", "pydantic-settings" : "2.10.1", "pydantic_core" : "2.33.2", "pyparsing" : "3.2.3", "PyPatchMatch" : "1.0.2", "pyreadline3" : "3.5.4", "python-dateutil" : "2.9.0.post0", "python-dotenv" : "1.1.1", "python-engineio" : "4.12.2", "python-multipart" : "0.0.20", "python-socketio" : "5.13.0", "PyWavelets" : "1.9.0", "PyYAML" : "6.0.2", "regex" : "2025.7.34", "requests" : "2.28.1", "safetensors" : "0.6.1", "scipy" : "1.16.1", "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" : "0.5.2", "spandrel" : "0.4.1", "starlette" : "0.47.2", "sympy" : "1.13.3", "tokenizers" : "0.21.4", "torch" : "2.7.1+cu128", "torchsde" : "0.2.6", "torchvision" : "0.22.1+cu128", "tqdm" : "4.66.5", "trampoline" : "0.1.2", "transformers" : "4.55.0", "typing-inspection" : "0.4.1", "typing_extensions" : "4.12.2", "urllib3" : "1.26.13", "uvicorn" : "0.35.0", "watchfiles" : "1.1.0", "wcwidth" : "0.2.13", "websockets" : "15.0.1", "wrapt" : "1.17.2", "wsproto" : "1.2.0", "zipp" : "3.19.2" }, "config": { "schema_version": "4.0.2", "legacy_models_yaml_path": null, "host": "0.0.0.0", "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": 50, "max_cache_vram_gb": null, "log_memory_usage": false, "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", "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": null, "scan_models_on_startup": false, "unsafe_disable_picklescan": false }, "set_config_fields": [ "host", "pytorch_cuda_alloc_conf", "legacy_models_yaml_path", "max_cache_ram_gb", "enable_partial_loading" ] }
What happened
When trying to install the Kontext LORA from this link : https://civitai.com/models/1871505/kontext-reality-transform-by-aldniki?modelVersionId=2118275 The following error is displayed:
Model install error Unknown LoRA type
What you expected to happen
Successfully install and be used with Flux Kontext
How to reproduce the problem
Start the Invoke app. Download from CivitAI and point Invoke to install the safetensor file. Get the error.
Additional context
In Ruined Fooocus it seems to work fine though.
Discord username
lancermaster
Hi, I'm getting the same error with this model with both local and CivitAI installation. It works in SwarmUI https://civitai.com/models/1128288/dramatic-lighting-slider-illustrious
Hi, I'm getting the same error with this model with both local and CivitAI installation. It works in SwarmUI https://civitai.com/models/1128288/dramatic-lighting-slider-illustrious
I think this one is a SDXL LoRA, not flux compatible. I assembled some tools to 'fix' LoRAs for InvokeAI and this is what it reported for that model:
% python test_invokeai_compatibility.py /Users/andre/Documents/machine_learning/lora/Dramatic\ Lighting\ Slider.safetensors
======================================================================
InvokeAI LoRA Compatibility Test
======================================================================
Testing 1 file(s)...
✗ Dramatic Lighting Slider.safetensors
Format: Stable Diffusion (not Flux)
Size: 7.74 MB
Keys: 840 total
Rank: Unknown
Key breakdown:
- lora_unet: 840
- transformer: 840
Issues:
- This is a Stable Diffusion (SD1.5/SDXL) LoRA, not a Flux LoRA
- SD LoRAs use down_blocks/up_blocks architecture, incompatible with Flux
Sample keys:
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_k.alpha
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_k.lora_down.weight
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_k.lora_up.weight
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_out_0.alpha
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_out_0.lora_down.weight
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_out_0.lora_up.weight
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_q.alpha
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_q.lora_down.weight
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_q.lora_up.weight
- lora_unet_down_blocks_1_attentions_0_transformer_blocks_0_attn1_to_v.alpha
======================================================================
Summary:
Total files: 1
✓ Compatible: 0
✗ Incompatible: 1
======================================================================
What happened
When trying to install the Kontext LORA from this link : https://civitai.com/models/1871505/kontext-reality-transform-by-aldniki?modelVersionId=2118275 The following error is displayed:
Model install error Unknown LoRA type
I have a tool that can fix this.
% python repair_lora.py /Users/andre/Documents/machine_learning/lora/aldniki_reality_transform_v01.safetensors
======================================================================
Flux LoRA Repair Tool
======================================================================
Input: /Users/andre/Documents/machine_learning/lora/aldniki_reality_transform_v01.safetensors
Output: /Users/andre/Documents/machine_learning/lora/aldniki_reality_transform_v01_fixed.safetensors
Analyzing file...
Issue detected: Non-standard final_layer keys
Strategy: Remove non-standard final_layer keys
Applying fix: Removing non-standard final_layer keys
======================================================================
Pass 2: Re-analyzing file...
======================================================================
Re-analyzing file...
Validating repair...
File size:
Original: 292.58 MB
Repaired: 292.39 MB
Fixes applied (1):
- final_layer_keys: Removed 2 non-standard final_layer key(s)
======================================================================
✓ Repair successful!
======================================================================
The repaired file is now compatible with InvokeAI.
Validation result: All keys match Flux Kohya format (InvokeAI strict check)
Test it with: python test_invokeai_compatibility.py "/Users/andre/Documents/machine_learning/lora/aldniki_reality_transform_v01_fixed.safetensors"
same for Lora ID 1594293
This one loads for me without any changes. My inspector tool says:
% python test_invokeai_compatibility.py /Users/andre/Documents/machine_learning/lora/Tennis_love_story_two_boys_OCs-000017.safetensors
======================================================================
InvokeAI LoRA Compatibility Test
======================================================================
Testing 1 file(s)...
✓ Tennis_love_story_two_boys_OCs-000017.safetensors
Format: Flux Diffusers
Size: 217.87 MB
Keys: 2958 total
Rank: 32
======================================================================
Summary:
Total files: 1
✓ Compatible: 1
✗ Incompatible: 0
Format breakdown:
- Flux Diffusers: 1
======================================================================
same for Lora ID 1594293
This one loads for me without any changes. My inspector tool says:
% python test_invokeai_compatibility.py /Users/andre/Documents/machine_learning/lora/Tennis_love_story_two_boys_OCs-000017.safetensors ====================================================================== InvokeAI LoRA Compatibility Test ====================================================================== Testing 1 file(s)... ✓ Tennis_love_story_two_boys_OCs-000017.safetensors Format: Flux Diffusers Size: 217.87 MB Keys: 2958 total Rank: 32 ====================================================================== Summary: Total files: 1 ✓ Compatible: 1 ✗ Incompatible: 0 Format breakdown: - Flux Diffusers: 1 ======================================================================
Thanks for the help. I just noticed that Civitai uses different ID numbers in their download links than in their website URL's. So the Lora i was talking about is https://civitai.com/api/download/models/1594293?type=Model&format=SafeTensor I just tried it again an Invoke can't import it