You're looking at a specific version of this model. Jump to the model overview.
prompthunt /swap_mask:e098a7ad
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| weights |
string
|
Weights url
|
|
| control_image |
string
|
Optional Image to use for guidance based on posenet
|
|
| pose_image |
string
|
Direct Pose image to use for guidance based on posenet, if available, ignores control_image
|
|
| image |
string
|
Optional Image to use for img2img guidance
|
|
| mask |
string
|
Optional Mask to use for legacy inpainting
|
|
| prompt |
string
|
photo of cjw person
|
Input prompt
|
| negative_prompt |
string
|
|
Specify things to not see in the output. Supported embeddings: realisticvision-negative-embedding, cyberrealistic-neg, EasyNegative, FastNegativeV2, negative-hand, BadDream, UnrealisticDream, badhandv4
|
| width |
integer
|
512
|
Width of output image
|
| height |
integer
|
512
|
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 40 |
Number of images to output.
|
| num_inference_steps |
integer
|
50
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| prompt_strength |
number
|
0.8
Max: 1 |
Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
|
| pose_strength |
number
|
0.75
Max: 1 |
Pose strength
|
| scheduler |
string
(enum)
|
DPM++SDEKarras
Options: DDIM, DPMSolverMultistep, HeunDiscrete, K_EULER_ANCESTRAL, K_EULER, KLMS, PNDM, UniPCMultistep, KarrasDPM, DPM++SDEKarras |
Choose a scheduler.
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| source_image |
string
|
Source image for face swap
|
|
| show_debug_images |
boolean
|
False
|
Show debug images
|
| upscale_final_size |
integer
|
4
|
Upscale final size multiplier
|
| upscale_fidelity |
number
|
0.7
|
Upscale codeformer fidelity
|
| upscale_background_enhance |
boolean
|
True
|
Upscale background enhance
|
| upscale_face_upsample |
boolean
|
True
|
Upscale face upsample
|
| use_new_vae |
boolean
|
False
|
Use new vae
|
| second_pass_strength |
number
|
0.8
|
Second pass strength
|
| second_pass_guidance_scale |
number
|
3
|
Second pass guidance scale
|
| second_pass_steps |
integer
|
50
|
Second pass steps
|
| prompt_2 |
string
|
Input prompt
|
|
| prompt_3 |
string
|
Input prompt
|
|
| prompt_4 |
string
|
Input prompt
|
|
| pose_image_2 |
string
|
Direct Pose image to use for guidance based on posenet, if available, ignores control_image
|
|
| pose_image_3 |
string
|
Direct Pose image to use for guidance based on posenet, if available, ignores control_image
|
|
| pose_image_4 |
string
|
Direct Pose image to use for guidance based on posenet, if available, ignores control_image
|
|
| image_2 |
string
|
Optional Image to use for img2img guidance
|
|
| image_3 |
string
|
Optional Image to use for img2img guidance
|
|
| image_4 |
string
|
Optional Image to use for img2img guidance
|
|
| prompt_strength_2 |
number
|
0.8
Max: 1 |
Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
|
| prompt_strength_3 |
number
|
0.8
Max: 1 |
Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
|
| prompt_strength_4 |
number
|
0.8
Max: 1 |
Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
|
| source_image_2 |
string
|
Source image for face swap
|
|
| source_image_3 |
string
|
Source image for face swap
|
|
| source_image_4 |
string
|
Source image for face swap
|
|
| disable_cn_second_pass |
boolean
|
False
|
Disable controlnet second pass
|
| use_tile |
boolean
|
False
|
Use tile
|
| cf_acc_id |
string
|
Cloudflare account ID
|
|
| cf_api_key |
string
|
Cloudflare API key
|
|
| mask_blur_amount |
number
|
8
|
Amount of blur to apply to the mask.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'title': 'Output'}