playgroundai/playground-v2.5-1024px-aesthetic
Playground v2.5 is the state-of-the-art open-source model in aesthetic quality
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
apply_watermark | boolean | Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking. | true | — |
disable_safety_checker | boolean | Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety | false | — |
guidance_scale | number | Scale for classifier-free guidance | 3 | min: 0.1, max: 20 |
height | integer | Height of output image | 1024 | min: 256, max: 1536 |
image | string(uri) | Input image for img2img or inpaint mode | — | — |
mask | string(uri) | Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted. | — | — |
negative_prompt | string | Negative Input prompt | "ugly, deformed, noisy, blurry, distorted" | — |
num_inference_steps | integer | Number of denoising steps | 25 | min: 1, max: 60 |
num_outputs | integer | Number of images to output. | 1 | min: 1, max: 4 |
prompt | string | Input prompt | "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" | — |
prompt_strength | number | Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image | 0.8 | min: 0, max: 1 |
scheduler | string | Scheduler. DPMSolver++ or DPM++2MKarras is recommended for most cases | "DPMSolver++" | DDIMDPMSolverMultistepHeunDiscreteK_EULER_ANCESTRALK_EULERPNDMDPM++2MKarrasDPMSolver++ |
seed | integer | Random seed. Leave blank to randomize the seed | — | — |
width | integer | Width of output image | 1024 | min: 256, max: 1536 |
apply_watermarkbooleanApplies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
truedisable_safety_checkerbooleanDisable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety
falseguidance_scalenumberScale for classifier-free guidance
3min: 0.1, max: 20heightintegerHeight of output image
1024min: 256, max: 1536imagestringInput image for img2img or inpaint mode
maskstringInput mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
negative_promptstringNegative Input prompt
"ugly, deformed, noisy, blurry, distorted"num_inference_stepsintegerNumber of denoising steps
25min: 1, max: 60num_outputsintegerNumber of images to output.
1min: 1, max: 4promptstringInput prompt
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"prompt_strengthnumberPrompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
0.8min: 0, max: 1schedulerstringScheduler. DPMSolver++ or DPM++2MKarras is recommended for most cases
"DPMSolver++"seedintegerRandom seed. Leave blank to randomize the seed
widthintegerWidth of output image
1024min: 256, max: 1536a45f82a1382bUpdated: 7/25/20263.0M runs
cinemasetfree.com