> ## Content Index
> Fetch the complete content index at: https://hyperallergic.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# This Wacky AI Tool Will Finish Your Artwork for You
- URL: https://hyperallergic.com/stable-diffusion-ai-image-generator/
- Published: 2022-10-19T21:31:57.000Z
- Updated: 2025-11-24T16:21:07.000Z
- Description: In the latest twist in the saga of AI image generation, Stable Diffusion’s “Diffuse the Rest” will turn any sketch into a finished work.
- Author: Elaine Velie
- Tags: News, Artificial Intelligence, Stable Diffusion, #wp, #wp-post, #image-position-hidden, #Import 2025-11-24 09:22 (2021, 2022, part 2)

Artificial intelligence (AI) image generators have been quite busy lately, from producing [spooky art](https://hyperallergic.com/the-ai-halloween-art-of-your-nightmares-is-here/), [strange videos](https://hyperallergic.com/meta-launched-an-ai-video-generator-and-its-creepy/), and a terrifying creation called "[Loab](https://hyperallergic.com/loab-the-internets-latest-urban-legend-is-worse-than-anything/)" to helping a Colorado artist [win a blue ribbon](https://hyperallergic.com/ai-beats-out-human-artists-at-art-competition/) at the state fair this summer.

Generators like Midjourney and [DALL-E](https://hyperallergic.com/new-ai-artist-who-can-draw-anything/) normally use text prompts — along with their vast encyclopedias of imagery from the Internet — to formulate results. Now, Stable Diffusion's AI allows users to create images from other pictures, drawn on the spot. That's right: Input your napkin doodles and half-sketched masterpieces and AI will produce a complete image. (Well, sort of.)

[Stable Diffusion](https://stability.ai/blog/stable-diffusion-public-release?ref=hyperallergic.com) is an open-AI platform, meaning that users can manipulate and change the code to achieve their desired results. One of those projects, called "[Diffuse the Rest](https://huggingface.co/spaces/huggingface-projects/diffuse-the-rest?ref=hyperallergic.com)," adds action, detail, and stylization to drawings and uploaded pictures. The tool is based on the work of [Suraj Patil](https://twitter.com/psuraj28?ref=hyperallergic.com) and comprises a set of collaboratively-created GitHub [code](https://colab.research.google.com/github/patil-suraj/Notebooks/blob/master/image%5F2%5Fimage%5Fusing%5Fdiffusers.ipynb?ref=hyperallergic.com#scrollTo=DQ11k9JVIXII). (Stable Diffusion's own beta program, called "[Dreamstudio](https://beta.dreamstudio.ai/dream?ref=hyperallergic.com)," also includes an image-to-image generator, but there is no drawing option.)

Users can draw or upload an image and then add a text prompt. In one example, Stable Diffusion turned a bad drawing of a horse into a better one, and following the text prompt "galloping," placed the new rendering in motion.

![](https://storage.ghost.io/c/51/f8/51f871d8-b6be-4a73-b958-0ca4fff0110a/content/images/hyperallergic-newspack-s3-amazonaws-com/uploads/2022/10/screen-shot-2022-10-19-at-2-35-52-pm-edited.jpg)

Stable Infusion added the Loch Ness monster to a regular image of the lake. (original photo by Jon Roberts via [Flickr](https://www.flickr.com/photos/jon%5Froberts/31970141161/in/photolist-QH6k9n-jn9u9K-25Yhzq7-nN1iwZ-2b2ixMN-qjbAVu-6e5FoY-umDwW-d4X6yU-RxZZjw-aB3VnV-8TX5CJ-8zBCve-2TtGNX-8ph1Y2-ZK5SF1-umMUX-crXQAJ-9QEgSb-sz6Vm-DwfZ1r-Ui5vba-fCjRND-fCjRaV-ajfxe3-dEM22v-JekLhV-wKtEB-wKuxP-wKsEz-5g7RW2-2mDCk5B-2cGjz78-2nvSnf6-vTuGmk-2nvSn1i-s4epew-3m2AU-cDLmdo-Xz9oro-uSLNw9-4D2Yo3-5evUL2-5d4B66-8CUJsq-7Wg76R-7dmYVt-5EdgWj-5kX7Qa-7dqQg5?ref=hyperallergic.com))

We also fed Diffuse the Rest an image of a stormy Loch Ness Lake in Scotland, and following the simple text prompt "Loch Ness monster," the generator added the storied creature to the photograph. Pairing the prompt "style of Picasso" with theMona Lisa also produced realistic results.

![](https://storage.ghost.io/c/51/f8/51f871d8-b6be-4a73-b958-0ca4fff0110a/content/images/hyperallergic-newspack-s3-amazonaws-com/uploads/2022/10/screen-shot-2022-10-19-at-4-34-33-pm.jpg)

The prompt "style of Picasso" with a photograph of the Mona Lisa

In a [video](https://www.tiktok.com/@%5Ferichu/video/7135947571675008298?is%5Fcopy%5Furl=1&is%5Ffrom%5Fwebapp=v1&ref=hyperallergic.com), TikTok user Eric Hu explains the new feature and its potential application for design. He shows a sketch of a dog transformed into an impressive illustration, then a plug-in that turns a sketch of sneakers into a 3D-modeled illustration that looks ready to shop. Created by Antonio Cao, who posted the sneaker demo on [Twitter](https://twitter.com/RemitNotPaucity/status/1562319004563173376?ref=hyperallergic.com), the plug-in is for design software Figma and utilizes the Stable Diffusion AI.

https://www.tiktok.com/@\_erichu/video/7135947571675008298

Using the Diffuse the Rest generator, a photograph of a sailboat coupled with the prompt "whales jumping" created a very strange image ofwhales flying through the sky like seagulls. Just like DALL-E, Stable Diffusion isn't perfect, but it's a fascinating example of the way in which AI is evolving to create increasingly sophisticated — and increasingly bizarre — content.

![](https://storage.ghost.io/c/51/f8/51f871d8-b6be-4a73-b958-0ca4fff0110a/content/images/hyperallergic-newspack-s3-amazonaws-com/uploads/2022/10/screen-shot-2022-10-19-at-2-01-45-pm-edited.jpg)

The generator couldn't create a perfect image of "whale jumping."