stable-diffusion-v1-4-smashed

Model Card for dataset-viber/stable-diffusion-v1-4-smashed

This model was created using the pruna library. Pruna is a model optimization framework built for developers, enabling you to deliver more efficient models with minimal implementation overhead.

Usage

First things first, you need to install the pruna library:

pip install pruna

You can then load this model using the following code:

from pruna import PrunaModel

loaded_model = PrunaModel.from_hub("dataset-viber/stable-diffusion-v1-4-smashed")

After loading the model, you can use the inference methods of the original model.

Smash Configuration

The compression configuration of the model is stored in the smash_config.json file.

{
    "batcher": null,
    "cacher": "deepcache",
    "compiler": null,
    "pruner": null,
    "quantizer": null,
    "deepcache_interval": 2,
    "max_batch_size": 1,
    "device": "cpu",
    "save_fns": [],
    "load_fns": [
        "diffusers"
    ],
    "reapply_after_load": {
        "pruner": null,
        "quantizer": null,
        "cacher": "deepcache",
        "compiler": null,
        "batcher": null
    }
}

Model Configuration

The configuration of the model is stored in the config.json file.

{
    "model_index": {
        "_class_name": "StableDiffusionPipeline",
        "_diffusers_version": "0.33.1",
        "_name_or_path": "CompVis/stable-diffusion-v1-4",
        "feature_extractor": [
            "transformers",
            "CLIPImageProcessor"
        ],
        "image_encoder": [
            null,
            null
        ],
        "requires_safety_checker": true,
        "safety_checker": [
            "stable_diffusion",
            "StableDiffusionSafetyChecker"
        ],
        "scheduler": [
            "diffusers",
            "PNDMScheduler"
        ],
        "text_encoder": [
            "transformers",
            "CLIPTextModel"
        ],
        "tokenizer": [
            "transformers",
            "CLIPTokenizer"
        ],
        "unet": [
            "diffusers",
            "UNet2DConditionModel"
        ],
        "vae": [
            "diffusers",
            "AutoencoderKL"
        ]
    },
    "dtype_info": {
        "dtype": "float32"
    }
}

🌍 Join the Pruna AI community!