You're looking at a specific version of this model. Jump to the model overview.
goodguy1963 /sdxl-finetunes-img2img:6cff2d9f
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 |
|---|---|---|---|
| input_image |
string
|
Input image for processing. If not provided, the default image will be used.
|
|
| prompt |
string
|
high quality, detailed, photorealistic, perfect eyes, bokeh, photo, perfect light, detailed style, depth of field
|
High quality modifiers to add to prompt
|
| negative_prompt |
string
|
ugly, deformed, soft, ext, watermark, abstract, big hands, fake, fake hands, distorted, drawing, painting, crayon, sketch, impressionist, worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed
|
Things you do not want to see in your image
|
| checkpoint_name |
string
(enum)
|
realismEngineSDXL_v30VAE.safetensors
Options: cyberrealisticXL_v5.safetensors, albedobaseXL_v31Large.safetensors, realDream_sdxl5.safetensors, realismEngineSDXL_v30VAE.safetensors, realvisxlV50_v50Bakedvae.safetensors |
Checkpoint model to use
|
| steps |
integer
|
50
Min: 1 Max: 100 |
Number of inference steps
|
| cfg |
number
|
7.5
Min: 1 Max: 20 |
Guidance scale
|
| denoise |
number
|
0.8
Max: 1 |
Denoising strength
|
| sampler_name |
string
(enum)
|
euler
Options: euler, euler_ancestral, heun, 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, ddim |
Sampling algorithm to use
|
| scheduler |
string
(enum)
|
karras
Options: normal, karras, exponential, sgm_uniform, simple, ddim_uniform |
Scheduler for the sampler
|
| lora1_strength_model |
number
|
1
Max: 2 |
LoRA 1 (product marketing) model strength
|
| lora1_strength_clip |
number
|
1
Max: 2 |
LoRA 1 (product marketing) clip strength
|
| lora2_strength_model |
number
|
2
Max: 2 |
LoRA 2 (add-detail-xl) model strength
|
| lora2_strength_clip |
number
|
1
Max: 2 |
LoRA 2 (add-detail-xl) clip strength
|
| lora3_strength_model |
number
|
1
Max: 2 |
LoRA 3 (detailed_notrigger) model strength
|
| lora3_strength_clip |
number
|
1
Max: 2 |
LoRA 3 (detailed_notrigger) clip strength
|
| ipadapter_weight |
number
|
0.9
Max: 1 |
IP-Adapter weight
|
| ipadapter_start_at |
number
|
0
Max: 1 |
IP-Adapter start at step percentage
|
| ipadapter_end_at |
number
|
1
Max: 1 |
IP-Adapter end at step percentage
|
| controlnet_strength |
number
|
1
Max: 2 |
ControlNet strength
|
| controlnet_start_percent |
number
|
0
Max: 1 |
ControlNet start percentage
|
| controlnet_end_percent |
number
|
0.5
Max: 1 |
ControlNet end percentage
|
| safety_filter |
boolean
|
True
|
Enable Replicate safety filter to detect and filter NSFW content (can't be disabled in web UI)
|
| width |
integer
|
1024
Min: 512 Max: 2048 |
Width of the image
|
| height |
integer
|
1024
Min: 512 Max: 2048 |
Height of the image
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images
|
| output_quality |
integer
|
95
Max: 100 |
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
|
| seed |
integer
|
Set a seed for reproducibility. Random by default.
|
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'}