The "illusion" model is a Text-to-Image type AI developed by Monster Labs. It is based on the ControlNet on top of SD 1.5 and is designed to generate an image based on the given prompt while excluding characteristics listed in the negative prompt. Input parameters include image characteristics like seed, width, border, height, guidance scale, qr_code_content, and qrcode_background, as well as prompts. The output of the model is a URL leading to the generated image. The example shows that the model can generate medieval city street scenes as oil paintings, excluding features such as being ugly, disfigured, low-quality, blurry, or not safe for work.

Use cases

The "illusion" AI model developed by Monster Labs integrates the ControlNet system on top of SD 1.5, with the capacity to translate specific text-based prompts into detailed image outputs. In terms of potential use cases, the model could be utilized across a range of creative industries, such as in digital art creation, graphic design, or even more complex sectors such as film and gaming, specifically in the creation of scenery or background images. Another promising application could be in urban planning or architectural design, with the ability to visualize city streets, buildings, trees, and people, as the input schema suggests. Any profession or industry that requires image-based visualization could potentially benefit from the application of this model. The technology could also be developed into a product, such as a software application for professional designers, architects, or educators that require image creation from text-based descriptions. Overall, the practical uses of this model are far-reaching, offering significant potential for industries requiring detailed, high-resolution image creation from text inputs.



Cost per run
Avg run time

Creator Models

Llama 2 13b Embeddings$?172,645
Codellama 7b Instruct Gguf$?46
Llama 2 13b Chat Gguf$?1,352
Codellama 34b Instruct Gguf$?60
Llama 2 7b Embeddings$?30

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Illusion 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 NameIllusion
Monster Labs' control_v1p_sd15_qrcode_monster ControlNet on top of SD 1.5
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-