bytedance/flux-pulid

⚡️FLUX PuLID: FLUX-dev based Pure and Lightning ID Customization via Contrastive Alignment🎭

Capabilities

1:14:33:416:99:162:33:2Negative PromptSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`main_face_image`*	string(uri)	Upload an ID image for face generation	`—`	—
`guidance_scale`	number	Set the guidance scale for text prompt influence (1.0-10.0)	`4`	min: 1, max: 10
`height`	integer	Set the height of the generated image (256-1536 pixels)	`1152`	min: 256, max: 1536
`id_weight`	number	Set the weight of the ID image influence (0.0-3.0)	`1`	min: 0, max: 3
`max_sequence_length`	integer	Set the max sequence length for prompt (T5), smaller is faster (128-512)	`128`	min: 128, max: 512
`negative_prompt`	string	Enter a negative prompt to specify what to avoid in the image	`"bad quality, worst quality, text, signature, watermark, extra limbs, low resolution, partially rendered objects, deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed, blurry"`	—
`num_outputs`	integer	Set the number of images to generate (1-4)	`1`	min: 1, max: 4
`num_steps`	integer	Set the number of denoising steps (1-20)	`20`	min: 1, max: 20
`output_format`	string	Choose the format of the output image	`"webp"`	pngjpgwebp
`output_quality`	integer	Set the quality of the output image for jpg and webp (1-100)	`80`	min: 1, max: 100
`prompt`	string	Enter a text prompt to guide image generation	`"portrait, color, cinematic"`	—
`seed`	integer	Set a random seed for generation (leave blank or -1 for random)	`—`	—
`start_step`	integer	Set the timestep to start inserting ID (0-4 recommended, 0 for highest fidelity, 4 for more editability)	`0`	min: 0, max: 10
`true_cfg`	number	Set the Classifier-Free Guidance (CFG) scale. 1.0 uses standard CFG, while values >1.0 enable True CFG for more precise control over generation. Higher values increase adherence to the prompt at the cost of image quality.	`1`	min: 1, max: 10
`width`	integer	Set the width of the generated image (256-1536 pixels)	`896`	min: 256, max: 1536

main_face_imagerequiredstring

Upload an ID image for face generation

guidance_scalenumber

Set the guidance scale for text prompt influence (1.0-10.0)

Default: 4min: 1, max: 10

heightinteger

Set the height of the generated image (256-1536 pixels)

Default: 1152min: 256, max: 1536

id_weightnumber

Set the weight of the ID image influence (0.0-3.0)

Default: 1min: 0, max: 3

max_sequence_lengthinteger

Set the max sequence length for prompt (T5), smaller is faster (128-512)

Default: 128min: 128, max: 512

negative_promptstring

Enter a negative prompt to specify what to avoid in the image

Default:

"bad quality, worst quality, text, signature, watermark, extra limbs, low resolution, partially rendered objects, deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed, blurry"

num_outputsinteger

Set the number of images to generate (1-4)

Default: 1min: 1, max: 4

num_stepsinteger

Set the number of denoising steps (1-20)

Default: 20min: 1, max: 20

output_formatstring

Choose the format of the output image

Default: "webp"

pngjpgwebp

output_qualityinteger

Set the quality of the output image for jpg and webp (1-100)

Default: 80min: 1, max: 100

promptstring

Enter a text prompt to guide image generation

Default: "portrait, color, cinematic"

seedinteger

Set a random seed for generation (leave blank or -1 for random)

start_stepinteger

Set the timestep to start inserting ID (0-4 recommended, 0 for highest fidelity, 4 for more editability)

Default: 0min: 0, max: 10

true_cfgnumber

Set the Classifier-Free Guidance (CFG) scale. 1.0 uses standard CFG, while values >1.0 enable True CFG for more precise control over generation. Higher values increase adherence to the prompt at the cost of image quality.

Default: 1min: 1, max: 10

widthinteger

Set the width of the generated image (256-1536 pixels)

Default: 896min: 256, max: 1536

Version: 8baa7ef22550Updated: 7/25/20262.5M runs