hen we reached the first section of grass, on our way along the footpath, Poppy decided that it was time for a chase, and Gizmo was going to be her partner.

 He’s twice her age and less that half her size, so I didn’t feel she was being particularly ambitious, but Gizmo didn’t see a problem with the plan, so I left them to it.

Teddy

We met Teddy as we arrived at the field, which is always a treat.  Nova didn’t know whether to play with him, or get fuss from his Dad.  She managed to split her time between them both quite successfully.

Rupert and Teddy did have a lovely play together, although Rupert thought the chase should end with being jumped on (as happens with Nova), but Teddy didn’t quite understand why Rupert rolled on his back in surrender.

Archie

Archie found himself a ball to play with, so when we left Teddy, he could show it off to everybody.  Nova and Rupert would both have loved it, but it took Nova’s concentration to spot when Archie dropped it.  When everyone was distracted, and the ball appeared forgotten, I decided to put it away for safe keeping.  Nova was the one who realised what had happened, so she promptly found another ball.  Rupert barked at Nova a few times, in the hope it would persuade her to relinquish the new ball to him, but it’s never worked in the past, and is unlikely ever to be successful.  It’s impossible not to knock his ambition.

Gizmo decided it was time for another round of hide-and-seek, instead of leaving the park.  The main challenge with the game is making sure Gizmo thinks he’s successfully hidden himself.  Today he was ‘hidden’ behind a wire mesh fence, which in no way hid him from sight.

Ascend NPUs

For models compatible with Ascend Extension for PyTorch (torch_npu). To get started, ensure your environment meets the prerequisites outlined on the installation page. Here's a step-by-step guide tailored to your platform and installation method:

1. Begin by installing the recommended or newer kernel version for Linux as specified in the Installation page of torch-npu, if necessary.
2. Proceed with the installation of Ascend Basekit, which includes the driver, firmware, and CANN, following the instructions provided for your specific platform.
3. Next, install the necessary packages for torch-npu by adhering to the platform-specific instructions on the Installation page.
4. Finally, adhere to the ComfyUI manual installation guide for Linux. Once all components are installed, you can run ComfyUI as described earlier.

Cambricon MLUs

For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a step-by-step guide tailored to your platform and installation method:

1. Install the Cambricon CNToolkit by adhering to the platform-specific instructions on the Installation
2. Next, install the PyTorch(torch_mlu) following the instructions on the Installation
3. Launch ComfyUI by running python main.py

Iluvatar Corex

For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:

1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the Installation
2. Launch ComfyUI by running python main.py

Git clone this repo.

Put your SD checkpoints (the huge ckpt/safetensors files) in: models/checkpoints

Put your VAE in: models/vae

AMD GPUs (Linux)

AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4

This is the command to install the nightly with ROCm 7.1 which might have some performance improvements:

pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.1