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

T2i Adapter Sdxl Depth Midas



The t2i-adapter-sdxl-depth-midas model is a system that modifies images based on depth maps. The model employs a type of conditioning, a process that affects the output of the model by manipulating input data. The input parameters to the model include the image URL, a descriptive prompt, scheduling settings, guidance scale, negative prompts, inferences steps, and conditioning factors. The output of the model consists of two URLs that lead to the modified image and the intermediates steps of the process, respectively. It is capable of creating photo-realistic images from prompts while avoiding certain undesired aspects mentioned in the "negative_prompt". The images generated are of high quality as specified in the initial prompt.

Use cases

The t2i-adapter-sdxl-depth-midas AI model is designed to refine images using depth maps. Therefore, there are numerous potential use cases in industries that utilize image manipulation and visual effects. For instance, in the film and gaming industry, this model could be utilized to generate more realistic graphics based on image depths. The model could also have applications in the real estate industry, where it can be used to enhance the quality of property images captured for marketing purposes, giving potential buyers a better understanding of depth and scale. Furthermore, this model might also be beneficial in automated driving systems, providing depth information to help vehicles navigate their environment more accurately. As for product development, the model could be integrated into photo editing software to introduce a new feature that optimizes images using depth data. Another potential product could be a mobile application designed to enhance personal photographs, thus offering its users the ability to capture images with professional quality. Additionally, the model could also be repurposed into a practical tool for professionals like architects, interior designers, or landscape artists who need to visualize and communicate spaces' depth and details.


Cost per run
Avg run time

Creator Models

Inst Inpaint$?251
T2i Adapter Sdxl Openpose$?4,645
Lightweight Openpose$?1,442

Similar Models

No similar models found

Try it!

You can use this area to play around with demo applications that incorporate the T2i Adapter Sdxl Depth Midas 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 NameT2i Adapter Sdxl Depth Midas
Modify images using depth maps
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


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-