cinemasetfree.com
datacte/proteus-v0.3
ProteusV0.3: The Anime Update
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. Recommended 7-8 | 7.5 | min: 1, max: 50 |
height | integer | Height of output image. Recommended 1024 or 1280 | 1024 | — |
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 | "worst quality, low quality" | — |
num_inference_steps | integer | Number of denoising steps. 20 to 60 steps for more detail, 20 steps for faster results. | 20 | min: 1, max: 100 |
num_outputs | integer | Number of images to output. | 1 | min: 1, max: 4 |
prompt | string | Input prompt | "Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)" | — |
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 | "DPM++2MSDE" | DDIM DPMSolverMultistep HeunDiscrete KarrasDPM K_EULER_ANCESTRAL K_EULER PNDM DPM++2MSDE |
seed | integer | Random seed. Leave blank to randomize the seed | — | — |
width | integer | Width of output image. Recommended 1024 or 1280 | 1024 | — |
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. Recommended 7-8
7.5 min: 1, max: 50 height integer Height of output image. Recommended 1024 or 1280
1024 image string Input image for img2img or inpaint mode
mask string Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
negative_prompt string Negative Input prompt
"worst quality, low quality" num_inference_steps integer Number of denoising steps. 20 to 60 steps for more detail, 20 steps for faster results.
20 min: 1, max: 100 num_outputs integer Number of images to output.
1 min: 1, max: 4 prompt string Input prompt
"Anime full body portrait of a swordsman holding his weapon in front of him. He is facing the camera with a fierce look on his face. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)" 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
"DPM++2MSDE" seed integer Random seed. Leave blank to randomize the seed
width integer Width of output image. Recommended 1024 or 1280
1024 b28b79d725c8 Updated: 2/26/2026 5.4M runs