[FEATURE REQUEST] txt2imghd, the upscaler port of GOBIG

[JamesIV4]

https://github.com/jquesnelle/txt2imghd

This upscaling script would be an amazing addition to the WebUI. The author describes it best:

txt2imghd is a port of the GOBIG mode from progrockdiffusion applied to Stable Diffusion, with Real-ESRGAN as the upscaler. It creates detailed, higher-resolution images by first generating an image from a prompt, upscaling it, and then running img2img on smaller pieces of the upscaled image, and blending the result back into the original image.

txt2imghd with default settings has the same VRAM requirements as regular Stable Diffusion, although generation of the detailed images will take longer.

I tried to get it working and was able to submit a prompt, but it failed part-way in. Looks like it would be really close to working though without too many changes.

My error for reference:

  File "D:\Repos\stable-diffusion\scripts\txt2imghd.py", line 549, in <module>
    main()
  File "D:\Repos\stable-diffusion\scripts\txt2imghd.py", line 365, in main
    text2img2(opt)
  File "D:\Repos\stable-diffusion\scripts\txt2imghd.py", line 388, in text2img2
    model = load_model_from_config(config, f"{opt.ckpt}")
  File "D:\Repos\stable-diffusion\scripts\txt2imghd.py", line 53, in load_model_from_config
    model = instantiate_from_config(config.model)
  File "d:\repos\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "d:\repos\stable-diffusion\ldm\util.py", line 93, in get_obj_from_str
    return getattr(importlib.import_module(module, package=None), cls)
  File "C:\Users\james\anaconda3\lib\importlib\__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1030, in _gcd_import
  File "<frozen importlib._bootstrap>", line 1007, in _find_and_load
  File "<frozen importlib._bootstrap>", line 986, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 680, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 850, in exec_module
  File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed
  File "d:\repos\stable-diffusion\ldm\models\diffusion\ddpm.py", line 24, in <module>
    from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
  File "d:\repos\stable-diffusion\ldm\models\autoencoder.py", line 6, in <module>
    from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
ImportError: cannot import name 'VectorQuantizer2' from 'taming.modules.vqvae.quantize' (C:\Users\james\anaconda3\lib\site-packages\taming\modules\vqvae\quantize.py)```