This Stable Diffusion Turbo model has been optimized to work with WebNN. This model is licensed under the STABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT. For terms of use, please visit the Acceptable Use Policy. If you comply with the license and terms of use, you have the rights described therin. By using this Model, you accept the terms.
SD-Turbo-WebNN is meant to be used with the corresponding sample here (originally: here) for educational or testing purposes only.
WebNN changes
This original model is SD-Turbo. SD-Turbo-WebNN is an ONNX version of the SD-Turbo model that optimizes for WebNN by using static input shapes and eliminates operators that are not in use.
SD-Turbo Model Card
SD-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation.
We release SD-Turbo as a research artifact, and to study small, distilled text-to-image models. For increased quality and prompt understanding,
we recommend SDXL-Turbo.
SD-Turbo is a distilled version of Stable Diffusion 2.1, trained for real-time synthesis.
SD-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational
image diffusion models in 1 to 4 steps at high image quality.
This approach uses score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal and combines this with an
adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps.
For research purposes, we recommend our generative-models Github repository (https://github.com/Stability-AI/generative-models),
which implements the most popular diffusion frameworks (both training and inference).
SD-Turbo does not make use of guidance_scale or negative_prompt, we disable it with guidance_scale=0.0.
Preferably, the model generates images of size 512x512 but higher image sizes work as well.
A single step is enough to generate high quality images.
py
1from diffusers import AutoPipelineForText2Image
2import torch
34pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/sd-turbo", torch_dtype=torch.float16, variant="fp16")5pipe.to("cuda")67prompt ="A cinematic shot of a baby racoon wearing an intricate italian priest robe."8image = pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0.0).images[0]
Image-to-image:
When using SD-Turbo for image-to-image generation, make sure that num_inference_steps * strength is larger or equal
to 1. The image-to-image pipeline will run for int(num_inference_steps * strength) steps, e.g. 0.5 * 2.0 = 1 step in our example
below.
The model was not trained to be factual or true representations of people or events,
and therefore using the model to generate such content is out-of-scope for the abilities of this model.
The model should not be used in any way that violates Stability AI's Acceptable Use Policy.
Limitations and Bias
Limitations
The quality and prompt alignment is lower than that of SDXL-Turbo.
The generated images are of a fixed resolution (512x512 pix), and the model does not achieve perfect photorealism.
The model cannot render legible text.
Faces and people in general may not be generated properly.
The autoencoding part of the model is lossy.
Recommendations
The model is intended for both non-commercial and commercial usage.
