FLUX HF LoRA
Generate images using LoRA models with FLUX HF LoRA. Supports multiple aspect ratios (1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21), reproducible results via seed.
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": "flux-hf-lora",
"version": "0.0.1",
"input": {
"prompt": "A photorealistic portrait of a woman in a garden",
"hf_lora": "alvdansen/frosting_lane_flux"
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
aspect_ratio |
string |
1:1 |
An enumeration.. Options: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |
disable_safety_checker |
boolean |
True |
Disable safety checker for generated images. This feature is only available thro |
guidance_scale |
number |
3.5 |
Guidance scale for the diffusion process |
hf_lora |
string |
|
HF, Replicate, CivitAI, or URL to a LoRA. Ex: alvdansen/frosting_lane_flux |
image |
string |
|
Input image for image to image mode. The aspect ratio of your output will match |
lora_scale |
number |
0.8 |
Scale for the LoRA weights |
num_inference_steps |
integer |
28 |
Number of inference steps |
num_outputs |
integer |
1 |
Number of images to output. |
output_format |
string |
webp |
An enumeration.. Options: webp, jpg, png |
output_quality |
integer |
80 |
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is |
prompt |
string |
|
Prompt for generated image |
prompt_strength |
number |
0.8 |
Prompt strength (or denoising strength) when using image to image. 1.0 correspon |
seed |
integer |
|
Random seed. Set for reproducible generation |
Examples
Generate with LoRA:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-hf-lora",
"version": "0.0.1",
"input": {
"prompt": "A photorealistic portrait of a woman in a garden",
"hf_lora": "alvdansen/frosting_lane_flux"
}
}'
LoRA with custom settings:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-hf-lora",
"version": "0.0.1",
"input": {
"prompt": "A fantasy landscape with crystalline structures",
"hf_lora": "example/fantasy-lora",
"lora_scale": 0.8,
"guidance_scale": 4.0,
"seed": 42
}
}'
Documentation
1---2name: flux-hf-lora3description: FLUX HF LoRA. Generate images using LoRA models with FLUX HF LoRA. Triggers: flux, image generation, lora4---56# FLUX HF LoRA78Generate images using LoRA models with FLUX HF LoRA. Supports multiple aspect ratios (1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21), reproducible results via seed.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": "flux-hf-lora",20 "version": "0.0.1",21 "input": {22 "prompt": "A photorealistic portrait of a woman in a garden",23 "hf_lora": "alvdansen/frosting_lane_flux"24 }25 }'26```2728## Parameters2930| Parameter | Type | Default | Description |31|-----------|------|---------|-------------|32| `aspect_ratio` | string | 1:1 | An enumeration.. Options: `1:1`, `16:9`, `21:9`, `3:2`, `2:3`, `4:5`, `5:4`, `3:4`, `4:3`, `9:16`, `9:21` |33| `disable_safety_checker` | boolean | True | Disable safety checker for generated images. This feature is only available thro |34| `guidance_scale` | number | 3.5 | Guidance scale for the diffusion process |35| `hf_lora` | string | | HF, Replicate, CivitAI, or URL to a LoRA. Ex: alvdansen/frosting_lane_flux |36| `image` | string | | Input image for image to image mode. The aspect ratio of your output will match |37| `lora_scale` | number | 0.8 | Scale for the LoRA weights |38| `num_inference_steps` | integer | 28 | Number of inference steps |39| `num_outputs` | integer | 1 | Number of images to output. |40| `output_format` | string | webp | An enumeration.. Options: `webp`, `jpg`, `png` |41| `output_quality` | integer | 80 | Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is |42| `prompt` | string | | Prompt for generated image |43| `prompt_strength` | number | 0.8 | Prompt strength (or denoising strength) when using image to image. 1.0 correspon |44| `seed` | integer | | Random seed. Set for reproducible generation |4546## Examples4748**Generate with LoRA:**49```bash50curl -X POST https://api.eachlabs.ai/v1/prediction \51 -H "Content-Type: application/json" \52 -H "X-API-Key: $EACHLABS_API_KEY" \53 -d '{54 "model": "flux-hf-lora",55 "version": "0.0.1",56 "input": {57 "prompt": "A photorealistic portrait of a woman in a garden",58 "hf_lora": "alvdansen/frosting_lane_flux"59 }60 }'61```6263**LoRA with custom settings:**64```bash65curl -X POST https://api.eachlabs.ai/v1/prediction \66 -H "Content-Type: application/json" \67 -H "X-API-Key: $EACHLABS_API_KEY" \68 -d '{69 "model": "flux-hf-lora",70 "version": "0.0.1",71 "input": {72 "prompt": "A fantasy landscape with crystalline structures",73 "hf_lora": "example/fantasy-lora",74 "lora_scale": 0.8,75 "guidance_scale": 4.0,76 "seed": 4277 }78 }'79```8081## Documentation8283- [each::labs Docs](https://docs.eachlabs.ai)84- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia