falText to imageComing soon

fal-ai/lora

Name: fal-ai/lora
Brand: fal

fal-ai/lora is a text to image tool from fal that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: image
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`model_name` required	text	—	URL or HuggingFace ID of the base model to generate the image.
`unet_name`	text	—	URL or HuggingFace ID of the custom U-Net model to use for the image generation.
`variant`	text	—	The variant of the model to use for huggingface models, e.g. 'fp16'.
`prompt` required	text	—	The prompt to use for generating the image. Be as descriptive as possible for best results.
`negative_prompt`	text		The negative prompt to use.Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).
`prompt_weighting`	true or false	false	If set to true, the prompt weighting syntax will be used. Additionally, this will lift the 77 token limit by averaging embeddings.
`loras`	JSON	[]	The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.
`embeddings`	JSON	[]	The embeddings to use for the image generation. Only a single embedding is supported at the moment. The embeddings will be used to map the tokens in the prompt to the embedding weights.
`controlnets`	JSON	[]	The control nets to use for the image generation. You can use any number of control nets and they will be applied to the image at the specified timesteps.
`controlnet_guess_mode`	true or false	false	If set to true, the controlnet will be applied to only the conditional predictions.
`ip_adapter`	JSON	[]	IP adapters for image generation. A non-empty list requires image_encoder_path.
`image_encoder_path`	text	—	Hugging Face ID or HTTPS URL of the image encoder; required when ip_adapter is non-empty. Choose an encoder compatible with the IP-Adapter weights. For h94/IP-Adapter SDXL weights, use h94/IP-Adapter with image_encoder_subfolder='sdxl_models/image_encoder'; for SD1.5 weights, use image_encoder_subfolder='models/image_encoder'.
`image_encoder_subfolder`	text	—	Subfolder containing the image encoder weights in image_encoder_path.
`image_encoder_weight_name`	text	pytorch_model.bin	The weight name of the image encoder model to use for the image generation.
`ic_light_model_url`	text	—	The URL of the IC Light model to use for the image generation.
`ic_light_model_background_image_url`	text	—	The URL of the IC Light model background image to use for the image generation. Make sure to use a background compatible with the model.
`ic_light_image_url`	text	—	The URL of the IC Light model image to use for the image generation.
`seed`	number (whole)	—	The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.
`image_size`	JSON	square_hd	The size of the generated image. You can choose between some presets or custom height and width that must be multiples of 8.
`num_inference_steps`	number (whole) 1 to 150	30	Increasing the amount of steps tells Stable Diffusion that it should take more steps to generate your final result which can increase the amount of detail in your image.
`guidance_scale`	number 0 to 20	7.5	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.
`clip_skip`	number (whole) 0 to 2	0	Skips part of the image generation process, leading to slightly different results. This means the image renders faster, too.
`scheduler`	one of DPM++ 2M, DPM++ 2M Karras, DPM++ 2M SDE, DPM++ 2M SDE Karras, Euler, Euler A, Euler (trailing timesteps), LCM, LCM (trailing timesteps), DDIM, TCD	—	Scheduler / sampler to use for the image denoising process.
`timesteps`	JSON	{"array":[],"method":"default"}	Optionally override the timesteps to use for the denoising process. Only works with schedulers which support the `timesteps` argument in their `set_timesteps` method. Defaults to not overriding, in which case the scheduler automatically sets the timesteps based on the `num_inference_steps` parameter. If set to a custom timestep schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `sigmas` is set.
`sigmas`	JSON	{"array":[],"method":"default"}	Optionally override the sigmas to use for the denoising process. Only works with schedulers which support the `sigmas` argument in their `set_sigmas` method. Defaults to not overriding, in which case the scheduler automatically sets the sigmas based on the `num_inference_steps` parameter. If set to a custom sigma schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `timesteps` is set.
`prediction_type`	one of v_prediction, epsilon	epsilon	The type of prediction to use for the image generation. The `epsilon` is the default.
`rescale_betas_snr_zero`	true or false	false	Whether to set the rescale_betas_snr_zero option or not for the sampler
`image_format`	one of jpeg, png	png	The format of the generated image.
`num_images`	number (whole) 1 to 8	1	Number of images to generate in one request. Note that the higher the batch size, the longer it will take to generate the images.
`tile_width`	number (whole) 128 to 4096	4096	The size of the tiles to be used for the image generation.
`tile_height`	number (whole) 128 to 4096	4096	The size of the tiles to be used for the image generation.
`tile_stride_width`	number (whole) 64 to 2048	2048	The stride of the tiles to be used for the image generation.
`tile_stride_height`	number (whole) 64 to 2048	2048	The stride of the tiles to be used for the image generation.
`eta`	number 0 to 1	0	The eta value to be used for the image generation.
`debug_latents`	true or false	false	If set to true, the latents will be saved for debugging.
`debug_per_pass_latents`	true or false	false	If set to true, the latents will be saved for debugging per pass.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/lora",
    "input": {
      "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
      "prompt": "Photo of a european medieval 40 year old queen, silver hair, highly detailed face, detailed eyes, head shot, intricate crown, age spots, wrinkles"
    }
  }'