does not work on windows...

[mat-536]

can someone who has this working on windows describe how they did it?

Nothing happens.

Just keeps saying that Exiftool failed or some such.

Maybe dumb it down for me please?

Thanks.

[jabberjabberjabber]

It should work fine on Windows. Can you provide more details? Screenshots, what process you followed, your specifications, etc.

[mat-536]

Hi, and thank you.
Windows 10, admin account, run bat file as admin.

First installed the tool, downloaded prerequisites, and also a few LLMs to use.
Run the kobold item next and downloaded / updated and succeeeded.

Installed exiftool, both from your share and locally unzipped another copy as well.

Added multiple lines to users systems environment variables and also the system variables:

and

also

and here

Run tool
load kobold
run gui
select folder with JPG and or RAW [ARW] files
run

Exiftool failed
Exiftool failed
Exiftool failed
Exiftool failed

kobold:

---

Welcome to KoboldCpp - Version 1.104
Loading Chat Completions Adapter: C:\Users\NM\AppData\Local\Temp_MEI105122\kcpp_adapters\ChatML.json
Chat Completions Adapter Loaded
Qwen2-VL-2B-Instruct-Q6_K.gguf already exists, using existing file.
mmproj-Qwen2-VL-2B-Instruct-f16.gguf already exists, using existing file.
No GPU or CPU backend was selected. Trying to assign one for you automatically...
Auto Selected CUDA Backend (flag=0)

Auto Recommended GPU Layers: 16
System: Windows 10.0.19045 AMD64 Intel64 Family 6 Model 165 Stepping 5, GenuineIntel
Detected Available GPU Memory: 4096 MB
Detected Available RAM: 23114 MB
Initializing dynamic library: koboldcpp_cublas.dll

Namespace(admin=False, admindir='', adminpassword=None, analyze='', autofit=False, batchsize=512, benchmark=None, blasthreads=0, chatcompletionsadapter='ChatML', cli=False, config=None, contextsize=4096, debugmode=0, defaultgenamt=896, draftamount=8, draftgpulayers=999, draftgpusplit=None, draftmodel='', embeddingsgpu=False, embeddingsmaxctx=0, embeddingsmodel='', enableguidance=False, exportconfig='', exporttemplate='', failsafe=False, flashattention=True, forceversion=False, foreground=False, genlimit=0, gpulayers=16, highpriority=False, hordeconfig=None, hordegenlen=0, hordekey='', hordemaxctx=0, hordemodelname='', hordeworkername='', host='', ignoremissing=False, jinja=False, jinja_tools=False, launch=False, lora=None, loramult=1.0, lowvram=False, maingpu=-1, maxrequestsize=32, mmproj='mmproj-Qwen2-VL-2B-Instruct-f16.gguf', mmprojcpu=False, model=[], model_param='Qwen2-VL-2B-Instruct-Q6_K.gguf', moecpu=0, moeexperts=-1, multiplayer=False, multiuser=1, noavx2=False, noblas=False, nobostoken=False, nocertify=False, nofastforward=False, nommap=False, nomodel=False, noshift=False, onready='', overridekv='', overridenativecontext=0, overridetensors='', password=None, pipelineparallel=False, port=5001, port_param=5001, preloadstory='', prompt='', quantkv=0, quiet=False, ratelimit=0, remotetunnel=False, ropeconfig=[0.0, 10000.0], savedatafile='', sdclamped=0, sdclampedsoft=0, sdclip1='', sdclip2='', sdclipgpu=False, sdconfig=None, sdconvdirect='off', sdflashattention=False, sdgendefaults='', sdlora='', sdloramult=1.0, sdmodel='', sdnotile=False, sdoffloadcpu=False, sdphotomaker='', sdquant=0, sdt5xxl='', sdthreads=0, sdtiledvae=768, sdvae='', sdvaeauto=False, sdvaecpu=False, showgui=False, singleinstance=False, skiplauncher=False, smartcache=False, smartcontext=False, ssl=None, tensor_split=None, testmemory=False, threads=5, ttsgpu=False, ttsmaxlen=4096, ttsmodel='', ttsthreads=0, ttswavtokenizer='', unpack='', useclblast=None, usecpu=False, usecuda=['normal', 'mmq'], usemlock=False, usemmap=False, useswa=False, usevulkan=None, version=False, visionmaxres=9999, websearch=False, whispermodel='')

Loading Text Model: C:_progs\ImageIndexer-main\ImageIndexer-main\resources\Qwen2-VL-2B-Instruct-Q6_K.gguf

The reported GGUF Arch is: qwen2vl
Arch Category: 7

---

Identified as GGUF model.
Attempting to Load...

Using automatic RoPE scaling for GGUF. If the model has custom RoPE settings, they'll be used directly instead!
System Info: AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | AMX_INT8 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
CUDA MMQ: True

Initializing CUDA/HIP, please wait, the following step may take a few minutes (only for first launch)...

ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce GTX 1050 Ti, compute capability 6.1, VMM: yes
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce GTX 1050 Ti) (0000:01:00.0) - 3357 MiB free
llama_model_loader: loaded meta data with 37 key-value pairs and 338 tensors from C:_progs\ImageIndexer-main\ImageIndexer-main\resources\Qwen2-VL-2B-Instruct-Q6_K.gguf (version GGUF V3 (latest))
print_info: file format = GGUF V3 (latest)
print_info: file size = 1.18 GiB (6.56 BPW)
init_tokenizer: initializing tokenizer for type 2
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: special tokens cache size = 14
load: token to piece cache size = 0.9309 MB
print_info: arch = qwen2vl
print_info: vocab_only = 0
print_info: no_alloc = 0
print_info: n_ctx_train = 32768
print_info: n_embd = 1536
print_info: n_embd_inp = 1536
print_info: n_layer = 28
print_info: n_head = 12
print_info: n_head_kv = 2
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 6
print_info: n_embd_k_gqa = 256
print_info: n_embd_v_gqa = 256
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 8960
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: n_expert_groups = 0
print_info: n_group_used = 0
print_info: causal attn = 1
print_info: pooling type = -1
print_info: rope type = 8
print_info: rope scaling = linear
print_info: freq_base_train = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 32768
print_info: rope_yarn_log_mul= 0.0000
print_info: rope_finetuned = unknown
print_info: mrope sections = [16, 24, 24, 0]
print_info: model type = 1.5B
print_info: model params = 1.54 B
print_info: general.name = Qwen2 VL 2B Instruct
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
print_info: LF token = 198 'ÄS'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: relocated tensors: 1 of 339
load_tensors: offloading output layer to GPU
load_tensors: offloading 15 repeating layers to GPU
load_tensors: offloaded 16/29 layers to GPU
load_tensors: CPU model buffer size = 182.57 MiB
load_tensors: CUDA0 model buffer size = 731.97 MiB
load_tensors: CUDA_Host model buffer size = 476.14 MiB
load_all_data: using async uploads for device CUDA0, buffer type CUDA0, backend CUDA0
............................................................................

MRope is used, context shift will be disabled!
Automatic RoPE Scaling: Using model internal value.
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4352
llama_context: n_ctx_seq = 4352
llama_context: n_batch = 512
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = enabled
llama_context: kv_unified = true
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_seq (4352) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
set_abort_callback: call
llama_context: CUDA_Host output buffer size = 0.58 MiB
llama_kv_cache: CPU KV buffer size = 55.25 MiB
llama_kv_cache: CUDA0 KV buffer size = 63.75 MiB
llama_kv_cache: size = 119.00 MiB ( 4352 cells, 28 layers, 1/1 seqs), K (f16): 59.50 MiB, V (f16): 59.50 MiB
llama_context: enumerating backends
llama_context: backend_ptrs.size() = 2
llama_context: max_nodes = 2712
llama_context: reserving full memory module
llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 1
llama_context: CUDA0 compute buffer size = 299.75 MiB
llama_context: CUDA_Host compute buffer size = 11.52 MiB
llama_context: graph nodes = 959
llama_context: graph splits = 184 (with bs=512), 2 (with bs=1)
Threadpool set to 5 threads and 5 blasthreads...
attach_threadpool: call

Attempting to apply Multimodal Projector: C:_progs\ImageIndexer-main\ImageIndexer-main\resources\mmproj-Qwen2-VL-2B-Instruct-f16.gguf
clip_model_loader: model name: Qwen2-VL-2B-Instruct
clip_model_loader: description: image encoder for Qwen2VL
clip_model_loader: GGUF version: 3
clip_model_loader: alignment: 32
clip_model_loader: n_tensors: 521
clip_model_loader: n_kv: 20

clip_model_loader: has vision encoder
clip_ctx: CLIP using CUDA0 backend
load_hparams: projector: qwen2vl_merger
load_hparams: n_embd: 1280
load_hparams: n_head: 16
load_hparams: n_ff: 0
load_hparams: n_layer: 32
load_hparams: ffn_op: gelu_quick
load_hparams: projection_dim: 1536

--- vision hparams ---
load_hparams: image_size: 560
load_hparams: patch_size: 14
load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 0
load_hparams: n_merge: 2
load_hparams: n_wa_pattern: 0
load_hparams: image_min_pixels: 6272
load_hparams: image_max_pixels: 1605632

load_hparams: model size: 1269.94 MiB
load_hparams: metadata size: 0.21 MiB
load_tensors: ffn up/down are swapped
load_tensors: loaded 521 tensors from C:_progs\ImageIndexer-main\ImageIndexer-main\resources\mmproj-Qwen2-VL-2B-Instruct-f16.gguf
Starting model warm up, please wait a moment...
Load Text Model OK: True
Embedded KoboldAI Lite loaded.
Embedded API docs loaded.
Llama.cpp UI loaded.

Active Modules: TextGeneration MultimodalVision
Inactive Modules: ImageGeneration VoiceRecognition MultimodalAudio NetworkMultiplayer ApiKeyPassword WebSearchProxy TextToSpeech VectorEmbeddings AdminControl
Enabled APIs: KoboldCppApi OpenAiApi OllamaApi
Starting Kobold API on port 5001 at http://localhost:5001/api/
Starting OpenAI Compatible API on port 5001 at http://localhost:5001/v1/
Starting llama.cpp secondary WebUI at http://localhost:5001/lcpp/

Please connect to custom endpoint at http://localhost:5001

run tool:

Please make a selection: 3
Launching GUI...
Exiftool error
Exiftool error
Exiftool error
Exiftool error
Exiftool error
Exiftool error
Waiting for indexer to complete...
Indexing completed.

also:

Running Image Indexer...
Processing directory: G:@pics all cards copies 2025 09 13 DO NOT DELETE\card_16

Directory processed. Files remaining in queue: 286

Processing directory: G:@pics all cards copies 2025 09 13 DO NOT DELETE\card_16

Directory processed. Files remaining in queue: 286

Processing directory: G:@pics all cards copies 2025 09 13 DO NOT DELETE\card_16

Directory processed. Files remaining in queue: 286

ExifTool process terminated cleanly

Image Indexer finished.

[jabberjabberjabber]

I think it is because you have an @ sign in the directory. Rename it and remove the @ and try again.

[mat-536]

Thank you for taking a look.
Renamed directory to many different things, All failed like this:

Please make a selection: 3
Launching GUI...
Exiftool error
Waiting for indexer to complete...
Indexing completed.

---

Running Image Indexer...
Processing directory: G:\card 08 DCIM\100MSDCF

Directory processed. Files remaining in queue: 49

ExifTool process terminated cleanly

Image Indexer finished.