Prior-preservation is used to avoid overfitting and language-drift. Refer to the paper to learn more about it. For prior-preservation we first generate images using the model with a class prompt and then use those during training along with our data.
Prior-preservation is used to avoid overfitting and language-drift. Refer to the paper to learn more about it. For prior-preservation we first generate images using the model with a class prompt and then use those during training along with our data.
Or use the Flax implementation if you need a speedup
### Inference
Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `identifier`(e.g. sks in above example) in your prompt.
For faster training on TPUs and GPUs you can leverage the flax training example. Follow the instructions above to get the model and dataset before running the script.
____Note: The flax example don't yet support features like gradient checkpoint, gradient accumulation etc, so to use flax for faster training we will need >30GB cards.___
Before running the scripts, make sure to install the library's training dependencies:
Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `identifier`(e.g. sks in above example) in your prompt.
___This script is experimental. The script fine-tunes the whole model and often times the model overifits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparamters to get the best result on your dataset.___
___This script is experimental. The script fine-tunes the whole model and often times the model overifits and runs into issues like catastrophic forgetting. It's recommended to try different hyperparamters to get the best result on your dataset.___
## Running locally
## Running locally with PyTorch
### Installing the dependencies
### Installing the dependencies
Before running the scripts, make sure to install the library's training dependencies:
Before running the scripts, make sure to install the library's training dependencies:
To run on your own training files prepare the dataset according to the format required by `datasets`, you can find the instructions for how to do that in this [document](https://huggingface.co/docs/datasets/v2.4.0/en/image_load#imagefolder-with-metadata).
To run on your own training files prepare the dataset according to the format required by `datasets`, you can find the instructions for how to do that in this [document](https://huggingface.co/docs/datasets/v2.4.0/en/image_load#imagefolder-with-metadata).
If you wish to use custom loading logic, you should modify the script, we have left pointers for that in the training script.
If you wish to use custom loading logic, you should modify the script, we have left pointers for that in the training script.
Or use the Flax implementation if you need a speedup
Once the training is finished the model will be saved in the `output_dir` specified in the command. In this example it's `sd-pokemon-model`. To load the fine-tuned model for inference just pass that path to `StableDiffusionPipeline`
For faster training on TPUs and GPUs you can leverage the flax training example. Follow the instructions above to get the model and dataset before running the script.
____Note: The flax example don't yet support features like gradient checkpoint, gradient accumulation etc, so to use flax for faster training we will need >30GB cards.___
Before running the scripts, make sure to install the library's training dependencies:
Once the training is finished the model will be saved in the `output_dir` specified in the command. In this example it's `sd-pokemon-model`. To load the fine-tuned model for inference just pass that path to `StableDiffusionPipeline`
To run on your own training files prepare the dataset according to the format required by `datasets`, you can find the instructions for how to do that in this [document](https://huggingface.co/docs/datasets/v2.4.0/en/image_load#imagefolder-with-metadata).
If you wish to use custom loading logic, you should modify the script, we have left pointers for that in the training script.
[](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb)
[](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb)
## Running locally
## Running locally with PyTorch
### Installing the dependencies
### Installing the dependencies
Before running the scripts, make sure to install the library's training dependencies:
Before running the scripts, make sure to install the library's training dependencies:
A full training run takes ~1 hour on one V100 GPU.
A full training run takes ~1 hour on one V100 GPU.
If you want to speed it up even more, Flax implementation is available:
### Inference
Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `placeholder_token` in your prompt.
For faster training on TPUs and GPUs you can leverage the flax training example. Follow the instructions above to get the model and dataset before running the script.
Before running the scripts, make sure to install the library's training dependencies:
It should be at least 70% faster than the PyTorch script with the same configuration.
It should be at least 70% faster than the PyTorch script with the same configuration.
\ No newline at end of file
### Inference
Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `placeholder_token` in your prompt.
