Wan2GP: [GGUF][llama.cpp CUDA] Get only black video with WAN2GP on a Nvidia MSI RTX 4060 8Gb

App: Wan2GP (wan.git)
Repo: https://github.com/pinokiofactory/wan.git
Generated: 2026-07-11T15:59:14.760Z
Pinokio: 8.0.8
Platform: win32 x64
Node: v22.21.1

Summary

System

{
  "pinokio": {
    "version": "8.0.8",
    "node": "v22.21.1",
    "platform": "win32",
    "arch": "x64"
  },
  "hardware": {
    "gpu": "nvidia",
    "gpu_model": "nvidia geforce rtx 4060",
    "ram_gb": 32,
    "vram_gb": 8
  },
  "os": {
    "platform": "Windows",
    "distro": "Microsoft Windows 11 Professionnel",
    "release": "10.0.26200",
    "codename": "25H2",
    "kernel": "10.0.26200",
    "arch": "x64",
    "build": "26200",
    "servicepack": "0.0",
    "uefi": true
  },
  "system": {
    "manufacturer": "Micro-Star International Co., Ltd.",
    "model": "MS-7E02",
    "version": "1.0",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Intel",
    "brand": "Gen Intel® Core™ i5-12600KF",
    "vendor": "GenuineIntel",
    "family": "6",
    "model": "151",
    "stepping": "2",
    "speed": 3.7,
    "speedMin": 3.7,
    "speedMax": 3.7,
    "cores": 16,
    "physicalCores": 10,
    "processors": 1,
    "performanceCores": 16,
    "efficiencyCores": 0,
    "virtualization": false,
    "cache": {
      "l1d": 425984,
      "l1i": 458752,
      "l2": 9961472,
      "l3": 20971520
    }
  },
  "memory": {
    "total": 34140372992,
    "free": 26150547456,
    "used": 7989825536,
    "active": 7989825536,
    "available": 26150547456,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 0,
    "swaptotal": 2147483648,
    "swapused": 936378368,
    "swapfree": 1211105280
  },
  "gpus": [
    {
      "model": "nvidia geforce rtx 4060"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "NVIDIA",
        "model": "NVIDIA GeForce RTX 4060",
        "bus": "PCI",
        "vram": 8188,
        "vramDynamic": false,
        "driverVersion": "610.62"
      }
    ],
    "displays": [
      {
        "model": "Moniteur Plug-and-Play générique",
        "main": true,
        "builtin": false,
        "connection": "HDMI",
        "currentResX": 2560,
        "currentResY": 1080,
        "resolutionX": 2560,
        "resolutionY": 1080,
        "pixelDepth": "32",
        "currentRefreshRate": 60
      },
      {
        "main": false,
        "builtin": false,
        "connection": "DP",
        "currentResX": 1920,
        "currentResY": 1080,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": "32",
        "currentRefreshRate": 60
      }
    ]
  }
}

Logs

logs/api/start.js/1783774622704

Source: api / start.js
Lines: 36 total, last 36 included

[api shell.run]
Microsoft Windows [version 10.0.26200.8737]
(c) Microsoft Corporation. Tous droits réservés.

C:\pinokio\api\wan.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\wan.git\app\env\Scripts\activate C:\pinokio\api\wan.git\app\env && python wgp.py --multiple-images 
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
Loaded plugin: Motion Designer (from motion_designer)
* Running on local URL:  http://127.0.0.1:42003
* To create a public link, set `share=True` in `launch()`.
diffusion_models/ltx-2-19b-distilled_Q8_(…): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20.4G/20.4G [23:02<00:00, 14.8MB/s]
Loading Model 'ckpts\ltx-2-19b-distilled_Q8_0.gguf' ...
Loading Text Encoder 'ckpts\gemma-3-12b-it-qat-q4_0-unquantized\gemma-3-12b-it-qat-q4_0-unquantized_quanto_bf16_int8.safetensors' ...
************ Memory Management for the GPU Poor (mmgp 3.7.7) by DeepBeepMeep ************
Switching to partial pinning since full requirements for pinned models is 19452.7 MB while estimated available reservable RAM is 13023.5 MB. You may increase the value of parameter 'perc_reserved_mem_max' to a value higher than 0.40 to force full pinnning.
Partial pinning of data of 'transformer' to reserved RAM
The model was partially pinned to reserved RAM: 56 large blocks spread across 12922.12 MB
Hooked to model 'transformer' (X0Model)
Async loading plan for model 'transformer' : base size of 443.19 MB will be preloaded with a 391.57 MB async circular shuttle
Hooked to model 'text_encoder' (Gemma3ForCausalLM)
Async loading plan for model 'text_encoder' : base size of 1920.48 MB will be preloaded with a 213.87 MB async circular shuttle
Hooked to model 'text_embedding_projection' (GemmaFeaturesExtractorProjLinear)
Hooked to model 'text_embeddings_connector' (GemmaTextEmbeddingsConnectorModel)
Hooked to model 'vae' (VideoDecoder)
Hooked to model 'video_encoder' (VideoEncoder)
Hooked to model 'audio_encoder' (AudioEncoder)
Hooked to model 'audio_decoder' (AudioDecoder)
Hooked to model 'vocoder' (Vocoder)
Hooked to model 'spatial_upsampler' (LatentUpsampler)
 12%|██████████████████████████████████████▊                                                                                                                                                                                                                                                                               | 1/8 [00:24<02:54, 24.97s/steps]C:\pinokio\api\wan.git\app\wgp.py:8057: RuntimeWarning: invalid value encountered in cast
  images = images.numpy().clip(0, 255).astype(np.uint8)
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [01:30<00:00, 11.37s/steps]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:47<00:00, 15.95s/steps]
New video saved to Path: outputs\2026-07-11-15h27m00s_seed689548976_A warm sunny backyard. The camera starts in a tigh.mp4
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:58<00:00,  7.35s/steps]
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:23<00:00,  7.86s/steps]
New video saved to Path: outputs\2026-07-11-17h53m13s_seed219026716_A warm sunny backyard. The camera starts in a tigh.mp4