jyoung105 / lcm

Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference

  • Public
  • 124 runs
  • L40S
  • GitHub
  • Weights
  • Paper
  • License

Input

string
Shift + Return to add a new line

Input prompt, text of what you want to generate.

string
Shift + Return to add a new line

Input negative prompt, text of what you don't want to generate.

integer
(minimum: 1, maximum: 2048)

Width of the output image.

Default: 1024

integer
(minimum: 1, maximum: 2048)

Height of the output image.

Default: 1024

integer
(minimum: 1, maximum: 4)

Number of output images.

Default: 1

integer
(minimum: 1, maximum: 50)

Number of denoising steps.

Default: 4

number
(minimum: 0, maximum: 1)

Stochastic parameter to control the randomness.

Default: 0

number
(minimum: 0, maximum: 20)

Scale for classifier-free guidance.

Default: 0

integer

Random seed. Leave blank to randomize the seed.

integer

Number of the layers to skip in CLIP.

Default: 0

Output

output
Generated in

This output was created using a different version of the model, jyoung105/lcm:1eccb313.

Run time and cost

This model costs approximately $0.0045 to run on Replicate, or 222 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 5 seconds.

Readme

Latent Consistency Models

Official Repository of the paper: Latent Consistency Models. Project Page: https://latent-consistency-models.github.io

Try our Hugging Face demos:

Hugging Face Spaces

Model Descriptions:

Distilled from Dreamshaper v7 fine-tune of Stable-Diffusion v1-5 with only 4,000 training iterations (~32 A100 GPU Hours).

BibTeX

@misc{luo2023latent,
      title={Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference}, 
      author={Simian Luo and Yiqin Tan and Longbo Huang and Jian Li and Hang Zhao},
      year={2023},
      eprint={2310.04378},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}