Image
Stable Diffusion with LoRAs
Generate images with a chosen Stable Diffusion base model and LoRA adapters.
- Text to image
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Stable Diffusion with LoRAs. Review your own result before publishing.
A starting point.
Use a compatible base and adapter for a particular character or style. Image-to-image and inpaint are separate operations.
Before you publish.
Check subject consistency and unwanted style spillover; inspect repaired edges when using inpaint.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
The default operation requires model_name and prompt. Add compatible loras and keep the base model fixed when comparing adapter weights.
Use image_url in image-to-image; supply the source and mask_url for inpaint. noise_strength belongs to those image operations, not the default text mode.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for lora. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
model_name | Text | Required | — |
prompt | Text | Required | — |
clip_skip | Whole number | Optional | ≥ 0 · ≤ 2 |
controlnet_guess_mode | On/off | Optional | — |
controlnets | List | Optional | — |
debug_latents | On/off | Optional | — |
debug_per_pass_latents | On/off | Optional | — |
embeddings | List | Optional | — |
enable_safety_checker | On/off | Optional | — |
eta | Number | Optional | ≥ 0 · ≤ 1 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
ic_light_image_url | Text | Optional | — |
ic_light_model_background_image_url | Text | Optional | — |
ic_light_model_url | Text | Optional | — |
image_encoder_path | Text | Optional | — |
image_encoder_subfolder | Text | Optional | — |
image_encoder_weight_name | Text | Optional | — |
image_format | Text | Optional | — |
ip_adapter | List | Optional | — |
loras | List | Optional | — |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 8 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 150 |
prediction_type | Text | Optional | — |
prompt_weighting | On/off | Optional | — |
rescale_betas_snr_zero | On/off | Optional | — |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
sigmas | Object | Optional | — |
tile_height | Whole number | Optional | ≥ 128 · ≤ 4096 |
tile_stride_height | Whole number | Optional | ≥ 64 · ≤ 2048 |
tile_stride_width | Whole number | Optional | ≥ 64 · ≤ 2048 |
Showing the first 32 of 36 inputs.
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
image-to-image (image-to-image)lora/image-to-image
Supported inputs
These fields come from the current studio form for lora/image-to-image. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
model_name | Text | Required | — |
prompt | Text | Required | — |
clip_skip | Whole number | Optional | ≥ 0 · ≤ 2 |
controlnet_guess_mode | On/off | Optional | — |
controlnets | List | Optional | — |
debug_latents | On/off | Optional | — |
debug_per_pass_latents | On/off | Optional | — |
embeddings | List | Optional | — |
enable_safety_checker | On/off | Optional | — |
eta | Number | Optional | ≥ 0 · ≤ 1 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
ic_light_image_url | Text | Optional | — |
ic_light_model_background_image_url | Text | Optional | — |
ic_light_model_url | Text | Optional | — |
image_encoder_path | Text | Optional | — |
image_encoder_subfolder | Text | Optional | — |
image_encoder_weight_name | Text | Optional | — |
image_format | Text | Optional | — |
image_url | Text | Optional | — |
ip_adapter | List | Optional | — |
loras | List | Optional | — |
negative_prompt | Text | Optional | — |
noise_strength | Number | Optional | ≤ 1 · > 0 |
num_images | Whole number | Optional | ≥ 1 · ≤ 8 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 150 |
prediction_type | Text | Optional | — |
prompt_weighting | On/off | Optional | — |
rescale_betas_snr_zero | On/off | Optional | — |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
sigmas | Object | Optional | — |
tile_height | Whole number | Optional | ≥ 128 · ≤ 4096 |
Showing the first 32 of 38 inputs.
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
image-to-image (inpaint)lora/inpaint
Supported inputs
These fields come from the current studio form for lora/inpaint. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
model_name | Text | Required | — |
prompt | Text | Required | — |
clip_skip | Whole number | Optional | ≥ 0 · ≤ 2 |
controlnet_guess_mode | On/off | Optional | — |
controlnets | List | Optional | — |
debug_latents | On/off | Optional | — |
debug_per_pass_latents | On/off | Optional | — |
embeddings | List | Optional | — |
enable_safety_checker | On/off | Optional | — |
eta | Number | Optional | ≥ 0 · ≤ 1 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
ic_light_image_url | Text | Optional | — |
ic_light_model_background_image_url | Text | Optional | — |
ic_light_model_url | Text | Optional | — |
image_encoder_path | Text | Optional | — |
image_encoder_subfolder | Text | Optional | — |
image_encoder_weight_name | Text | Optional | — |
image_format | Text | Optional | — |
image_url | Text | Optional | — |
ip_adapter | List | Optional | — |
loras | List | Optional | — |
mask_url | Text | Optional | — |
negative_prompt | Text | Optional | — |
noise_strength | Number | Optional | ≤ 1 · > 0 |
num_images | Whole number | Optional | ≥ 1 · ≤ 8 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 150 |
prediction_type | Text | Optional | — |
prompt_weighting | On/off | Optional | — |
rescale_betas_snr_zero | On/off | Optional | — |
scheduler | Text | Optional | — |
seed | Whole number | Optional | — |
sigmas | Object | Optional | — |
Showing the first 32 of 39 inputs.
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Stable Diffusion with LoRAs through the API.
Start with this model ID for the endpoint featured on this page:
lora
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-image ·
lora - image-to-image (image-to-image) ·
lora/image-to-image - image-to-image (inpaint) ·
lora/inpaint
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.