You're looking at a specific version of this model. Jump to the model overview.
zsxkib /instant-id-basic:449191dc
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 |
|---|---|---|---|
| image |
string
|
Input image for face reference
|
|
| prompt |
string
|
Cyberpunk character, neon lights, futuristic implants, urban dystopia, high contrast, young man
|
None
|
| negative_prompt |
string
|
NSFW, nudity, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured
|
None
|
| seed |
integer
|
Set a seed for reproducibility. Random by default.
|
|
| steps |
integer
|
30
Min: 1 Max: 50 |
Number of sampling steps
|
| cfg |
number
|
4.5
Min: 0.01 Max: 10 |
Classifier-free guidance scale
|
| sampler_name |
string
(enum)
|
ddpm
Options: euler, euler_ancestral, heun, heunpp2, dpm_2, dpm_2_ancestral, lms, dpm_fast, dpm_adaptive, dpmpp_2s_ancestral, dpmpp_sde, dpmpp_sde_gpu, dpmpp_2m, dpmpp_2m_sde, dpmpp_2m_sde_gpu, dpmpp_3m_sde, dpmpp_3m_sde_gpu, ddpm, lcm, ddim, uni_pc, uni_pc_bh2 |
Name of the sampler
|
| scheduler |
string
(enum)
|
karras
Options: normal, karras, exponential, sgm_uniform, simple, ddim_uniform |
Name of the scheduler
|
| denoise |
number
|
1
Max: 1 |
Denoising strength (recommended to keep at 1.0)
|
| width |
integer
|
1600
|
Width of the output image
|
| height |
integer
|
1600
|
Height of the output image
|
| batch_size |
integer
|
1
Min: 1 Max: 8 |
Batch size for generation (higher values may cause OOM errors with large width/height)
|
| instantid_weight |
number
|
0.6
Min: 0.01 Max: 2 |
Weight of the InstantID effect
|
| instantid_start_at |
number
|
0
Max: 1 |
Start point of InstantID effect
|
| instantid_end_at |
number
|
1
Max: 1 |
End point of InstantID effect
|
| ipadapter_weight |
number
|
0.7
Min: 0.01 Max: 2 |
Weight of the IPAdapter effect
|
| ipadapter_weight_type |
string
(enum)
|
linear
Options: linear, ease in, ease out, ease in-out, reverse in-out, weak input, weak output, weak middle, strong middle, style transfer, composition, strong style transfer, style and composition, style transfer precise |
Weight type for IPAdapter
|
| ipadapter_combine_embeds |
string
(enum)
|
average
Options: concat, add, subtract, average, norm average |
Method to combine embeddings in IPAdapter
|
| ipadapter_start_at |
number
|
0
Max: 1 |
Start point of IPAdapter effect
|
| ipadapter_end_at |
number
|
1
Max: 1 |
End point of IPAdapter effect
|
| ipadapter_embeds_scaling |
string
(enum)
|
V only
Options: V only, K+V, K+V w/ C penalty, K+mean(V) w/ C penalty |
Embeds scaling method for IPAdapter
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images
|
| output_quality |
integer
|
80
Max: 100 |
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
|
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',
'x-cog-array-type': 'iterator'}