RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting, misto anyline controlnet
Run this model in Node.js with one line of code:
npm install replicateREPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
import Replicate from "replicate";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run oliversaternus/realvisxl-3-multi-controlnet-lora-misto using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"oliversaternus/realvisxl-3-multi-controlnet-lora-misto:6315b5311a83d918f5c3ac59683c8cdd44c6532920be8e17b8d0a46be5653f0f",
{
input: {
image: "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
width: 768,
height: 768,
prompt: "living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements",
refine: "no_refiner",
scheduler: "K_EULER",
lora_scale: 0.6,
num_outputs: 1,
controlnet_1: "lineart_anyline",
controlnet_2: "none",
controlnet_3: "none",
guidance_scale: 7.5,
apply_watermark: false,
negative_prompt: "",
prompt_strength: 1,
sizing_strategy: "input_image",
controlnet_1_end: 0.8,
controlnet_2_end: 1,
controlnet_3_end: 1,
controlnet_1_image: "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
controlnet_1_start: 0,
controlnet_2_start: 0,
controlnet_3_start: 0,
num_inference_steps: 30,
controlnet_1_conditioning_scale: 0.8,
controlnet_2_conditioning_scale: 0.75,
controlnet_3_conditioning_scale: 0.75
}
}
);
// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateREPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
import replicateRun oliversaternus/realvisxl-3-multi-controlnet-lora-misto using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"oliversaternus/realvisxl-3-multi-controlnet-lora-misto:6315b5311a83d918f5c3ac59683c8cdd44c6532920be8e17b8d0a46be5653f0f",
input={
"image": "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
"width": 768,
"height": 768,
"prompt": "living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"controlnet_1": "lineart_anyline",
"controlnet_2": "none",
"controlnet_3": "none",
"guidance_scale": 7.5,
"apply_watermark": False,
"negative_prompt": "",
"prompt_strength": 1,
"sizing_strategy": "input_image",
"controlnet_1_end": 0.8,
"controlnet_2_end": 1,
"controlnet_3_end": 1,
"controlnet_1_image": "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
"controlnet_1_start": 0,
"controlnet_2_start": 0,
"controlnet_3_start": 0,
"num_inference_steps": 30,
"controlnet_1_conditioning_scale": 0.8,
"controlnet_2_conditioning_scale": 0.75,
"controlnet_3_conditioning_scale": 0.75
}
)
# To access the file URL:
print(output[0].url())
#=> "http://example.com"
# To write the file to disk:
with open("my-image.png", "wb") as file:
file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run oliversaternus/realvisxl-3-multi-controlnet-lora-misto 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": "oliversaternus/realvisxl-3-multi-controlnet-lora-misto:6315b5311a83d918f5c3ac59683c8cdd44c6532920be8e17b8d0a46be5653f0f",
"input": {
"image": "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
"width": 768,
"height": 768,
"prompt": "living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"controlnet_1": "lineart_anyline",
"controlnet_2": "none",
"controlnet_3": "none",
"guidance_scale": 7.5,
"apply_watermark": false,
"negative_prompt": "",
"prompt_strength": 1,
"sizing_strategy": "input_image",
"controlnet_1_end": 0.8,
"controlnet_2_end": 1,
"controlnet_3_end": 1,
"controlnet_1_image": "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
"controlnet_1_start": 0,
"controlnet_2_start": 0,
"controlnet_3_start": 0,
"num_inference_steps": 30,
"controlnet_1_conditioning_scale": 0.8,
"controlnet_2_conditioning_scale": 0.75,
"controlnet_3_conditioning_scale": 0.75
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2025-05-29T21:12:12.393090Z",
"created_at": "2025-05-29T21:07:39.065000Z",
"data_removed": false,
"error": null,
"id": "jrcy031xq5rme0cq3qfs33x76g",
"input": {
"image": "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
"width": 768,
"height": 768,
"prompt": "living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"controlnet_1": "lineart_anyline",
"controlnet_2": "none",
"controlnet_3": "none",
"guidance_scale": 7.5,
"apply_watermark": false,
"negative_prompt": "",
"prompt_strength": 1,
"sizing_strategy": "input_image",
"controlnet_1_end": 0.8,
"controlnet_2_end": 1,
"controlnet_3_end": 1,
"controlnet_1_image": "https://replicate.delivery/xezq/odRRGCQC6eXETiWAfO7HyjrKwuNfwG4PZ0tbLBOPC62uyPjpA/out-0.webp",
"controlnet_1_start": 0,
"controlnet_2_start": 0,
"controlnet_3_start": 0,
"num_inference_steps": 30,
"controlnet_1_conditioning_scale": 0.8,
"controlnet_2_conditioning_scale": 0.75,
"controlnet_3_conditioning_scale": 0.75
},
"logs": "Using seed: 60054\nResizing based on input_image\nOriginal dimensions: Width: 1024, Height: 1024\nAspect Ratio: 1.00\nDimensions to resize to: Width: 1024, Height: 1024\nresize took: 0.10s\nPrompt: living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements\nProcessing image with lineart_anyline\nInitializing Anyline preprocessor\ncontrolnet preprocess took: 1.40s\nUsing img2img + controlnet pipeline\nInitializing TheMistoAI/MistoLine\nThe config attributes {'mid_block_type': 'UNetMidBlock2DCrossAttn'} were passed to ControlNetModel, but are not expected and will be ignored. Please verify your config.json configuration file.\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 20545.93it/s]\nYou have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:07, 3.86it/s]\n 7%|▋ | 2/30 [00:00<00:05, 4.97it/s]\n 10%|█ | 3/30 [00:00<00:04, 5.42it/s]\n 13%|█▎ | 4/30 [00:00<00:04, 5.66it/s]\n 17%|█▋ | 5/30 [00:00<00:04, 5.81it/s]\n 20%|██ | 6/30 [00:01<00:04, 5.89it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 5.95it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.00it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.02it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.03it/s]\n 37%|███▋ | 11/30 [00:01<00:03, 6.05it/s]\n 40%|████ | 12/30 [00:02<00:02, 6.06it/s]\n 43%|████▎ | 13/30 [00:02<00:02, 6.07it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.07it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.07it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.07it/s]\n 57%|█████▋ | 17/30 [00:02<00:02, 6.08it/s]\n 60%|██████ | 18/30 [00:03<00:01, 6.07it/s]\n 63%|██████▎ | 19/30 [00:03<00:01, 6.07it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.07it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.08it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.07it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.06it/s]\n 80%|████████ | 24/30 [00:04<00:00, 6.06it/s]\n 83%|████████▎ | 25/30 [00:04<00:00, 6.07it/s]\n 87%|████████▋ | 26/30 [00:04<00:00, 6.07it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.06it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.06it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.06it/s]\n100%|██████████| 30/30 [00:05<00:00, 6.06it/s]\n100%|██████████| 30/30 [00:05<00:00, 5.96it/s]\ninference took: 5.69s\nprediction took: 8.57s",
"metrics": {
"predict_time": 8.7471848,
"total_time": 273.32809
},
"output": [
"https://replicate.delivery/xezq/afnfeCZgpCIdgI8Bj4rP4k1caH3weWNo5EeWhACSZWqm1fZMF/control-0.png",
"https://replicate.delivery/xezq/w6G0XoeSVFWgQCKNGjpUfTt61STWz5GPegAL5OepOpux6fMmC/out-0.png"
],
"started_at": "2025-05-29T21:12:03.645906Z",
"status": "succeeded",
"urls": {
"stream": "https://stream.replicate.com/v1/files/bcwr-fnj6w5ylndm34abdqght6vniu7gmt7h6wlwqf36genffed677ypa",
"get": "https://api.replicate.com/v1/predictions/jrcy031xq5rme0cq3qfs33x76g",
"cancel": "https://api.replicate.com/v1/predictions/jrcy031xq5rme0cq3qfs33x76g/cancel"
},
"version": "6315b5311a83d918f5c3ac59683c8cdd44c6532920be8e17b8d0a46be5653f0f"
}Using seed: 60054
Resizing based on input_image
Original dimensions: Width: 1024, Height: 1024
Aspect Ratio: 1.00
Dimensions to resize to: Width: 1024, Height: 1024
resize took: 0.10s
Prompt: living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements
Processing image with lineart_anyline
Initializing Anyline preprocessor
controlnet preprocess took: 1.40s
Using img2img + controlnet pipeline
Initializing TheMistoAI/MistoLine
The config attributes {'mid_block_type': 'UNetMidBlock2DCrossAttn'} were passed to ControlNetModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 20545.93it/s]
You have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.
0%| | 0/30 [00:00<?, ?it/s]
3%|▎ | 1/30 [00:00<00:07, 3.86it/s]
7%|▋ | 2/30 [00:00<00:05, 4.97it/s]
10%|█ | 3/30 [00:00<00:04, 5.42it/s]
13%|█▎ | 4/30 [00:00<00:04, 5.66it/s]
17%|█▋ | 5/30 [00:00<00:04, 5.81it/s]
20%|██ | 6/30 [00:01<00:04, 5.89it/s]
23%|██▎ | 7/30 [00:01<00:03, 5.95it/s]
27%|██▋ | 8/30 [00:01<00:03, 6.00it/s]
30%|███ | 9/30 [00:01<00:03, 6.02it/s]
33%|███▎ | 10/30 [00:01<00:03, 6.03it/s]
37%|███▋ | 11/30 [00:01<00:03, 6.05it/s]
40%|████ | 12/30 [00:02<00:02, 6.06it/s]
43%|████▎ | 13/30 [00:02<00:02, 6.07it/s]
47%|████▋ | 14/30 [00:02<00:02, 6.07it/s]
50%|█████ | 15/30 [00:02<00:02, 6.07it/s]
53%|█████▎ | 16/30 [00:02<00:02, 6.07it/s]
57%|█████▋ | 17/30 [00:02<00:02, 6.08it/s]
60%|██████ | 18/30 [00:03<00:01, 6.07it/s]
63%|██████▎ | 19/30 [00:03<00:01, 6.07it/s]
67%|██████▋ | 20/30 [00:03<00:01, 6.07it/s]
70%|███████ | 21/30 [00:03<00:01, 6.08it/s]
73%|███████▎ | 22/30 [00:03<00:01, 6.07it/s]
77%|███████▋ | 23/30 [00:03<00:01, 6.06it/s]
80%|████████ | 24/30 [00:04<00:00, 6.06it/s]
83%|████████▎ | 25/30 [00:04<00:00, 6.07it/s]
87%|████████▋ | 26/30 [00:04<00:00, 6.07it/s]
90%|█████████ | 27/30 [00:04<00:00, 6.06it/s]
93%|█████████▎| 28/30 [00:04<00:00, 6.06it/s]
97%|█████████▋| 29/30 [00:04<00:00, 6.06it/s]
100%|██████████| 30/30 [00:05<00:00, 6.06it/s]
100%|██████████| 30/30 [00:05<00:00, 5.96it/s]
inference took: 5.69s
prediction took: 8.57sThis model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.
Fork of https://replicate.com/fofr/realvisxl-v3-multi-controlnet-lora with additional support for lineart-anyline controlnet https://huggingface.co/TheMistoAI/MistoLine
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
This model runs on L40S hardware which costs $0.000975 per second. View more.
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Using seed: 60054
Resizing based on input_image
Original dimensions: Width: 1024, Height: 1024
Aspect Ratio: 1.00
Dimensions to resize to: Width: 1024, Height: 1024
resize took: 0.10s
Prompt: living room, modern interior design, a functional space, white walls, matte gray floor, black and white colors, geometric shapes, modular furniture, steel and glass, and modern design elements
Processing image with lineart_anyline
Initializing Anyline preprocessor
controlnet preprocess took: 1.40s
Using img2img + controlnet pipeline
Initializing TheMistoAI/MistoLine
The config attributes {'mid_block_type': 'UNetMidBlock2DCrossAttn'} were passed to ControlNetModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 20545.93it/s]
You have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.
0%| | 0/30 [00:00<?, ?it/s]
3%|▎ | 1/30 [00:00<00:07, 3.86it/s]
7%|▋ | 2/30 [00:00<00:05, 4.97it/s]
10%|█ | 3/30 [00:00<00:04, 5.42it/s]
13%|█▎ | 4/30 [00:00<00:04, 5.66it/s]
17%|█▋ | 5/30 [00:00<00:04, 5.81it/s]
20%|██ | 6/30 [00:01<00:04, 5.89it/s]
23%|██▎ | 7/30 [00:01<00:03, 5.95it/s]
27%|██▋ | 8/30 [00:01<00:03, 6.00it/s]
30%|███ | 9/30 [00:01<00:03, 6.02it/s]
33%|███▎ | 10/30 [00:01<00:03, 6.03it/s]
37%|███▋ | 11/30 [00:01<00:03, 6.05it/s]
40%|████ | 12/30 [00:02<00:02, 6.06it/s]
43%|████▎ | 13/30 [00:02<00:02, 6.07it/s]
47%|████▋ | 14/30 [00:02<00:02, 6.07it/s]
50%|█████ | 15/30 [00:02<00:02, 6.07it/s]
53%|█████▎ | 16/30 [00:02<00:02, 6.07it/s]
57%|█████▋ | 17/30 [00:02<00:02, 6.08it/s]
60%|██████ | 18/30 [00:03<00:01, 6.07it/s]
63%|██████▎ | 19/30 [00:03<00:01, 6.07it/s]
67%|██████▋ | 20/30 [00:03<00:01, 6.07it/s]
70%|███████ | 21/30 [00:03<00:01, 6.08it/s]
73%|███████▎ | 22/30 [00:03<00:01, 6.07it/s]
77%|███████▋ | 23/30 [00:03<00:01, 6.06it/s]
80%|████████ | 24/30 [00:04<00:00, 6.06it/s]
83%|████████▎ | 25/30 [00:04<00:00, 6.07it/s]
87%|████████▋ | 26/30 [00:04<00:00, 6.07it/s]
90%|█████████ | 27/30 [00:04<00:00, 6.06it/s]
93%|█████████▎| 28/30 [00:04<00:00, 6.06it/s]
97%|█████████▋| 29/30 [00:04<00:00, 6.06it/s]
100%|██████████| 30/30 [00:05<00:00, 6.06it/s]
100%|██████████| 30/30 [00:05<00:00, 5.96it/s]
inference took: 5.69s
prediction took: 8.57s