TorAllex

`python entry_with_update.py --all-in-fp16 --attention-pytorch --disable-offload-from-vram --always-high-vram --gpu-device-id 0 --async-cuda-allocation --preset realistic` I have not M# silicon, my Mac is Intel based hackintosh ``` 100%|██████████████████████████████████████████████████| 6/6 [01:40

> Can you tell me where to put this script? I'm very bad at this. > > `python entry_with_update.py --all-in-fp16 --attention-pytorch --disable-offload-from-vram --always-high-vram --gpu-device-id 0 --async-cuda-allocation --preset realistic` Just type...

OSX 11.7.7, adapter PL2303 works fine for me. Also, a've try CP2102, that one not works. ``` alex@alex burn % ./burn --chip hi3518ev200 --file=autoupdate-uboot.bin -p /dev/cu.usbserial-1430 --break Trying open /dev/cu.usbserial-1430...

> Please try the newest version. Ok, now I can set exposure. But can't see if it really any affect for picture. More, i've tried varios values for exposure, ispGain,...

> These settings have been adjusted on the current build, following options can change the night picture: > > ``` > cli -s .isp.drc 400 > cli -s .isp.slowShutter high...

Yes, I've try use omost. Just I've load your "start_with_OMOST.json" workflow and click "Queue Prompt", then got error. Of course, this can be a hardware problem, since I use a...

I tried to double the maximum length up to 32768, but it didn't fix the error. Text node message: "PreTrainedTokenizerFast" object has no attribute "apply_chat_template".

I'll try an upgrade transformers, I need to see how to do it in MacOs

Ok, now the error looks different - "gpu not found". Does the device MPS not work with it?

 ``` Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Unused kwargs: ['_load_in_4bit', '_load_in_8bit',...