GithubHelp home page GithubHelp logo

experimental-consistory's People

Contributors

kousw avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Forkers

adityapandey9

experimental-consistory's Issues

About multi-subject generation.

Thanks a lot for your excellent implementation of ConsiStory. It helps a lot.
I wonder how can I do multi-subject generation with this repo. Do you have time to implement and provide some examples? Thanks in advance.

How to get your results in README?

When I run this script python inference_consistory.py --guidance_scale 1.0 --num_inference_steps 10 --keywords "1girl" --prompt "1girl, best quality, ultra detailed, sitting on the beach" "1girl, best quality, ultra detailed, resting on the wood" "1girl, best quality, ultra detailed, shoot guns and run the battlefield",
the generated result is like this:
image

models:
models--runwayml--stable-diffusion-v1-5
latent-consistency-lcm-lora-sdv1-5
stabilityai/stable-diffusion-2-1

To use guidance scale > 1.0

Any workaround to use guidance scale > 1.0. The code seems to break when guidance scale of > 1.0 is used.

Error using default models/aom3

Is using the default models/aom3 working ? I get the following error:

Repository Not Found for url: https://huggingface.co/models/aom3/resolve/main/scheduler/scheduler_config.json.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "inference_consistory.py", line 606, in <module>
    pre_generate_images_for_dift(args)
  File "inference_consistory.py", line 62, in pre_generate_images_for_dift
    noise_scheduler = DDPMScheduler.from_pretrained(args.model_name_or_path, subfolder="scheduler", cache_dir = CACHE_DIR)
  File "/usr/local/lib/python3.8/dist-packages/diffusers/schedulers/scheduling_utils.py", line 140, in from_pretrained
    config, kwargs, commit_hash = cls.load_config(
  File "/usr/local/lib/python3.8/dist-packages/diffusers/configuration_utils.py", line 385, in load_config
    raise EnvironmentError(
OSError: models/aom3 is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login`.

Could you kindly help me out ?

License of the codebase

Thank you for releasing the unofficial codebase of consistory. It is really a wonderful work with lot of insights into using cross attention across frames. I was wondering what would be the license for this work. We would like to suggest MIT license if possible.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.