stabilityai-stable-diffusion-2-1 · azureml v5

This `stable-diffusion-2-1` model is fine-tuned from [stable-diffusion-2](https://huggingface.co/stabilityai/stable-diffusion-2) (`768-v-ema.ckpt`) with an additional 55k steps on the same dataset (w…

azureFoundry/azureml/stabilityai-stable-diffusion-2-1@5

This stable-diffusion-2-1 model is fine-tuned from stable-diffusion-2 (768-v-ema.ckpt) with an additional 55k steps on the same dataset (with punsafe=0.1), and then fine-tuned for another 155k extra steps with punsafe=0.98.

The model is intended for research purposes only. Possible research areas and tasks include

  • Safe deployment of models which have the potential to generate harmful content.
  • Probing and understanding the limitations and biases of generative models.
  • Generation of artworks and use in design and other artistic processes.
  • Applications in educational or creative tools.
  • Research on generative models.

Training Details

Training Data

The model developers used the following dataset for training the model:

  • LAION-5B and subsets (details below). The training data is further filtered using LAION's NSFW detector, with a "p_unsafe" score of 0.1 (conservative). For more details, please refer to LAI

Specifications & capabilities

Input
text
Output
image
Capabilities
imageOutput

Provider specifications & access

1–1 / 1

stabilityai-stable-diffusion-2-1 · azureml v5 ↗

source model id
azureml/stabilityai-stable-diffusion-2-1@5
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
creativeml-openrail++-m
architecture
input_modalities
  • text
output_modalities
  • image
capabilities

    Original sources

    1–3 / 3

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace