falImage to imageComing soon

fal-ai/telestyle-v2

Name: fal-ai/telestyle-v2
Brand: fal

fal-ai/telestyle-v2 is an image 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.

Priced by usage

Pricing

$0.0455 per megapixel. Each image_size preset counts as 1 MP, and a custom width × height rounds up to whole megapixels. Billed on num_images, default 1. The final charge comes from usage.

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
`content_image_url` required	text	—	URL of the content image — the image whose subject and structure are preserved while the style is applied.
`style_image_url` required	text	—	URL of the style reference image — the artistic style, material, lighting and color of this image are transferred onto the content image.
`lora_scale`	number 0 to 4	1	Strength of the TeleStyleV2 style adapter. 1.0 matches the reference implementation; lower values apply the style more subtly.
`use_lightning_lora`	true or false	true	If true, use the Lightning LoRA in addition to the default LoRA.
`lightning_lora_scale`	number 0 to 4	1	Strength of the Lightning LoRA. 1.0 matches the reference implementation; lower values apply the style more subtly.
`use_content_description`	true or false	true	If true, describe the content image with a VLM and add the description to the prompt.
`use_style_description`	true or false	true	If true, describe the style image with a VLM and add the description to the prompt.
`image_size`	JSON	—	The size of the generated image. If not provided, the size of the content image is used.
`negative_prompt`	text		The negative prompt for the generation.
`num_inference_steps`	number (whole) 2 to 50	4	The number of inference steps to perform.
`guidance_scale`	number 0 to 20	1	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.
`acceleration`	one of none, regular	none	Acceleration level for image generation. 'none' (the default) honors the requested num_inference_steps, so the default 4-step Lightning configuration runs in 4 steps. 'regular' engages the downstream accelerated path, which runs a fixed 10 steps regardless of num_inference_steps.
`num_images`	number (whole) 1 to 4	1	The number of images to generate.
`seed`	number (whole)	—	The same seed and the same inputs given to the same version of the model will output the same image every time.
`output_format`	one of jpeg, png	png	The format of the generated image.

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/telestyle-v2",
    "input": {
      "content_image_url": "https://v3.fal.media/files/monkey/i3saq4bAPXSIl08nZtq9P_ec535747aefc4e31943136a6d8587075.png",
      "style_image_url": "https://v3.fal.media/files/penguin/BCOZp6teRhSQFuOXpbBOa_da8ef9b4982347a2a62a516b737d4f21.png"
    }
  }'