Hugging Face's logo

huggan
/
distill-ccld-wa

Text-to-Image
PyTorch
huggan
diffusion
Model card Files Community
gigant commited on
Commit
7396a83
•
1 Parent(s): 0a58d5f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -58,4 +58,5 @@ The model was fine-tuned on the Wikiart dataset for ~12 hours on 2 A6000 GPUs ki
58
  * [Model card for the student model on HuggingFace](https://huggingface.co/huggan/distill-ccld-wa), trained by me. You can check my [WandB report](https://wandb.ai/gigant/distill-ccld/reports/Distill-Diffusion-105M--VmlldzoxODQwMTUz?accessToken=mfbrz1ghfakmh01lybsuycwm3qj3isv60uynnvmina3tiwz5e5ufbjui5xqhmaqi). This version has 105M parameters, against 1.2B parameters for the teacher version. It is lighter, and allows for faster inference, while maintaining some of the original model capability at generating paintings from prompts.
59
  * [Gradio demo app on HuggingFace's Spaces](https://huggingface.co/spaces/huggan/wikiart-diffusion-mini) to try out the model with an online demo app
60
  * [iPython Notebook](https://github.com/giganttheo/distill-ccld/blob/master/distillCCLD_(Wikiart)_demo.ipynb) to use the model in Python
 
61
  * [GitHub repository](https://github.com/giganttheo/distill-ccld)
 
58
  * [Model card for the student model on HuggingFace](https://huggingface.co/huggan/distill-ccld-wa), trained by me. You can check my [WandB report](https://wandb.ai/gigant/distill-ccld/reports/Distill-Diffusion-105M--VmlldzoxODQwMTUz?accessToken=mfbrz1ghfakmh01lybsuycwm3qj3isv60uynnvmina3tiwz5e5ufbjui5xqhmaqi). This version has 105M parameters, against 1.2B parameters for the teacher version. It is lighter, and allows for faster inference, while maintaining some of the original model capability at generating paintings from prompts.
59
  * [Gradio demo app on HuggingFace's Spaces](https://huggingface.co/spaces/huggan/wikiart-diffusion-mini) to try out the model with an online demo app
60
  * [iPython Notebook](https://github.com/giganttheo/distill-ccld/blob/master/distillCCLD_(Wikiart)_demo.ipynb) to use the model in Python
61
+ * [WikiArt dataset on `datasets` hub](https://huggingface.co/datasets/huggan/wikiart)
62
  * [GitHub repository](https://github.com/giganttheo/distill-ccld)