You're looking at a specific version of this model. Jump to the model overview.
prompthunt /cog-sd15-inference-embeds:12edf3a9
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
|
LoRA weights to use. Leave blank to use the default weights.
|
|
| prompt |
string
|
An photo of cjw man
|
Input prompt
|
| negative_prompt |
string
|
|
Specify things to not see in the output. Supported embeddings: realisticvision-negative-embedding, EasyNegative, FastNegativeV2, BadDream, ng_deepnegative_v1_75t, UnrealisticDream, negative_hand-neg
|
| 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.
|
|
| width |
integer
|
512
|
Width of output image
|
| height |
integer
|
512
|
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of images to output.
|
| scheduler |
string
(enum)
|
K_EULER
Options: DDIM, DPMSolverMultistep, HeunDiscrete, DPM++SDEKarras, K_EULER_ANCESTRAL, K_EULER, PNDM |
scheduler
|
| 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 img2img / inpaint. 1.0 corresponds to full destruction of information in image
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| should_swap_face |
boolean
|
False
|
Should swap face
|
| source_image |
string
|
Source image for face swap
|
|
| refine |
string
(enum)
|
no_refiner
Options: no_refiner, expert_ensemble_refiner, base_image_refiner |
Which refine style to use
|
| high_noise_frac |
number
|
0.8
Max: 1 |
For expert_ensemble_refiner, the fraction of noise to use
|
| refine_steps |
integer
|
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
|
|
| disable_safety_checker |
boolean
|
True
|
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
|
| pose_image |
string
|
Pose image for controlnet
|
|
| controlnet_conditioning_scale |
number
|
0.75
Max: 4 |
How strong the controlnet conditioning is
|
| controlnet_start |
number
|
0
Max: 1 |
When controlnet conditioning starts
|
| controlnet_end |
number
|
1
Max: 1 |
When controlnet conditioning ends
|
| fix_face |
boolean
|
False
|
Fix the face in the image
|
| mask_blur_amount |
number
|
8
|
Amount of blur to apply to the mask.
|
| face_padding |
number
|
2
|
Amount of padding (as percentage) to add to the face bounding box.
|
| face_resize_to |
integer
|
512
|
Resize the face bounding box to this size (in pixels).
|
| upscale_face |
boolean
|
False
|
Upscale the face using GFPGAN
|
| inpaint_prompt |
string
|
A photo of cjw man
|
Input prompt
|
| inpaint_negative_prompt |
string
|
|
Input Negative Prompt
|
| inpaint_num_inference_steps |
integer
|
25
Min: 1 Max: 500 |
Number of denoising steps
|
| inpaint_guidance_scale |
number
|
3
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| inpaint_strength |
number
|
0.35
Max: 1 |
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
|
| inpaint_lora_scale |
number
|
0.6
Max: 1 |
LoRA additive scale. Only applicable on trained models.
|
| inpaint_controlnet_conditioning_scale |
number
|
0.75
Max: 4 |
How strong the controlnet conditioning is
|
| inpaint_controlnet_start |
number
|
0
Max: 1 |
When controlnet conditioning starts
|
| inpaint_controlnet_end |
number
|
1
Max: 1 |
When controlnet conditioning ends
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}