friendli api text-to-image create
Usage
friendli api text-to-image create [OPTIONS]
Summary
Create image from text.
Options
Option | Type | Summary | Default | Required |
---|---|---|---|---|
--model , -m | TEXT | The model to use for chat completions. See https://docs.friendli.ai/guides/serverless_endpoints/pricing for more about available models and pricing. | - | ✅ |
--prompt , -p | TEXT | A text description of the desired image(s). | - | ✅ |
--negative-prompt , -N | TEXT | A text specifying what you don't want in your image(s). | None | ❌ |
--num-outputs , -n | INTEGER RANGE | The number of images to generate. Only 1 output will be generated when not provided. | None | ❌ |
--num-inference-steps , -I | INTEGER RANGE | The number of inference steps for denoising process. 50 steps will be taken when not provided. | None | ❌ |
--guidance-scale , -G | FLOAT | Guidance scale to control how much generation process adheres to the text prompt. When not provided, it is set to 7.5. | None | ❌ |
--seed , -s | INTEGER | Seed to control random procedure. | None | ❌ |
--response-format , -R | CHOICE: [url, png, jpeg, raw] | The format in which the generated images are returned. | ResponseFormat.URL | ❌ |
--token , -t | TEXT | Personal access token for auth. | None | ❌ |
--team-id | TEXT | ID of team to run as. | None | ❌ |