Question: Image to Prompt Possible with this SDK?

[bin2ai]

There is a function inside the client.py script called image_to_prompt which returns type generation.prompt which appears to be a byte string.

Has anyone had any luck converting an image to prompt (ASCII) using this SDK?

[shishimaru]

@bin2ai
Hi,

I also found the internal function and there is a sample program to get as ASCII string.
https://colab.research.google.com/github/pharmapsychotic/clip-interrogator/blob/main/clip_interrogator.ipynb#scrollTo=xpPKQR40qvz2

The function you want would be below.

def image_to_prompt(image, mode):
    ci.config.chunk_size = 2048 if ci.config.clip_model_name == "ViT-L-14/openai" else 1024
    ci.config.flavor_intermediate_count = 2048 if ci.config.clip_model_name == "ViT-L-14/openai" else 1024
    image = image.convert('RGB')
    if mode == 'best':
        return ci.interrogate(image)
    elif mode == 'classic':
        return ci.interrogate_classic(image)
    elif mode == 'fast':
        return ci.interrogate_fast(image)
    elif mode == 'negative':
        return ci.interrogate_negative(image)

On the Web UI, the one was shown.