vetkastar/stable_diffusion_control_photo_epic – Run with an API on Replicate

vetkastar / stable_diffusion_control_photo_epic

Cold

Public
17.4K runs
L40S

Run with an API

Playground API Examples README Versions

Input

generation_type

string

Generation mode

Default: "txt2img"

clip_stop_at_last_layers

integer

(minimum: 1, maximum: 12)

Clip skip

Default: 2

tiling

boolean

Enable tiling

Default: false

upload_lora

string

Shift + Return to add a new line

Upload LoRA

prompt

string

Shift + Return to add a new line

Prompt

Default: ""

negative_prompt

string

Shift + Return to add a new line

(deformed, distorted, disfigured:1.3), (naked, nude:1.5), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation(deformed, distorted, disfigured:1.3), (naked, nude:1.5), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation

Negative prompt

Default: "(deformed, distorted, disfigured:1.3), (naked, nude:1.5), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation"

image

file

Input image [img2img or postprocessing modes only]

cfg_scale

number

CFG scale

Default: 7

seed

integer

Seed. Leave blank for random generation

width

integer

Width

Default: 512

height

integer

Height

Default: 512

num_outputs

integer

(minimum: 1, maximum: 4)

Batch size [Doesn't work in postprocess mode].

Default: 1

sampler

string

Sampling method

Default: "Euler a"

sampler_steps

integer

(minimum: 1, maximum: 50)

Sampling steps [Doesn't work in postprocess mode].

Default: 20

hr_enabled

boolean

[HR] Enable

Default: false

denoising_strength

number

[HR] Denoising strength

Default: 0.75

hr_scale

number

[HR] Upscale by

Default: 2

hr_second_pass_steps

number

[HR] Hires steps

Default: 0

hr_upscaler

string

[HR] Upscaler

Default: "4x_foolhardy_Remacri"

hr_resize_x

integer

[HR] Resize width to

Default: 0

hr_resize_y

integer

[HR] Resize height to

Default: 0

ad_enabled

boolean

[adetailer] Enable

Default: false

ad_model

string

[adetailer] ADetailer model

Default: "face_yolov8s"

ad_prompt

string

Shift + Return to add a new line

[adetailer] ADetailer prompt

Default: ""

ad_negative_prompt

string

Shift + Return to add a new line

[adetailer] ADetailer negative prompt

Default: ""

ad_use_sampler

boolean

[adetailer] Use separate sampler

Default: true

ad_sampler

string

[adetailer] ADetailer sampler

Default: "Euler a"

ad_confidence

number

[adetailer] Detection model confidence threshold

Default: 0.3

ad_dilate_erode

integer

[adetailer] Mask erosion (-) / dilation (+)

Default: 4

ad_mask_blur

integer

[adetailer] Inpaint mask blur

Default: 4

ad_mask_merge_mode

string

[adetailer] Mask merge mode

Default: "None"

ad_denoising_strength

number

[adetailer] Inpaint denoising strength

Default: 0.4

ad_inpaint_only_masked

boolean

[adetailer] Inpaint only masked

Default: true

ad_inpaint_only_masked_padding

integer

[adetailer] Inpaint only masked padding, pixels

Default: 32

ad_use_inpaint_width_height

boolean

[adetailer] Use separate width/height

Default: false

ad_inpaint_width

integer

[adetailer] Inpaint width

Default: 512

ad_inpaint_height

integer

[adetailer] Inpaint height

Default: 512

ad_2_ad_enabled

boolean

[adetailer — 2] Enable

Default: false

ad_2_ad_model

string

[adetailer — 2] ADetailer model

Default: "face_yolov8s"

ad_2_ad_prompt

string

Shift + Return to add a new line

[adetailer — 2] ADetailer prompt

Default: ""

ad_2_ad_negative_prompt

string

Shift + Return to add a new line

[adetailer — 2] ADetailer negative prompt

Default: ""

ad_2_ad_use_sampler

boolean

[adetailer — 2] Use separate sampler

Default: true

ad_2_ad_sampler

string

[adetailer — 2] ADetailer sampler

Default: "Euler a"

ad_2_ad_confidence

number

[adetailer — 2] Detection model confidence threshold

Default: 0.3

ad_2_ad_dilate_erode

integer

[adetailer — 2] Mask erosion (-) / dilation (+)

Default: 4

ad_2_ad_mask_blur

integer

[adetailer — 2] Inpaint mask blur

Default: 4

ad_2_ad_mask_merge_mode

string

[adetailer — 2] Mask merge mode

Default: "None"

ad_2_ad_denoising_strength

number

[adetailer — 2] Inpaint denoising strength

Default: 0.4

ad_2_ad_inpaint_only_masked

boolean

[adetailer — 2] Inpaint only masked

Default: true

ad_2_ad_inpaint_only_masked_padding

integer

[adetailer — 2] Inpaint only masked padding, pixels

Default: 32

ad_2_ad_use_inpaint_width_height

boolean

[adetailer — 2] Use separate width/height

Default: false

ad_2_ad_inpaint_width

integer

[adetailer — 2] Inpaint width

Default: 512

ad_2_ad_inpaint_height

integer

[adetailer — 2] Inpaint height

Default: 512

ad_3_ad_enabled

boolean

[adetailer — 3] Enable

Default: false

ad_3_ad_model

string

[adetailer — 3] ADetailer model

Default: "face_yolov8s"

ad_3_ad_prompt

string

Shift + Return to add a new line

[adetailer — 3] ADetailer prompt

Default: ""

ad_3_ad_negative_prompt

string

Shift + Return to add a new line

[adetailer — 3] ADetailer negative prompt

Default: ""

ad_3_ad_use_sampler

boolean

[adetailer — 3] Use separate sampler

Default: true

ad_3_ad_sampler

string

[adetailer — 3] ADetailer sampler

Default: "Euler a"

ad_3_ad_confidence

number

[adetailer — 3] Detection model confidence threshold

Default: 0.3

ad_3_ad_dilate_erode

integer

[adetailer — 3] Mask erosion (-) / dilation (+)

Default: 4

ad_3_ad_mask_blur

integer

[adetailer — 3] Inpaint mask blur

Default: 4

ad_3_ad_mask_merge_mode

string

[adetailer — 3] Mask merge mode

Default: "None"

ad_3_ad_denoising_strength

number

[adetailer — 3] Inpaint denoising strength

Default: 0.4

ad_3_ad_inpaint_only_masked

boolean

[adetailer — 3] Inpaint only masked

Default: true

ad_3_ad_inpaint_only_masked_padding

integer

[adetailer — 3] Inpaint only masked padding, pixels

Default: 32

ad_3_ad_use_inpaint_width_height

boolean

[adetailer — 3] Use separate width/height

Default: false

ad_3_ad_inpaint_width

integer

[adetailer — 3] Inpaint width

Default: 512

ad_3_ad_inpaint_height

integer

[adetailer — 3] Inpaint height

Default: 512

ad_4_ad_enabled

boolean

[adetailer — 4] Enable

Default: false

ad_4_ad_model

string

[adetailer — 4] ADetailer model

Default: "face_yolov8s"

ad_4_ad_prompt

string

Shift + Return to add a new line

[adetailer — 4] ADetailer prompt

Default: ""

ad_4_ad_negative_prompt

string

Shift + Return to add a new line

[adetailer — 4] ADetailer negative prompt

Default: ""

ad_4_ad_use_sampler

boolean

[adetailer — 4] Use separate sampler

Default: true

ad_4_ad_sampler

string

[adetailer — 4] ADetailer sampler

Default: "Euler a"

ad_4_ad_confidence

number

[adetailer — 4] Detection model confidence threshold

Default: 0.3

ad_4_ad_dilate_erode

integer

[adetailer — 4] Mask erosion (-) / dilation (+)

Default: 4

ad_4_ad_mask_blur

integer

[adetailer — 4] Inpaint mask blur

Default: 4

ad_4_ad_mask_merge_mode

string

[adetailer — 4] Mask merge mode

Default: "None"

ad_4_ad_denoising_strength

number

[adetailer — 4] Inpaint denoising strength

Default: 0.4

ad_4_ad_inpaint_only_masked

boolean

[adetailer — 4] Inpaint only masked

Default: true

ad_4_ad_inpaint_only_masked_padding

integer

[adetailer — 4] Inpaint only masked padding, pixels

Default: 32

ad_4_ad_use_inpaint_width_height

boolean

[adetailer — 4] Use separate width/height

Default: false

ad_4_ad_inpaint_width

integer

[adetailer — 4] Inpaint width

Default: 512

ad_4_ad_inpaint_height

integer

[adetailer — 4] Inpaint height

Default: 512

sd_upscaler_enable

boolean

[SD upscaler] Enable

Default: false

sd_upscaler_upscaler

string

[SD upscaler] Upscaler

Default: "4x_foolhardy_Remacri"

sd_upscaler_tile_overlap

integer

[SD upscaler] Tile overlap

Default: 16

sd_upscaler_scale_factor

number

[SD upscaler] Scale Factor

Default: 2

openpose_enabled

boolean

[ControlNet — openpose] Enable

Default: false

openpose_image

file

[ControlNet — openpose] Input image

openpose_use_image_size

boolean

[ControlNet — openpose] Use provided image size

Default: false

openpose_control_mode

string

[ControlNet — openpose] Control Mode

Default: "Balanced"

openpose_preprocessor

string

[ControlNet — openpose] Preprocessor

Default: "openpose_full"

openpose_model

string

[ControlNet — openpose] Model

Default: "controlnet11Models_openpose"

openpose_control_weight

number

(minimum: 0, maximum: 2)

[ControlNet — openpose] Control Weight

Default: 1

openpose_guidance_start

number

(minimum: 0, maximum: 1)

[ControlNet — openpose] Starting Control Step

Default: 0

openpose_guidance_end

number

(minimum: 0, maximum: 1)

[ControlNet — openpose] Ending Control Step

Default: 1

openpose_preprocessor_resolution

integer

[ControlNet — openpose] Preprocessor Resolution

Default: 512

scribble_enabled

boolean

[ControlNet — scribble] Enable

Default: false

scribble_image

file

[ControlNet — scribble] Input image

scribble_use_image_size

boolean

[ControlNet — scribble] Use provided image size

Default: false

scribble_control_mode

string

[ControlNet — scribble] Control Mode

Default: "Balanced"

scribble_preprocessor

string

[ControlNet — scribble] Preprocessor

Default: "t2ia_sketch_pidi"

scribble_model

string

[ControlNet — scribble] Model

Default: "controlnet11Models_scribble"

scribble_control_weight

number

(minimum: 0, maximum: 2)

[ControlNet — scribble] Control Weight

Default: 1

scribble_guidance_start

number

(minimum: 0, maximum: 1)

[ControlNet — scribble] Starting Control Step

Default: 0

scribble_guidance_end

number

(minimum: 0, maximum: 1)

[ControlNet — scribble] Ending Control Step

Default: 1

scribble_preprocessor_resolution

integer

(minimum: 64, maximum: 2048)

[ControlNet — scribble] Preprocessor Resolution

Default: 512

scribble_xdog_threshold

integer

(minimum: 1, maximum: 64)

[ControlNet — scribble] XDoG Threshold [only scribble_xdog preprocessor]

Default: 32

tile_blur_enabled

boolean

[ControlNet — tile/blur] Enable

Default: false

tile_blur_image

file

[ControlNet — tile/blur] Input image

tile_blur_use_image_size

boolean

[ControlNet — tile/blur] Use provided image size

Default: false

tile_blur_control_mode

string

[ControlNet — tile/blur] Control Mode

Default: "Balanced"

tile_blur_preprocessor

string

[ControlNet — tile/blur] Preprocessor

Default: "tile_resample"

tile_blur_model

string

[ControlNet — tile/blur] Model

Default: "controlnet11Models_tile"

tile_blur_control_weight

number

(minimum: 0, maximum: 2)

[ControlNet — tile/blur] Control Weight

Default: 1

tile_blur_guidance_start

number

(minimum: 0, maximum: 1)

[ControlNet — tile/blur] Starting Control Step

Default: 0

tile_blur_guidance_end

number

(minimum: 0, maximum: 1)

[ControlNet — tile/blur] Ending Control Step

Default: 1

tile_blur_down_sampling_rate

number

(minimum: 1, maximum: 8)

[ControlNet — tile/blur] Down Sampling Rate

Default: 1

instruct_p2p_enabled

boolean

[ControlNet — InstructP2P] Enable

Default: false

instruct_p2p_image

file

[ControlNet — InstructP2P] Input image

instruct_p2p_use_image_size

boolean

[ControlNet — InstructP2P] Use provided image size

Default: false

instruct_p2p_control_mode

string

[ControlNet — InstructP2P] Control Mode

Default: "Balanced"

instruct_p2p_model

string

[ControlNet — InstructP2P] Model

Default: "control_v11e_sd15_ip2p_fp16"

instruct_p2p_control_weight

number

(minimum: 0, maximum: 2)

[ControlNet — InstructP2P] Control Weight

Default: 1

instruct_p2p_guidance_start

number

(minimum: 0, maximum: 1)

[ControlNet — InstructP2P] Starting Control Step

Default: 0

instruct_p2p_guidance_end

number

(minimum: 0, maximum: 1)

[ControlNet — InstructP2P] Ending Control Step

Default: 1

reference_enabled

boolean

[ControlNet — reference] Enable

Default: false

reference_image

file

[ControlNet — reference] Input image

reference_use_image_size

boolean

[ControlNet — reference] Use provided image size

Default: false

reference_control_mode

string

[ControlNet — reference] Control Mode

Default: "Balanced"

reference_preprocessor

string

[ControlNet — reference] Preprocessor

Default: "reference_only"

reference_control_weight

number

(minimum: 0, maximum: 2)

[ControlNet — reference] Control Weight

Default: 1

reference_guidance_start

number

(minimum: 0, maximum: 1)

[ControlNet — reference] Starting Control Step

Default: 0

reference_guidance_end

number

(minimum: 0, maximum: 1)

[ControlNet — reference] Ending Control Step

Default: 1

reference_style_fidelity

number

(minimum: 0, maximum: 1)

[ControlNet — reference] Style Fidelity [only "Balanced" control mode]

Default: 0.5

reference_2_enabled

boolean

[ControlNet — reference — 2] Enable

Default: false

reference_2_image

file

[ControlNet — reference — 2] Input image

reference_2_use_image_size

boolean

[ControlNet — reference — 2] Use provided image size

Default: false

reference_2_control_mode

string

[ControlNet — reference — 2] Control Mode

Default: "Balanced"

reference_2_preprocessor

string

[ControlNet — reference — 2] Preprocessor

Default: "reference_only"

reference_2_control_weight

number

(minimum: 0, maximum: 2)

[ControlNet — reference — 2] Control Weight

Default: 1

reference_2_guidance_start

number

(minimum: 0, maximum: 1)

[ControlNet — reference — 2] Starting Control Step

Default: 0

reference_2_guidance_end

number

(minimum: 0, maximum: 1)

[ControlNet — reference — 2] Ending Control Step

Default: 1

reference_2_style_fidelity

number

(minimum: 0, maximum: 1)

[ControlNet — reference — 2] Style Fidelity [only "Balanced" control mode]

Default: 0.5

lineart_enabled

boolean

[LineArt — openpose] Enable

Default: false

lineart_image

file

[LineArt — openpose] Input image

lineart_use_image_size

boolean

[LineArt — openpose] Use provided image size

Default: false

lineart_control_mode

string

[LineArt — openpose] Control Mode

Default: "Balanced"

lineart_preprocessor

string

[LineArt — openpose] Preprocessor

Default: "lineart_realistic"

lineart_model

string

[LineArt — openpose] Model

Default: "controlnet11Models_lineart"

lineart_control_weight

number

(minimum: 0, maximum: 2)

[LineArt — openpose] Control Weight

Default: 1

lineart_guidance_start

number

(minimum: 0, maximum: 1)

[LineArt — openpose] Starting Control Step

Default: 0

lineart_guidance_end

number

(minimum: 0, maximum: 1)

[LineArt — openpose] Ending Control Step

Default: 1

lineart_preprocessor_resolution

integer

(minimum: 64, maximum: 2048)

[LineArt — openpose] Preprocessor Resolution

Default: 512

Run this model in Node.js with one line of code:

npx create-replicate --model=vetkastar/stable_diffusion_control_photo_epic

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run vetkastar/stable_diffusion_control_photo_epic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "vetkastar/stable_diffusion_control_photo_epic:4ca2dab584c2d24a272bc14e47a9cdb44822f656c2c6f12575f84b83a3618f9f",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "",
      tiling: false,
      sampler: "Euler a",
      ad_model: "face_yolov8s",
      hr_scale: 2,
      ad_prompt: "",
      cfg_scale: 7,
      ad_enabled: false,
      ad_sampler: "Euler a",
      hr_enabled: false,
      hr_resize_x: 0,
      hr_resize_y: 0,
      hr_upscaler: "4x_foolhardy_Remacri",
      num_outputs: 1,
      ad_mask_blur: 4,
      ad_2_ad_model: "face_yolov8s",
      ad_3_ad_model: "face_yolov8s",
      ad_4_ad_model: "face_yolov8s",
      ad_confidence: 0.3,
      lineart_model: "controlnet11Models_lineart",
      sampler_steps: 20,
      ad_2_ad_prompt: "",
      ad_3_ad_prompt: "",
      ad_4_ad_prompt: "",
      ad_use_sampler: true,
      openpose_model: "controlnet11Models_openpose",
      scribble_model: "controlnet11Models_scribble",
      ad_2_ad_enabled: false,
      ad_2_ad_sampler: "Euler a",
      ad_3_ad_enabled: false,
      ad_3_ad_sampler: "Euler a",
      ad_4_ad_enabled: false,
      ad_4_ad_sampler: "Euler a",
      ad_dilate_erode: 4,
      generation_type: "txt2img",
      lineart_enabled: false,
      negative_prompt: "(deformed, distorted, disfigured:1.3), (naked, nude:1.5), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
      tile_blur_model: "controlnet11Models_tile",
      ad_inpaint_width: 512,
      openpose_enabled: false,
      scribble_enabled: false,
      ad_2_ad_mask_blur: 4,
      ad_3_ad_mask_blur: 4,
      ad_4_ad_mask_blur: 4,
      ad_inpaint_height: 512,
      reference_enabled: false,
      tile_blur_enabled: false,
      ad_2_ad_confidence: 0.3,
      ad_3_ad_confidence: 0.3,
      ad_4_ad_confidence: 0.3,
      ad_mask_merge_mode: "None",
      ad_negative_prompt: "",
      denoising_strength: 0.75,
      instruct_p2p_model: "control_v11e_sd15_ip2p_fp16",
      sd_upscaler_enable: false,
      ad_2_ad_use_sampler: true,
      ad_3_ad_use_sampler: true,
      ad_4_ad_use_sampler: true,
      reference_2_enabled: false,
      ad_2_ad_dilate_erode: 4,
      ad_3_ad_dilate_erode: 4,
      ad_4_ad_dilate_erode: 4,
      hr_second_pass_steps: 0,
      instruct_p2p_enabled: false,
      lineart_control_mode: "Balanced",
      lineart_guidance_end: 1,
      lineart_preprocessor: "lineart_realistic",
      sd_upscaler_upscaler: "4x_foolhardy_Remacri",
      ad_2_ad_inpaint_width: 512,
      ad_3_ad_inpaint_width: 512,
      ad_4_ad_inpaint_width: 512,
      ad_denoising_strength: 0.4,
      openpose_control_mode: "Balanced",
      openpose_guidance_end: 1,
      openpose_preprocessor: "openpose_full",
      scribble_control_mode: "Balanced",
      scribble_guidance_end: 1,
      scribble_preprocessor: "t2ia_sketch_pidi",
      ad_2_ad_inpaint_height: 512,
      ad_3_ad_inpaint_height: 512,
      ad_4_ad_inpaint_height: 512,
      ad_inpaint_only_masked: true,
      lineart_control_weight: 1,
      lineart_guidance_start: 0,
      lineart_use_image_size: false,
      reference_control_mode: "Balanced",
      reference_guidance_end: 1,
      reference_preprocessor: "reference_only",
      tile_blur_control_mode: "Balanced",
      tile_blur_guidance_end: 1,
      tile_blur_preprocessor: "tile_resample",
      ad_2_ad_mask_merge_mode: "None",
      ad_2_ad_negative_prompt: "",
      ad_3_ad_mask_merge_mode: "None",
      ad_3_ad_negative_prompt: "",
      ad_4_ad_mask_merge_mode: "None",
      ad_4_ad_negative_prompt: "",
      openpose_control_weight: 1,
      openpose_guidance_start: 0,
      openpose_use_image_size: false,
      scribble_control_weight: 1,
      scribble_guidance_start: 0,
      scribble_use_image_size: false,
      scribble_xdog_threshold: 32,
      clip_stop_at_last_layers: 2,
      reference_2_control_mode: "Balanced",
      reference_2_guidance_end: 1,
      reference_2_preprocessor: "reference_only",
      reference_control_weight: 1,
      reference_guidance_start: 0,
      reference_style_fidelity: 0.5,
      reference_use_image_size: false,
      sd_upscaler_scale_factor: 2,
      sd_upscaler_tile_overlap: 16,
      tile_blur_control_weight: 1,
      tile_blur_guidance_start: 0,
      tile_blur_use_image_size: false,
      instruct_p2p_control_mode: "Balanced",
      instruct_p2p_guidance_end: 1,
      ad_2_ad_denoising_strength: 0.4,
      ad_3_ad_denoising_strength: 0.4,
      ad_4_ad_denoising_strength: 0.4,
      reference_2_control_weight: 1,
      reference_2_guidance_start: 0,
      reference_2_style_fidelity: 0.5,
      reference_2_use_image_size: false,
      ad_2_ad_inpaint_only_masked: true,
      ad_3_ad_inpaint_only_masked: true,
      ad_4_ad_inpaint_only_masked: true,
      ad_use_inpaint_width_height: false,
      instruct_p2p_control_weight: 1,
      instruct_p2p_guidance_start: 0,
      instruct_p2p_use_image_size: false,
      tile_blur_down_sampling_rate: 1,
      ad_inpaint_only_masked_padding: 32,
      lineart_preprocessor_resolution: 512,
      ad_2_ad_use_inpaint_width_height: false,
      ad_3_ad_use_inpaint_width_height: false,
      ad_4_ad_use_inpaint_width_height: false,
      openpose_preprocessor_resolution: 512,
      scribble_preprocessor_resolution: 512,
      ad_2_ad_inpaint_only_masked_padding: 32,
      ad_3_ad_inpaint_only_masked_padding: 32,
      ad_4_ad_inpaint_only_masked_padding: 32
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run vetkastar/stable_diffusion_control_photo_epic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "vetkastar/stable_diffusion_control_photo_epic:4ca2dab584c2d24a272bc14e47a9cdb44822f656c2c6f12575f84b83a3618f9f",
    input={
        "width": 512,
        "height": 512,
        "prompt": "",
        "tiling": False,
        "sampler": "Euler a",
        "ad_model": "face_yolov8s",
        "hr_scale": 2,
        "ad_prompt": "",
        "cfg_scale": 7,
        "ad_enabled": False,
        "ad_sampler": "Euler a",
        "hr_enabled": False,
        "hr_resize_x": 0,
        "hr_resize_y": 0,
        "hr_upscaler": "4x_foolhardy_Remacri",
        "num_outputs": 1,
        "ad_mask_blur": 4,
        "ad_2_ad_model": "face_yolov8s",
        "ad_3_ad_model": "face_yolov8s",
        "ad_4_ad_model": "face_yolov8s",
        "ad_confidence": 0.3,
        "lineart_model": "controlnet11Models_lineart",
        "sampler_steps": 20,
        "ad_2_ad_prompt": "",
        "ad_3_ad_prompt": "",
        "ad_4_ad_prompt": "",
        "ad_use_sampler": True,
        "openpose_model": "controlnet11Models_openpose",
        "scribble_model": "controlnet11Models_scribble",
        "ad_2_ad_enabled": False,
        "ad_2_ad_sampler": "Euler a",
        "ad_3_ad_enabled": False,
        "ad_3_ad_sampler": "Euler a",
        "ad_4_ad_enabled": False,
        "ad_4_ad_sampler": "Euler a",
        "ad_dilate_erode": 4,
        "generation_type": "txt2img",
        "lineart_enabled": False,
        "negative_prompt": "(deformed, distorted, disfigured:1.3), (naked, nude:1.5), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
        "tile_blur_model": "controlnet11Models_tile",
        "ad_inpaint_width": 512,
        "openpose_enabled": False,
        "scribble_enabled": False,
        "ad_2_ad_mask_blur": 4,
        "ad_3_ad_mask_blur": 4,
        "ad_4_ad_mask_blur": 4,
        "ad_inpaint_height": 512,
        "reference_enabled": False,
        "tile_blur_enabled": False,
        "ad_2_ad_confidence": 0.3,
        "ad_3_ad_confidence": 0.3,
        "ad_4_ad_confidence": 0.3,
        "ad_mask_merge_mode": "None",
        "ad_negative_prompt": "",
        "denoising_strength": 0.75,
        "instruct_p2p_model": "control_v11e_sd15_ip2p_fp16",
        "sd_upscaler_enable": False,
        "ad_2_ad_use_sampler": True,
        "ad_3_ad_use_sampler": True,
        "ad_4_ad_use_sampler": True,
        "reference_2_enabled": False,
        "ad_2_ad_dilate_erode": 4,
        "ad_3_ad_dilate_erode": 4,
        "ad_4_ad_dilate_erode": 4,
        "hr_second_pass_steps": 0,
        "instruct_p2p_enabled": False,
        "lineart_control_mode": "Balanced",
        "lineart_guidance_end": 1,
        "lineart_preprocessor": "lineart_realistic",
        "sd_upscaler_upscaler": "4x_foolhardy_Remacri",
        "ad_2_ad_inpaint_width": 512,
        "ad_3_ad_inpaint_width": 512,
        "ad_4_ad_inpaint_width": 512,
        "ad_denoising_strength": 0.4,
        "openpose_control_mode": "Balanced",
        "openpose_guidance_end": 1,
        "openpose_preprocessor": "openpose_full",
        "scribble_control_mode": "Balanced",
        "scribble_guidance_end": 1,
        "scribble_preprocessor": "t2ia_sketch_pidi",
        "ad_2_ad_inpaint_height": 512,
        "ad_3_ad_inpaint_height": 512,
        "ad_4_ad_inpaint_height": 512,
        "ad_inpaint_only_masked": True,
        "lineart_control_weight": 1,
        "lineart_guidance_start": 0,
        "lineart_use_image_size": False,
        "reference_control_mode": "Balanced",
        "reference_guidance_end": 1,
        "reference_preprocessor": "reference_only",
        "tile_blur_control_mode": "Balanced",
        "tile_blur_guidance_end": 1,
        "tile_blur_preprocessor": "tile_resample",
        "ad_2_ad_mask_merge_mode": "None",
        "ad_2_ad_negative_prompt": "",
        "ad_3_ad_mask_merge_mode": "None",
        "ad_3_ad_negative_prompt": "",
        "ad_4_ad_mask_merge_mode": "None",
        "ad_4_ad_negative_prompt": "",
        "openpose_control_weight": 1,
        "openpose_guidance_start": 0,
        "openpose_use_image_size": False,
        "scribble_control_weight": 1,
        "scribble_guidance_start": 0,
        "scribble_use_image_size": False,
        "scribble_xdog_threshold": 32,
        "clip_stop_at_last_layers": 2,
        "reference_2_control_mode": "Balanced",
        "reference_2_guidance_end": 1,
        "reference_2_preprocessor": "reference_only",
        "reference_control_weight": 1,
        "reference_guidance_start": 0,
        "reference_style_fidelity": 0.5,
        "reference_use_image_size": False,
        "sd_upscaler_scale_factor": 2,
        "sd_upscaler_tile_overlap": 16,
        "tile_blur_control_weight": 1,
        "tile_blur_guidance_start": 0,
        "tile_blur_use_image_size": False,
        "instruct_p2p_control_mode": "Balanced",
        "instruct_p2p_guidance_end": 1,
        "ad_2_ad_denoising_strength": 0.4,
        "ad_3_ad_denoising_strength": 0.4,
        "ad_4_ad_denoising_strength": 0.4,
        "reference_2_control_weight": 1,
        "reference_2_guidance_start": 0,
        "reference_2_style_fidelity": 0.5,
        "reference_2_use_image_size": False,
        "ad_2_ad_inpaint_only_masked": True,
        "ad_3_ad_inpaint_only_masked": True,
        "ad_4_ad_inpaint_only_masked": True,
        "ad_use_inpaint_width_height": False,
        "instruct_p2p_control_weight": 1,
        "instruct_p2p_guidance_start": 0,
        "instruct_p2p_use_image_size": False,
        "tile_blur_down_sampling_rate": 1,
        "ad_inpaint_only_masked_padding": 32,
        "lineart_preprocessor_resolution": 512,
        "ad_2_ad_use_inpaint_width_height": False,
        "ad_3_ad_use_inpaint_width_height": False,
        "ad_4_ad_use_inpaint_width_height": False,
        "openpose_preprocessor_resolution": 512,
        "scribble_preprocessor_resolution": 512,
        "ad_2_ad_inpaint_only_masked_padding": 32,
        "ad_3_ad_inpaint_only_masked_padding": 32,
        "ad_4_ad_inpaint_only_masked_padding": 32
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run vetkastar/stable_diffusion_control_photo_epic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "vetkastar/stable_diffusion_control_photo_epic:4ca2dab584c2d24a272bc14e47a9cdb44822f656c2c6f12575f84b83a3618f9f",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "",
      "tiling": false,
      "sampler": "Euler a",
      "ad_model": "face_yolov8s",
      "hr_scale": 2,
      "ad_prompt": "",
      "cfg_scale": 7,
      "ad_enabled": false,
      "ad_sampler": "Euler a",
      "hr_enabled": false,
      "hr_resize_x": 0,
      "hr_resize_y": 0,
      "hr_upscaler": "4x_foolhardy_Remacri",
      "num_outputs": 1,
      "ad_mask_blur": 4,
      "ad_2_ad_model": "face_yolov8s",
      "ad_3_ad_model": "face_yolov8s",
      "ad_4_ad_model": "face_yolov8s",
      "ad_confidence": 0.3,
      "lineart_model": "controlnet11Models_lineart",
      "sampler_steps": 20,
      "ad_2_ad_prompt": "",
      "ad_3_ad_prompt": "",
      "ad_4_ad_prompt": "",
      "ad_use_sampler": true,
      "openpose_model": "controlnet11Models_openpose",
      "scribble_model": "controlnet11Models_scribble",
      "ad_2_ad_enabled": false,
      "ad_2_ad_sampler": "Euler a",
      "ad_3_ad_enabled": false,
      "ad_3_ad_sampler": "Euler a",
      "ad_4_ad_enabled": false,
      "ad_4_ad_sampler": "Euler a",
      "ad_dilate_erode": 4,
      "generation_type": "txt2img",
      "lineart_enabled": false,
      "negative_prompt": "(deformed, distorted, disfigured:1.3), (naked, nude:1.5), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
      "tile_blur_model": "controlnet11Models_tile",
      "ad_inpaint_width": 512,
      "openpose_enabled": false,
      "scribble_enabled": false,
      "ad_2_ad_mask_blur": 4,
      "ad_3_ad_mask_blur": 4,
      "ad_4_ad_mask_blur": 4,
      "ad_inpaint_height": 512,
      "reference_enabled": false,
      "tile_blur_enabled": false,
      "ad_2_ad_confidence": 0.3,
      "ad_3_ad_confidence": 0.3,
      "ad_4_ad_confidence": 0.3,
      "ad_mask_merge_mode": "None",
      "ad_negative_prompt": "",
      "denoising_strength": 0.75,
      "instruct_p2p_model": "control_v11e_sd15_ip2p_fp16",
      "sd_upscaler_enable": false,
      "ad_2_ad_use_sampler": true,
      "ad_3_ad_use_sampler": true,
      "ad_4_ad_use_sampler": true,
      "reference_2_enabled": false,
      "ad_2_ad_dilate_erode": 4,
      "ad_3_ad_dilate_erode": 4,
      "ad_4_ad_dilate_erode": 4,
      "hr_second_pass_steps": 0,
      "instruct_p2p_enabled": false,
      "lineart_control_mode": "Balanced",
      "lineart_guidance_end": 1,
      "lineart_preprocessor": "lineart_realistic",
      "sd_upscaler_upscaler": "4x_foolhardy_Remacri",
      "ad_2_ad_inpaint_width": 512,
      "ad_3_ad_inpaint_width": 512,
      "ad_4_ad_inpaint_width": 512,
      "ad_denoising_strength": 0.4,
      "openpose_control_mode": "Balanced",
      "openpose_guidance_end": 1,
      "openpose_preprocessor": "openpose_full",
      "scribble_control_mode": "Balanced",
      "scribble_guidance_end": 1,
      "scribble_preprocessor": "t2ia_sketch_pidi",
      "ad_2_ad_inpaint_height": 512,
      "ad_3_ad_inpaint_height": 512,
      "ad_4_ad_inpaint_height": 512,
      "ad_inpaint_only_masked": true,
      "lineart_control_weight": 1,
      "lineart_guidance_start": 0,
      "lineart_use_image_size": false,
      "reference_control_mode": "Balanced",
      "reference_guidance_end": 1,
      "reference_preprocessor": "reference_only",
      "tile_blur_control_mode": "Balanced",
      "tile_blur_guidance_end": 1,
      "tile_blur_preprocessor": "tile_resample",
      "ad_2_ad_mask_merge_mode": "None",
      "ad_2_ad_negative_prompt": "",
      "ad_3_ad_mask_merge_mode": "None",
      "ad_3_ad_negative_prompt": "",
      "ad_4_ad_mask_merge_mode": "None",
      "ad_4_ad_negative_prompt": "",
      "openpose_control_weight": 1,
      "openpose_guidance_start": 0,
      "openpose_use_image_size": false,
      "scribble_control_weight": 1,
      "scribble_guidance_start": 0,
      "scribble_use_image_size": false,
      "scribble_xdog_threshold": 32,
      "clip_stop_at_last_layers": 2,
      "reference_2_control_mode": "Balanced",
      "reference_2_guidance_end": 1,
      "reference_2_preprocessor": "reference_only",
      "reference_control_weight": 1,
      "reference_guidance_start": 0,
      "reference_style_fidelity": 0.5,
      "reference_use_image_size": false,
      "sd_upscaler_scale_factor": 2,
      "sd_upscaler_tile_overlap": 16,
      "tile_blur_control_weight": 1,
      "tile_blur_guidance_start": 0,
      "tile_blur_use_image_size": false,
      "instruct_p2p_control_mode": "Balanced",
      "instruct_p2p_guidance_end": 1,
      "ad_2_ad_denoising_strength": 0.4,
      "ad_3_ad_denoising_strength": 0.4,
      "ad_4_ad_denoising_strength": 0.4,
      "reference_2_control_weight": 1,
      "reference_2_guidance_start": 0,
      "reference_2_style_fidelity": 0.5,
      "reference_2_use_image_size": false,
      "ad_2_ad_inpaint_only_masked": true,
      "ad_3_ad_inpaint_only_masked": true,
      "ad_4_ad_inpaint_only_masked": true,
      "ad_use_inpaint_width_height": false,
      "instruct_p2p_control_weight": 1,
      "instruct_p2p_guidance_start": 0,
      "instruct_p2p_use_image_size": false,
      "tile_blur_down_sampling_rate": 1,
      "ad_inpaint_only_masked_padding": 32,
      "lineart_preprocessor_resolution": 512,
      "ad_2_ad_use_inpaint_width_height": false,
      "ad_3_ad_use_inpaint_width_height": false,
      "ad_4_ad_use_inpaint_width_height": false,
      "openpose_preprocessor_resolution": 512,
      "scribble_preprocessor_resolution": 512,
      "ad_2_ad_inpaint_only_masked_padding": 32,
      "ad_3_ad_inpaint_only_masked_padding": 32,
      "ad_4_ad_inpaint_only_masked_padding": 32
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

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

Run time and cost

This model costs approximately $0.0055 to run on Replicate, or 181 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 6 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.