Code Monkey home page Code Monkey logo

Comments (8)

TonyLianLong avatar TonyLianLong commented on May 19, 2024

What is your setting? It works on my end.

To create a public link, set `share=True` in `launch()`.
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:30<00:00,  1.62it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:13<00:00,  1.15it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:23<00:00,  2.10it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:08<00:00,  1.85it/s]

from stable-diffusion-xl-demo.

TonyLianLong avatar TonyLianLong commented on May 19, 2024

Seems that the decoder VAE on the refiner is somehow not fp16. Did you change any config? You can also disable refiner to see if it still happens.

from stable-diffusion-xl-demo.

densechen avatar densechen commented on May 19, 2024

from stable-diffusion-xl-demo.

TonyLianLong avatar TonyLianLong commented on May 19, 2024

Seems like it still works if the models are not offloaded.

$ OFFLOAD_BASE=false OFFLOAD_REFINER=false python app.py 
Loading model stabilityai/stable-diffusion-xl-base-1.0
Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:01<00:00,  3.92it/s]
Loading model stabilityai/stable-diffusion-xl-refiner-1.0
Loading pipeline components...:  20%|███████████████████████████████                                                                                                                            | 1/5 [00:00<00:01,  2.55it/s]
Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:01<00:00,  4.18it/s]
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:06<00:00,  7.44it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:02<00:00,  7.47it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:06<00:00,  7.70it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:01<00:00,  7.72it/s]

from stable-diffusion-xl-demo.

TonyLianLong avatar TonyLianLong commented on May 19, 2024

Since you loaded custom weights, it's possible that somehow fp32 weights are loaded. You probably want to check whether you have fp16 weights (https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main/vae).

If you loaded fp32 weights, you can add refiner.to(torch.float16) to cast the model parameters to fp16.

from stable-diffusion-xl-demo.

densechen avatar densechen commented on May 19, 2024

Seems that the decoder VAE on the refiner is somehow not fp16. Did you change any config? You can also disable refiner to see if it still happens.

I have disabled refiner via PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512 SDXL_MODEL_DIR=pretrained_models OFFLOAD_BASE=false ENABLE_REFINER=false python app.py, failed to solve this issue.

from stable-diffusion-xl-demo.

densechen avatar densechen commented on May 19, 2024

It seems like that. A minor modification maybe required to make this repo more robust.

from stable-diffusion-xl-demo.

TonyLianLong avatar TonyLianLong commented on May 19, 2024

Since I could not reproduce this, could you show me your diff?

from stable-diffusion-xl-demo.

Related Issues (8)

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.