You're looking at a specific version of this model. Jump to the model overview.

zelenioncode /dreambooth_sdxl:e76c3569

Input

string

Gender of person in training photo ( woman or man )

Default: "woman"

string
Shift + Return to add a new line

Give name for your .safetensors model

Default: "Dreambooth_sdxl"

boolean

Send folder have .safetensors model direct to your huggingface account

Default: false

string
Shift + Return to add a new line

If you use huggingface, enter your API TOKEN

Default: "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"

string
Shift + Return to add a new line

If you use huggingface, enter repo_id to one of your project

Default: "WGlint/SafetensorsFromReplicate"

string
Shift + Return to add a new line

Enter a path to download your .safetensors model. Default = ./

Default: ""

string
Shift + Return to add a new line

Direct link download with training picture (Only .zip file and picture in 1024px/1024px !)

Default: "https://huggingface.co/WGlint/SafetensorsFromReplicate/resolve/main/input.zip"

integer
(minimum: 1, maximum: 1000)

Repeat of time GPU look training data ( e.g. 15 pictures * 100 repeat = 1500 steps )

Default: 100

boolean

Use regulat classification picture

Default: false

integer
(minimum: 1, maximum: 1000)

Repeat of time GPU look class reg picture ( e.g. 5000 pictures * 2 repeat = 10000 steps cache latents )

Default: 1

string
Shift + Return to add a new line

Direct link download for regular classification picture ( Default = class image of gender you use )

Default: ""

string

Choice a model pretrained can run for SDXL training with dreambooth

Default: "Stable Diffusion XL"

integer
(minimum: 1, maximum: 10)

Number CPU thread use with accelerate module

Default: 4

string
Shift + Return to add a new line

Resolution of your training picture data. WARNING ! Write in this formet : width,height ( e.g. 1024,1024 )

Default: "1024,1024"

string
Shift + Return to add a new line

VAE use for create model training

Default: "stabilityai/vae"

integer
(minimum: 1, maximum: 1000)

Num learning rate cycles for your training

Default: 1

integer
(minimum: 0, maximum: 100)

Maximun data loader for n workers you set

Default: 0

number

Value for learning_rate te1

Default: 0.00001

number

Value for learning_rate te2

Default: 0.00001

number

Value for learning_rate

Default: 0.00001

string

Method use for learning rate scheduler

Default: "constant"

integer
(minimum: 1, maximum: 64)

Select value for device max train step and speed the generation, WARINING ! High value = High value to have CUDA Memory

Default: 1

integer
(minimum: 100, maximum: 25000)

Number of step you want for your training, and in average 1000 steps = 10 minutes

Default: 2600

integer
(minimum: 1, maximum: 64)

Number of epochs model you want

Default: 1

string

Select if you want to use miwed precision

Default: "fp16"

string

Select if you want to use save precision

Default: "fp16"

string

Select a optimiser type

Default: "AdaFactor"

boolean

Use scale parameter

Default: false

boolean

Use relative step

Default: false

boolean

Use warmup init

Default: false

number

Give a float value for weight decay

Default: 0.01

integer
(minimum: 1, maximum: 1000)

Give a int value for bucket reso steps

Default: 64

integer
(minimum: 1, maximum: 5)

Number of .safetensors model you want, if you select 2 with 2000 max train steps, you well get 2 .safetensors. 1 with 1000 steps and 1 with 2000 steps

Default: 1

number

Give a float value for noise offset

Default: 0

number

Give a float value for max grad norm

Default: 0

boolean

Default: true

boolean

Default: true

boolean

Default: true

boolean

Default: true

boolean

Default: true

boolean

Default: true

boolean

Default: true

boolean

Default: true

boolean

Default: true

number

value for learning rate te1 bool

Default: 0.000003

number

value for learning rate te2 bool

Default: 0

Output

No output yet! Press "Submit" to start a prediction.