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

Latent Consistency Model



The Latent Consistency Model (LCM) is a super-fast text-to-image AI model that takes around 0.6 seconds per image. The model uses an image URL and other parameters such as image size and text prompts to generate an output image according to the provided prompt - for instance, based on the text "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k". The model also allows for finer control over its output with several customizable options, such as the amount of guidance provided to the model, the sizing strategy, and the image inference steps. The output of the model is an image URL where the resultant image is hosted.

Use cases

The latent-consistency-model (LCM) is an AI model that converts text to image, capable of generating an image in as fast as 0.6s. It has several practical applications, which can be utilized in numerous industries. For instance, in the art industry, by inputting a description of an artwork, such as "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k," this model can generate a digitized artistic illustration consistent with the input prompt. With its super-fast image generation capability, this model can be a tool for concept artists, illustrators, and graphic designers in visualizing their ideas quickly. In addition, with its img2img and canny controlnet features, the model can assist in large batch image processing, potentially finding utility in the production of animation or films where rapid generation of digitized images based on given prompts is crucial. The model could also be integrated into products engaged in the creation of customizable merchandise where consumers provide specific image descriptions they want to be produced as the design. Finally, in education, the LCM model could be utilized in producing visual aids based on teachers' descriptions, hence, enriching the learning materials available for students.



Cost per run
Avg run time

Creator Models

Sdxl Santa Hat$?475
Star Trek Adventure$0.0483154
Sdxl Dots$?167
Sdxl Cats Movie$?479
Sdxl Barbietron$?1,285

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Latent Consistency Model 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 NameLatent Consistency Model

Super-fast, 0.6s per image. LCM with img2img, large batching and canny cont...

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-