Useful or not, from you.
CogView Got error ''IndexError: tuple index out of range'' running super-res on colab with a tesla v100

/content/CogView Generate Samples WARNING: No training data specified using world size: 1 and model-parallel size: 1

using dynamic loss scaling initializing model parallel with size 1 initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 padded vocab (size: 58219) with 21 dummy tokens (new size: 58240) prepare tokenizer done building CogView2 model ... number of parameters on model parallel rank 0: 3928849920 current device: 0 tcmalloc: large alloc 7881007104 bytes == 0x5637e3fb2000 @ 0x7f61e428db6b 0x7f61e42ad379 0x7f6171f1e25e 0x7f6171f1f9d2 0x7f61aff48e7d 0x7f61c0b43120 0x7f61c0781bd9 0x5637152088a8 0x56371527bfd5 0x5637152767ad 0x5637152093ea 0x5637152773b5 0x5637152767ad 0x563715209003 0x563715208b09 0x56371535028d 0x5637152bf1db 0x563715207bb1 0x5637152f8fed 0x56371527b988 0x5637152767ad 0x563715148e2c 0x563715278bb5 0x5637152764ae 0x5637152093ea 0x56371527832a 0x56371520930a 0x5637152773b5 0x56371520930a 0x5637152773b5 0x5637152764ae Load model file pretrained/cogview/cogview-sr/20000/ Working on No. 0 on 0... Traceback (most recent call last): File "", line 326, in <module> main() File "", line 323, in main generate_images_continually(model, args) File "", line 215, in generate_images_continually for raw_text, seq, output_path in get_context(args, query_template): File "", line 132, in get_context seq = _parse_and_to_tensor(raw_text, img_size=img_size, query_template=query_template) File "", line 70, in _parse_and_to_tensor text = query_template.format(*text.split('\t')) IndexError: tuple index out of range /content

That's a useful answer
Without any help

#@title Super resolution (WIP) if you know how to implement this contact aze#1 on discord #@markdown this requires the cogview-sr model to be downloaded (look at the 3rd cell)

#@markdown can be 0.jpg, 1.jpg, 2.jpg ... etc depends on your batch_size image = "0.jpg" #@param {type:"string"}

prompt = "text\t/content/CogView/samples/" + image

%cd /content/CogView !sh scripts/ %cd /content


I am sorry but it seems the message is messy and I cannot know what you really input, but could you try to change the input source to a file?

./scripts/ --input-source sr_input.txt

where sr_input.txt is a line of


\t is TAB, which looks like some spaces. The line looks like (but changing spaces to a TAB)

 一个漂亮的女人走在街上    /content/CogView/samples/0.jpg