You're looking at a specific version of this model. Jump to the model overview.
prompthunt /cog-sd15-inference-embeds:6981eadf
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, CyberRealistic_Negative-neg, badhandv4
|
| root_prompt |
string
|
crisp details, neutral expression, high-definition, sharp focus, ambient lighting, masterpiece, cinematic light, cinematic lighting, ultrarealistic, photorealistic, 8k, raw photo, realistic, sharp focus on eyes, symmetrical eyes, intact eyes, hyperrealistic, highest quality, best quality, highly detailed, masterpiece, best quality, extremely detailed 8k wallpaper, masterpiece, best quality, ultra-detailed, best shadow, detailed background, detailed face, detailed eyes, high contrast, best illumination, detailed face, dulux, caustic, dynamic angle, detailed glow. dramatic lighting. highly detailed, insanely detailed hair, symmetrical, intricate details, professionally retouched, 8k high definition. strong bokeh. award winning photo.
|
Prompt added on top of every prediction
|
| root_negative_prompt |
string
|
old, multiple heads, 2 heads, elongated body, double image, 2 faces, multiple people, double head, <cyberrealistic-neg>, <badhandv4>, <negative-hand>, <baddream> , (nsfw), nsfw, nsfw, nsfw, nude, nude, nude, porn, porn, porn, naked, naked, nude, porn, frilly, frilled, lacy, ruffled, armpit hair, victorian, (sunglasses), (sunglasses), (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
|
Input prompt
|
| 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: 40 |
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
|
| inpaint_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
|
| show_debug_images |
boolean
|
False
|
Show debug images
|
| upscale_final_image |
boolean
|
False
|
Upscale the final image using GFPGAN
|
| upscale_scale |
number
|
2
|
Upscale scale
|
| codeformer_fidelity |
number
|
0.7
Max: 1 |
Codeformer fidelity
|
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'}