Get a weekly rundown of the latest AI models and research... subscribe!

Dark Sushi Mix 225d


AI model preview image
The Dark Sushi Mix 2.25D model is an AI model that produces images based on text or visual prompts, having applications in both text-to-image and image-to-image translations. The model is trained to avoid undesirable outputs, such as disfigured, kitsch, or oversaturated images, through the use of a negative prompt. The output is an image file. The power (or strength) in reproducing the given inputs, the schedule for the representation process, and the guidance scale for the input prompts can be tweaked by the user. The model also uses Karras Sigmas for further image refinement.

Use cases

The Dark Sushi Mix 2.25D Model, powered by the vae-ft-mse-840000-ema technology, offers a wide range of potential use cases, particularly in digital art and design domains. Its capability to render 2.25D images based on the provided textual prompt positions it as a useful tool for graphic design, concept art, or advertising industries. With a significant emphasis on accurate depictions, the model can generate custom images such as a girl with specific features and attire located on a street. Its ability to understand 'negative prompts' helps avoid unwanted elements in the generated image. In a digital marketing context, for example, advertising agencies could harness this AI model to rapidly generate high-quality, custom visuals for their campaigns. In graphic design, designers might use the model to create novel concept art sets. The fashion industry could also use the model to visualize new clothing designs on various models and backgrounds. Entertainment industries could employ this model as a character design tool, or even to create entire scenes for video games or animation. Meanwhile, individual artists might use the model to bring their art ideas to life, perhaps even offering a service that reimagines customer descriptions or stories into personalized digital art. Lastly, in an educational setting, this model could be used to help teach art or design theory, by allowing students to manipulate different components of a scene, character, or outfit, and see a visual AI interpretation of their adjustments live.


Cost per run
Avg run time

Creator Models

Kandinsky 2.2$?553
Realistic Vision V4$?22,354
Realistic Vision V5.1 Inpainting$?749
Kandinsky 3.0$?93,688
Proteus V0.2$?4,225

Similar Models

No similar models found

Try it!

You can use this area to play around with demo applications that incorporate the Dark Sushi Mix 225d model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameDark Sushi Mix 225d
Dark Sushi Mix 2.25D Model with vae-ft-mse-840000-ema (Text2Img, Img2Img)
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-