After adding any kind of task on WAN2.2 TextToVideo 14B (but any really) the generation is stuck and shows 0.0% queue 1/1.
First run of Pinokio ever, fresh install, run as Admin, installed on C.
Steps to reproduce
- Vanilla install of pinokio
- Load up WAN2.2
- Text 2 Image - Image to Image guided
- Add any simple guide prompt
- Add to queue and generate
Your system (OS / GPU / RAM / VRAM / etc.)
Win 11, 32GB Ram, AMD Radeon RX 9070 XT
Logs / full error output
C:\pinokio\api\wan2gp-amd.git\app>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base & C:\pinokio\api\wan2gp-amd.git\app\env\Scripts\activate C:\pinokio\api\wan2gp-amd.git\app\env && python wgp.py
[GGUF][llama.cpp CUDA] kernels unavailable, using fallback
Loaded plugin: Motion Manager (from wan2gp-motion-designer)
* Running on local URL: http://localhost:7860
* To create a public link, set `share=True` in `launch()`.
Loading Model 'ckpts\wan2.2_text2video_14B_high_quanto_mbf16_int8.safetensors' ...
Loading Model 'ckpts\wan2.2_text2video_14B_low_quanto_mbf16_int8.safetensors' ...
Loading Text Encoder 'ckpts\umt5-xxl\models_t5_umt5-xxl-enc-quanto_int8.safetensors' ...
************ Memory Management for the GPU Poor (mmgp 3.7.6) by DeepBeepMeep ************
Switching to partial pinning since full requirements for pinned models is 27717.9 MB while estimated available reservable RAM is 12764.3 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: 58 large blocks spread across 12743.14 MB
Hooked to model 'transformer' (WanModel)
Async loading plan for model 'transformer' : base size of 2.54 MB will be preloaded with a 335.35 MB async circular shuttle
Hooked to model 'vae' (WanVAE_)
Hooked to model 'text_encoder' (T5Encoder)
Async loading plan for model 'text_encoder' : base size of 2003.01 MB will be preloaded with a 184.10 MB async circular shuttle
Unable to pin data of 'transformer2' to reserved RAM as there is no reserved RAM left. Transfer speed from RAM to VRAM may be slower.
Hooked to model 'transformer2' (WanModel)
Async loading plan for model 'transformer2' : base size of 2.54 MB will be preloaded with a 335.35 MB async circular shuttle
After adding any kind of task on WAN2.2 TextToVideo 14B (but any really) the generation is stuck and shows 0.0% queue 1/1.
First run of Pinokio ever, fresh install, run as Admin, installed on C.
Steps to reproduce
Your system (OS / GPU / RAM / VRAM / etc.)
Win 11, 32GB Ram, AMD Radeon RX 9070 XT
Logs / full error output