Shareef
Shareef
> hi, > > OnnxStream is probably already capable of running the models you mentioned. > The problem is converting the code that "calls" these models into C++ (for >...
OpenBlas is fast tho u could add OpenBlas support and npu support for 8 gen 1-elite 888 supports npu also
> That's because causVid is not just like most LoRAs that add new knowledge to the model, it fundamentally changes the way the model is supposed to be sampled, kinda...
I fixed it with deepseek r1 I didn't have files permission so I had to do this: chmod 755 /root/fastsdcpu/libstable-diffusion.so. it was reading the wrong folder
> @KintCark hope it is working now ? Yes but it's forever processing no steps started
> @KintCark gguf is pretty slow compared to other modes, please check logs Can you add snapdragon 8 gen 1-elite npu processing ot will make generation faster
> What are your system specs? CPU/System RAM/GPU +VRAM? Cpu snapdragon 865 Ram 10602MB Gpu adreno 650 Vram N/A
> @stduhpf You're very right... you shouldn't expect miracles. But you should at least be able to get viable clips from it, which is what my particular example clip did....
> Can you supply a sample prompt you're attempting to use? If you're not using the `--diffusion-fa` option, it might be necessary as it seems to be with Vulkan and...
> > How you able to use the wan 2.1 1.3B fp16 model with utm5xxl q5_0 I have 10gb ram with 8gb free u tried wab 2.1 1 3B Q8...