Thomas Pang

@ycjing great work! and what the performance on your implementation? i noticed that it is very fast in your demo video.

@ycjing cool, i'm sure this will be a very potential project. where will Alibaba use this tech on? some application like prisma?

same problem, but i use smaller image size like "-image_size 256", it's work. is it possible error on gpu memory? like something "out of memory"

is there any parameter like "style scale" mentioned by neural-sytle. i agree bmaltais too, does any one tried code below tag texture_nets_v1

@DmitryUlyanov Thanks! so far in my test of some method, texture_nets is faster than others, so hope to be front runner while keep quality.

Me too

is there any node for ComfyUI can link or weighted multiple prompt text(each less than 77 tokens) to one output?

> [oobabooga/text-generation-webui#788 (comment)](https://github.com/oobabooga/text-generation-webui/issues/788#issuecomment-1496918979) 我跟着这个改了名称，以ggml开头，启动成功了。后面的还在研究 我用的ChatLLaMA-zh-7B，你的意思是直接把文件chatllama_7b.bin改名为gglm-chatllama_7b.bin吗？ 好像还是不行，还是提示缺乏config.json。

same issue

@DylanAlloy wow, great work! you generated a such large size image! does the style or style scale been applied looks as similar with small size image for example 720pixel?