Image Upscaler by Each AI
Upscale images with advanced controls for creativity, resemblance, sharpening, and optional face/hand enhancement. Supports multiple Stable Diffusion base models and schedulers.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "each-upscaler",
"version": "0.0.1",
"input": {
"image": "https://example.com/low-res-photo.jpg",
"scale_factor": 2,
"creativity": 0.35,
"resemblance": 0.6,
"num_inference_steps": 18
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
| creativity |
number |
0.35 |
Creativity level, try from 0.3 - 0.9 |
| custom_sd_model |
string |
- |
Custom SD model URL |
| downscaling |
boolean |
false |
Downscale before upscaling. Can improve quality for large images |
| downscaling_resolution |
integer |
768 |
Downscaling resolution |
| dynamic |
number |
6 |
HDR effect, try from 3 - 9 |
| handfix |
string |
disabled |
Hand fixing mode. enum: disabled, hands_only, image_and_hands |
| image |
string |
- |
Input image |
| lora_links |
string |
- |
Link to LoRA file(s) for upscaling |
| mask |
string |
- |
Mask image to mark areas to preserve during upscaling |
| negative_prompt |
string |
(worst quality, low quality, normal quality:2)... |
Negative prompt |
| num_inference_steps |
integer |
18 |
Number of denoising steps |
| output_format |
string |
png |
Output format. enum: webp, jpg, png |
| pattern |
boolean |
false |
Upscale a pattern with seamless tiling |
| prompt |
string |
masterpiece, best quality, highres... |
Prompt |
| resemblance |
number |
0.6 |
Resemblance to original, try from 0.3 - 1.6 |
| scale_factor |
number |
2 |
Scale factor |
| scheduler |
string |
DPM++ 3M SDE Karras |
Scheduler. enum: DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Karras, Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM++ 2M SDE, DPM++ 2M SDE Heun, and more |
| sd_model |
string |
juggernaut_reborn.safetensors |
Base model. enum: epicrealism_naturalSinRC1VAE.safetensors, juggernaut_reborn.safetensors, flat2DAnimerge_v45Sharp.safetensors |
| seed |
integer |
1337 |
Random seed |
| sharpen |
number |
0 |
Sharpening intensity after upscaling |
| tiling_height |
integer |
144 |
Tiling height |
| tiling_width |
integer |
112 |
Tiling width |
Examples
High-quality portrait upscale with face fix:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "each-upscaler",
"version": "0.0.1",
"input": {
"image": "https://example.com/portrait.jpg",
"scale_factor": 2,
"creativity": 0.4,
"resemblance": 0.8,
"handfix": "image_and_hands",
"dynamic": 5,
"output_format": "png"
}
}'
Creative upscale with HDR:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "each-upscaler",
"version": "0.0.1",
"input": {
"image": "https://example.com/landscape.jpg",
"scale_factor": 4,
"creativity": 0.6,
"resemblance": 0.5,
"dynamic": 8,
"sharpen": 1.5,
"sd_model": "epicrealism_naturalSinRC1VAE.safetensors [84d76a0328]",
"num_inference_steps": 25
}
}'
Related Models
Documentation
1---2name: each-upscaler3description: Image Upscaler by Each AI | AI Image Upscaling. Upscale images with creativity and resemblance controls, face enhancement, and multiple SD models. Triggers: upscaler, upscale, image upscale, each upscaler, enhance image, super resolution4---56# Image Upscaler by Each AI78Upscale images with advanced controls for creativity, resemblance, sharpening, and optional face/hand enhancement. Supports multiple Stable Diffusion base models and schedulers.910## Quick Start1112> Requires an each::labs API key. Get one at [eachlabs.ai](https://eachlabs.ai).1314```bash15curl -X POST https://api.eachlabs.ai/v1/prediction \16 -H "Content-Type: application/json" \17 -H "X-API-Key: $EACHLABS_API_KEY" \18 -d '{19 "model": "each-upscaler",20 "version": "0.0.1",21 "input": {22 "image": "https://example.com/low-res-photo.jpg",23 "scale_factor": 2,24 "creativity": 0.35,25 "resemblance": 0.6,26 "num_inference_steps": 1827 }28 }'29```3031## Parameters3233| Parameter | Type | Default | Description |34|-----------|------|---------|-------------|35| creativity | number | 0.35 | Creativity level, try from 0.3 - 0.9 |36| custom_sd_model | string | - | Custom SD model URL |37| downscaling | boolean | false | Downscale before upscaling. Can improve quality for large images |38| downscaling_resolution | integer | 768 | Downscaling resolution |39| dynamic | number | 6 | HDR effect, try from 3 - 9 |40| handfix | string | disabled | Hand fixing mode. enum: disabled, hands_only, image_and_hands |41| image | string | - | Input image |42| lora_links | string | - | Link to LoRA file(s) for upscaling |43| mask | string | - | Mask image to mark areas to preserve during upscaling |44| negative_prompt | string | (worst quality, low quality, normal quality:2)... | Negative prompt |45| num_inference_steps | integer | 18 | Number of denoising steps |46| output_format | string | png | Output format. enum: webp, jpg, png |47| pattern | boolean | false | Upscale a pattern with seamless tiling |48| prompt | string | masterpiece, best quality, highres... | Prompt |49| resemblance | number | 0.6 | Resemblance to original, try from 0.3 - 1.6 |50| scale_factor | number | 2 | Scale factor |51| scheduler | string | DPM++ 3M SDE Karras | Scheduler. enum: DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Karras, Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM++ 2M SDE, DPM++ 2M SDE Heun, and more |52| sd_model | string | juggernaut_reborn.safetensors | Base model. enum: epicrealism_naturalSinRC1VAE.safetensors, juggernaut_reborn.safetensors, flat2DAnimerge_v45Sharp.safetensors |53| seed | integer | 1337 | Random seed |54| sharpen | number | 0 | Sharpening intensity after upscaling |55| tiling_height | integer | 144 | Tiling height |56| tiling_width | integer | 112 | Tiling width |5758## Examples5960**High-quality portrait upscale with face fix:**61```bash62curl -X POST https://api.eachlabs.ai/v1/prediction \63 -H "Content-Type: application/json" \64 -H "X-API-Key: $EACHLABS_API_KEY" \65 -d '{66 "model": "each-upscaler",67 "version": "0.0.1",68 "input": {69 "image": "https://example.com/portrait.jpg",70 "scale_factor": 2,71 "creativity": 0.4,72 "resemblance": 0.8,73 "handfix": "image_and_hands",74 "dynamic": 5,75 "output_format": "png"76 }77 }'78```7980**Creative upscale with HDR:**81```bash82curl -X POST https://api.eachlabs.ai/v1/prediction \83 -H "Content-Type: application/json" \84 -H "X-API-Key: $EACHLABS_API_KEY" \85 -d '{86 "model": "each-upscaler",87 "version": "0.0.1",88 "input": {89 "image": "https://example.com/landscape.jpg",90 "scale_factor": 4,91 "creativity": 0.6,92 "resemblance": 0.5,93 "dynamic": 8,94 "sharpen": 1.5,95 "sd_model": "epicrealism_naturalSinRC1VAE.safetensors [84d76a0328]",96 "num_inference_steps": 2597 }98 }'99```100101## Related Models102103- [real-esrgan](../real-esrgan/) - Real-ESRGAN face enhancer and upscaler104- [real-esrgan-a100](../real-esrgan-a100/) - Fast face enhancement105- [gfpgan](../gfpgan/) - GFPGAN face restoration106107## Documentation108109- [each::labs Docs](https://docs.eachlabs.ai)110- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia