Skip to main content

friendli api text-to-image create


friendli api text-to-image create [OPTIONS]


Create image from text.


--model, -mTEXTThe model to use for chat completions. See for more about available models and pricing.-
--prompt, -pTEXTA text description of the desired image(s).-
--negative-prompt, -NTEXTA text specifying what you don't want in your image(s).None
--num-outputs, -nINTEGER RANGEThe number of images to generate. Only 1 output will be generated when not provided.None
--num-inference-steps, -IINTEGER RANGEThe number of inference steps for denoising process. 50 steps will be taken when not provided.None
--guidance-scale, -GFLOATGuidance scale to control how much generation process adheres to the text prompt. When not provided, it is set to 7.5.None
--seed, -sINTEGERSeed to control random procedure.None
--response-format, -RCHOICE: [url, png, jpeg, raw]The format in which the generated images are returned.ResponseFormat.URL
--token, -tTEXTPersonal access token for auth.None
--team-idTEXTID of team to run as.None