—
LoRA — Inpainting
Run Any Stable Diffusion model with customizable LoRA weights.
Input
Add your inputs and customize the generation settings.
Result & Pricing
Image output — your generated image will appear here.
Your image will appear here
Choose your inputs and customize your settings.
Model pricing (tax excluded) initial reservation per generation
| Billing stage | How it works |
|---|---|
| Reserved credits | A one-time reservation based on 300 compute seconds |
| Final charge | Adjusted to confirmed usage after generation |
Check the credits to reserve before you generate.
Prices, estimates and credit deductions exclude tax. Any applicable tax is charged only when you buy plans or credits.
Initial reservation: credits are reserved before generation. Your final charge is adjusted to confirmed usage after generation. Any unused reserved credits become available again automatically; additional usage may require more credits. The reservation covers compute time, which may differ from the length of your generated media.
- Prices shown are estimates, not final charges. Final billing details will be available in Reports after generation is complete.
API
WEBOT API · Inpainting
Generate from your server with your WEBOT account credits.
Use your 120-character WEBOT customer key (a–z, A–Z, 0–9). Send
Authorization: Bearer YOUR_KEY. Keys are secrets: call from a server, never from public frontend code. Results come from verified webhooks and remain saved if your stream disconnects.1. Configure your server
WEBOT_BASE_URL=https://webot.online
WEBOT_API_KEY=<your-server-side-WEBOT-key>This base URL is resolved from verified domain mappings and your direct creator reseller. Forwarded Host headers are not trusted. New custom reseller domains need DNS, TLS and platform verification before activation.
2. Quote, then generate
| Method | Endpoint | Purpose |
|---|---|---|
| POST | https://webot.online/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote | Validate input and calculate credits (no deduction). |
| POST | https://webot.online/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests | Reserve quoted credits and queue an asynchronous job. |
| GET | https://webot.online/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests/{request_id}/result | Read your saved result: 202 pending, 200 terminal. |
| GET | https://webot.online/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests/{request_id}/events | Authenticated SSE: generation / terminal events. |
Send JSON {"input":{…}} to quote. Send the same input plus integer quoted_credits to generate, with Authorization: Bearer … and Idempotency-Key. Use a unique 16–128 character key per new job; persist it and reuse the same key and input on any uncertain response. Never retry with a new key: that creates a second chargeable job.
Credits are reserved only after validation and a durable request is saved. A changed quote or insufficient balance returns 409. Credits exclude purchase taxes. The quoted amount is an initial reservation. After generation, the final charge replaces it using confirmed usage. Any verified unused allocation becomes available automatically; additional usage may require more credits. Missing billing stays pending, including for failed jobs.
3. Input example
Save this as input.json. Replace sample prompts, files and media URLs with your own. Schemas do not guarantee provider acceptance of the content.
{
"controlnets": [],
"controlnet_guess_mode": false,
"image_format": "png",
"eta": 0,
"timesteps": {
"array": [],
"method": "default"
},
"tile_stride_width": 2048,
"embeddings": [],
"tile_height": 4096,
"enable_safety_checker": false,
"debug_latents": false,
"rescale_betas_snr_zero": false,
"prediction_type": "epsilon",
"guidance_scale": 7.5,
"debug_per_pass_latents": false,
"negative_prompt": "",
"num_inference_steps": 30,
"model_name": "stabilityai/stable-diffusion-xl-base-1.0",
"image_encoder_weight_name": "pytorch_model.bin",
"num_images": 1,
"noise_strength": 0.5,
"tile_stride_height": 2048,
"clip_skip": 0,
"prompt": "Photo of a european medieval 40 year old queen, silver hair, highly detailed face, detailed eyes, head shot, intricate crown, age spots, wrinkles",
"prompt_weighting": false,
"loras": [],
"tile_width": 4096,
"ip_adapter": [],
"sigmas": {
"array": [],
"method": "default"
}
}4. Language examples
# Save the model's example input as input.json, then replace prompts/media URLs.
# Requires curl and jq. Store NONCE once for this job; reuse it on any retry.
export NONCE="$(openssl rand -hex 16)"
BASE="${WEBOT_BASE_URL%/}"
jq -n --slurpfile input input.json '{input:$input[0]}' > quote-body.json
curl --fail-with-body -sS "$BASE/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote" \
-H "Authorization: Bearer $WEBOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @quote-body.json > quote.json
CREDITS=$(jq -er '.quote.credits_consumed' quote.json)
jq --argjson credits "$CREDITS" '. + {quoted_credits:$credits}' quote-body.json > request-body.json
curl --fail-with-body -sS "$BASE/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests" \
-H "Authorization: Bearer $WEBOT_API_KEY" -H "Idempotency-Key: $NONCE" \
-H 'Content-Type: application/json' --data-binary @request-body.json > job.json
# Subscribe; after a nonterminal disconnect, reconnect this SAME URL.
curl --fail-with-body -N "$(jq -er '.events_url' job.json)" -H "Authorization: Bearer $WEBOT_API_KEY"
# Read saved output after terminal notification (never call provider status/results).
curl --fail-with-body -sS "$(jq -er '.result_url' job.json)" -H "Authorization: Bearer $WEBOT_API_KEY"// Node.js 18+. Save your customized input in input.json.
import { readFileSync } from 'node:fs';
import { randomUUID } from 'node:crypto';
const base = process.env.WEBOT_BASE_URL.replace(/\/$/, '');
const key = process.env.WEBOT_API_KEY;
const input = JSON.parse(readFileSync('input.json', 'utf8'));
const nonce = process.env.WEBOT_JOB_NONCE || randomUUID(); // Persist before submission.
async function post(path, body, nonce) {
const response = await fetch(base + path, {method:'POST', headers:{
Authorization:`Bearer ${key}`, 'Content-Type':'application/json',
...(nonce ? {'Idempotency-Key':nonce} : {})}, body:JSON.stringify(body)});
const json = await response.json();
if (!response.ok) throw new Error(JSON.stringify(json));
return json;
}
const {quote} = await post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote', {input});
const job = await post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests', {input, quoted_credits:quote.credits_consumed}, nonce);
console.log(job); // Stable WEBOT request_id, events_url, result_url.
// Stream saved webhook state. Reconnect ONLY the event stream, not the generation.
while (!job.terminal || job.financial_pending) {
const stream = await fetch(job.events_url, {headers:{Authorization:`Bearer ${key}`}});
if (!stream.ok) throw new Error(`Event stream HTTP ${stream.status}`);
let buffer = '';
for await (const chunk of stream.body.pipeThrough(new TextDecoderStream())) {
buffer += chunk;
let end;
while ((end = buffer.indexOf('\n\n')) !== -1) {
const event = buffer.slice(0, end); buffer = buffer.slice(end + 2);
const data = event.split('\n').find(line => line.startsWith('data: '));
if (!data) continue;
const state = JSON.parse(data.slice(6));
if (state.error && !state.status) throw new Error(JSON.stringify(state.error));
if (state.terminal && !state.financial_pending) { console.log(state.output ?? state.error); process.exit(0); }
}
}
await new Promise(resolve => setTimeout(resolve, 1500));
}
console.log(job.output ?? job.error);// Node.js 18+. Save your customized input in input.json.
import { readFileSync } from 'node:fs';
import { randomUUID } from 'node:crypto';
const base = process.env.WEBOT_BASE_URL!.replace(/\/$/, '');
const key = process.env.WEBOT_API_KEY!;
const input = JSON.parse(readFileSync('input.json', 'utf8'));
const nonce = process.env.WEBOT_JOB_NONCE || randomUUID(); // Persist before submission.
async function post(path: string, body: unknown, nonce?: string) {
const response = await fetch(base + path, {method:'POST', headers:{
Authorization:`Bearer ${key}`, 'Content-Type':'application/json',
...(nonce ? {'Idempotency-Key':nonce} : {})}, body:JSON.stringify(body)});
const json = await response.json();
if (!response.ok) throw new Error(JSON.stringify(json));
return json;
}
const {quote} = await post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote', {input});
const job = await post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests', {input, quoted_credits:quote.credits_consumed}, nonce);
console.log(job); // Stable WEBOT request_id, events_url, result_url.
// Stream saved webhook state. Reconnect ONLY the event stream, not the generation.
while (!job.terminal || job.financial_pending) {
const stream = await fetch(job.events_url, {headers:{Authorization:`Bearer ${key}`}});
if (!stream.ok) throw new Error(`Event stream HTTP ${stream.status}`);
let buffer = '';
for await (const chunk of stream.body.pipeThrough(new TextDecoderStream())) {
buffer += chunk;
let end;
while ((end = buffer.indexOf('\n\n')) !== -1) {
const event = buffer.slice(0, end); buffer = buffer.slice(end + 2);
const data = event.split('\n').find(line => line.startsWith('data: '));
if (!data) continue;
const state = JSON.parse(data.slice(6));
if (state.error && !state.status) throw new Error(JSON.stringify(state.error));
if (state.terminal && !state.financial_pending) { console.log(state.output ?? state.error); process.exit(0); }
}
}
await new Promise(resolve => setTimeout(resolve, 1500));
}
console.log(job.output ?? job.error);# Python 3.9+, pip install requests
import json, os, time, uuid, requests
base = os.environ['WEBOT_BASE_URL'].rstrip('/')
headers = {'Authorization': 'Bearer ' + os.environ['WEBOT_API_KEY']}
with open('input.json', encoding='utf-8') as file:
input_data = json.load(file)
nonce = os.environ.get('WEBOT_JOB_NONCE') or str(uuid.uuid4()) # Persist before submitting.
def post(path, body, extra=None):
response = requests.post(base + path, headers={**headers, **(extra or {})}, json=body, timeout=180)
response.raise_for_status()
return response.json()
quote = post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote', {'input': input_data})['quote']
job = post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests', {'input': input_data, 'quoted_credits': quote['credits_consumed']}, {'Idempotency-Key': nonce})
state = job
while not state['terminal'] or state.get('financial_pending', False):
# Reconnect while nonterminal; this reads WEBOT's database, never a provider status API.
with requests.get(job['events_url'], headers=headers, stream=True, timeout=(10, 40)) as stream:
stream.raise_for_status()
for line in stream.iter_lines(decode_unicode=True):
if line and line.startswith('data: '):
state = json.loads(line[6:])
if 'status' not in state: raise RuntimeError(state)
if state['terminal'] and not state.get('financial_pending', False): break
if not state['terminal'] or state.get('financial_pending', False): time.sleep(1.5)
print(state['output'] if state['status'] == 'completed' else state['error'])<?php // PHP 8.1+ with cURL
$base = rtrim(getenv('WEBOT_BASE_URL'), '/');
$input = json_decode(file_get_contents('input.json'), false, 64, JSON_THROW_ON_ERROR);
$nonce = getenv('WEBOT_JOB_NONCE') ?: bin2hex(random_bytes(16)); // Persist this before submission.
function post(string $path, array $body, ?string $nonce = null): array {
global $base;
$headers = ['Authorization: Bearer '.getenv('WEBOT_API_KEY'), 'Content-Type: application/json'];
if ($nonce) $headers[] = 'Idempotency-Key: '.$nonce;
$ch = curl_init($base.$path);
curl_setopt_array($ch, [CURLOPT_RETURNTRANSFER=>true, CURLOPT_POST=>true,
CURLOPT_TIMEOUT=>180, CURLOPT_HTTPHEADER=>$headers,
CURLOPT_POSTFIELDS=>json_encode($body, JSON_THROW_ON_ERROR)]);
$raw = curl_exec($ch); $status = curl_getinfo($ch, CURLINFO_HTTP_CODE); curl_close($ch);
if ($raw === false || $status < 200 || $status >= 300) throw new RuntimeException('WEBOT HTTP '.$status);
return json_decode($raw, true, 64, JSON_THROW_ON_ERROR);
}
$quote = post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote', ['input'=>$input])['quote'];
$job = post('/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests', ['input'=>$input, 'quoted_credits'=>$quote['credits_consumed']], $nonce);
echo json_encode($job, JSON_PRETTY_PRINT); // Connect to events_url with the same Bearer header.// Go 1.20+; save as main.go.
package main
import ("bytes"; "encoding/json"; "fmt"; "io"; "net/http"; "os"; "strings"; "time"; "crypto/rand"; "encoding/hex")
func main() {
base := strings.TrimRight(os.Getenv("WEBOT_BASE_URL"), "/")
raw, err := os.ReadFile("input.json"); if err != nil { panic(err) }
nonce := os.Getenv("WEBOT_JOB_NONCE")
if nonce == "" { b := make([]byte,16); if _,err:=rand.Read(b);err!=nil {panic(err)}; nonce=hex.EncodeToString(b) }
// Persist nonce before the submission; reuse on ambiguous responses.
client := &http.Client{Timeout:180*time.Second}
post := func(path string, body any, id string) map[string]any {
data, err := json.Marshal(body); if err != nil {panic(err)}
req, err := http.NewRequest("POST",base+path,bytes.NewReader(data)); if err!=nil {panic(err)}
req.Header.Set("Authorization","Bearer "+os.Getenv("WEBOT_API_KEY")); req.Header.Set("Content-Type","application/json")
if id!="" {req.Header.Set("Idempotency-Key",id)}
res,err:=client.Do(req); if err!=nil {panic(err)}; defer res.Body.Close()
data,err=io.ReadAll(res.Body); if err!=nil {panic(err)}
if res.StatusCode<200||res.StatusCode>=300 {panic(string(data))}
var result map[string]any; if err=json.Unmarshal(data,&result);err!=nil {panic(err)}; return result
}
input:=json.RawMessage(raw)
quote:=post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote",map[string]any{"input":input},"")["quote"].(map[string]any)
job:=post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests",map[string]any{"input":input,"quoted_credits":quote["credits_consumed"]},nonce)
fmt.Println(job) // Stream events_url with the same Authorization header.
}// Java 11+, Jackson databind dependency; class Main in Main.java.
import java.net.URI;
import java.net.http.*;
import java.nio.file.*;
import java.time.Duration;
import java.util.UUID;
import com.fasterxml.jackson.databind.*;
import com.fasterxml.jackson.databind.node.ObjectNode;
public class Main {
static final ObjectMapper json = new ObjectMapper();
static final HttpClient client = HttpClient.newHttpClient();
static final String base = System.getenv("WEBOT_BASE_URL").replaceAll("/$", "");
static JsonNode post(String path, JsonNode body, String nonce) throws Exception {
var b = HttpRequest.newBuilder(URI.create(base+path)).timeout(Duration.ofSeconds(180))
.header("Authorization","Bearer "+System.getenv("WEBOT_API_KEY")).header("Content-Type","application/json")
.POST(HttpRequest.BodyPublishers.ofString(json.writeValueAsString(body)));
if(nonce!=null)b.header("Idempotency-Key",nonce);
var r=client.send(b.build(),HttpResponse.BodyHandlers.ofString());
if(r.statusCode()<200||r.statusCode()>=300)throw new IllegalStateException(r.body());
return json.readTree(r.body());
}
public static void main(String[] args) throws Exception {
var input=json.readTree(Files.readString(Path.of("input.json")));
ObjectNode body=json.createObjectNode();body.set("input",input);
var quote=post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote",body,null).get("quote");
body.put("quoted_credits",quote.get("credits_consumed").asInt());
String nonce=System.getenv("WEBOT_JOB_NONCE");if(nonce==null)nonce=UUID.randomUUID().toString(); // Persist before POST.
var job=post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests",body,nonce);System.out.println(job);
// Subscribe to job.events_url with Authorization; use BodyHandlers.ofLines().
}
}// .NET 8 console app, top-level statements.
using System.Net.Http;
using System.Text;
using System.Text.Json.Nodes;
var client = new HttpClient { Timeout = TimeSpan.FromSeconds(180) };
var root = Environment.GetEnvironmentVariable("WEBOT_BASE_URL")!.TrimEnd('/');
var key = Environment.GetEnvironmentVariable("WEBOT_API_KEY");
async Task<JsonNode> Post(string path, JsonNode body, string? nonce = null) {
using var req = new HttpRequestMessage(HttpMethod.Post, root + path);
req.Headers.Add("Authorization", "Bearer " + key);
if (nonce != null) req.Headers.Add("Idempotency-Key", nonce);
req.Content = new StringContent(body.ToJsonString(), Encoding.UTF8, "application/json");
using var res = await client.SendAsync(req);
var raw = await res.Content.ReadAsStringAsync();res.EnsureSuccessStatusCode();
return JsonNode.Parse(raw)!;
}
var input = JsonNode.Parse(await File.ReadAllTextAsync("input.json"));
var body = new JsonObject { ["input"] = input };
var quote = await Post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote", body);
body["quoted_credits"] = quote["quote"]!["credits_consumed"]!.GetValue<int>();
var nonce = Environment.GetEnvironmentVariable("WEBOT_JOB_NONCE") ?? Guid.NewGuid().ToString(); // Persist before submitting.
var job = await Post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests", body, nonce);
Console.WriteLine(job); // Subscribe to events_url with the same Bearer header and ResponseHeadersRead.# Ruby 3+, standard library only.
require 'net/http'
require 'json'
require 'securerandom'
base = ENV.fetch('WEBOT_BASE_URL').sub(%r{/$}, '')
post = lambda do |path, body, nonce = nil|
uri = URI(base + path)
req = Net::HTTP::Post.new(uri)
req['Authorization'] = 'Bearer ' + ENV.fetch('WEBOT_API_KEY')
req['Content-Type'] = 'application/json'
req['Idempotency-Key'] = nonce if nonce
req.body = JSON.generate(body)
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true, read_timeout: 180) { |http| http.request(req) }
raise res.body unless res.is_a?(Net::HTTPSuccess)
JSON.parse(res.body)
end
input = JSON.parse(File.read('input.json'))
quote = post.call('/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote', {'input' => input})['quote']
nonce = ENV['WEBOT_JOB_NONCE'] || SecureRandom.uuid # Persist this before submission.
job = post.call('/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests', {'input' => input, 'quoted_credits' => quote['credits_consumed']}, nonce)
puts JSON.pretty_generate(job) # Subscribe to events_url with the same Authorization header.// Swift 5.9 server-side/CLI only. Do not embed customer keys in shipped apps.
import Foundation
#if canImport(FoundationNetworking)
import FoundationNetworking
#endif
@main struct Main {
static func main() async throws {
let env=ProcessInfo.processInfo.environment
let base=env["WEBOT_BASE_URL"]!.trimmingCharacters(in: CharacterSet(charactersIn:"/"))
let input=try JSONSerialization.jsonObject(with: Data(contentsOf:URL(fileURLWithPath:"input.json")))
func post(_ path:String,_ body:[String:Any],_ nonce:String?=nil) async throws -> [String:Any] {
var req=URLRequest(url:URL(string:base+path)!);req.httpMethod="POST";req.timeoutInterval=180
req.setValue("Bearer "+env["WEBOT_API_KEY"]!,forHTTPHeaderField:"Authorization")
req.setValue("application/json",forHTTPHeaderField:"Content-Type")
if let nonce {req.setValue(nonce,forHTTPHeaderField:"Idempotency-Key")}
req.httpBody=try JSONSerialization.data(withJSONObject:body)
let (data,res)=try await URLSession.shared.data(for:req)
guard let http=res as? HTTPURLResponse,(200..<300).contains(http.statusCode) else {throw NSError(domain:"WEBOT",code:1)}
return try JSONSerialization.jsonObject(with:data) as! [String:Any]
}
let quote=try await post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote",["input":input])["quote"] as! [String:Any]
let nonce=env["WEBOT_JOB_NONCE"] ?? UUID().uuidString // Persist before submission.
let job=try await post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests",["input":input,"quoted_credits":quote["credits_consumed"]!],nonce)
print(job) // Subscribe to events_url with the same Authorization header.
}
}// Server-side Kotlin/JVM 17+, Gradle dependencies: OkHttp 4.12, org.json 20240303.
import okhttp3.*
import okhttp3.MediaType.Companion.toMediaType
import okhttp3.RequestBody.Companion.toRequestBody
import org.json.JSONObject
import java.io.File
import java.util.UUID
import java.util.concurrent.TimeUnit
fun main() {
val base=System.getenv("WEBOT_BASE_URL").trimEnd('/')
val client=OkHttpClient.Builder().readTimeout(180,TimeUnit.SECONDS).build()
fun post(path:String,body:JSONObject,nonce:String?=null):JSONObject {
val b=Request.Builder().url(base+path).header("Authorization","Bearer "+System.getenv("WEBOT_API_KEY"))
.post(body.toString().toRequestBody("application/json".toMediaType()))
if(nonce!=null)b.header("Idempotency-Key",nonce)
return client.newCall(b.build()).execute().use {res ->
val raw=res.body!!.string();check(res.isSuccessful){raw};JSONObject(raw)
}
}
val body=JSONObject().put("input",JSONObject(File("input.json").readText()))
val quote=post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/quote",body).getJSONObject("quote")
body.put("quoted_credits",quote.getInt("credits_consumed"))
val nonce=System.getenv("WEBOT_JOB_NONCE") ?: UUID.randomUUID().toString() // Persist before submission.
val job=post("/api/v1/models/creative_67cba3d8279e504deb8c38a5/requests",body,nonce)
println(job) // Subscribe to events_url with the same Authorization header.
}5. Receive all results
The response includes a stable WEBOT request_id, events_url and result_url. Subscribe with a Bearer-authenticated HTTP stream. Nonterminal streams end after 25 seconds; reconnect to the same URL after at least 1.5 seconds. Current saved state is replayed immediately, including completion that happened while disconnected. A terminal event contains the result envelope. The JSON terminal flag describes generation completion. Keep reconnecting while financial_pending is true; stop after the terminal event confirms financial settlement. Never poll provider status/results. Native browser EventSource cannot send a Bearer header; keep the key on your server.
Completed output contains the full model result, including every generated media/document item, not just the first URL. Failed output is null with error and refund_state. Results are strictly limited to the key owner, including on reseller domains. Model-independent aliases: /api/v1/requests/{request_id}/result and /events. Revoking a key blocks subsequent reads and streams; saved results remain accessible with another valid key of the same account.
6. Schemas and parameter defaults
Required fields are marked with *. Required text must contain non-whitespace content. Defaults apply when an optional parameter is omitted; null, false, 0 and an empty array are distinct values. “No documented default” means WEBOT does not invent one. Examples are sample inputs, not defaults. WEBOT generation constraints can require an explicit value even when the provider publishes an automatic default.
Input schema · fields, constraints and defaults
| Parameter | Type | Required | Default when omitted | Description / constraints |
|---|---|---|---|---|
controlnets | array | No | [] | The control nets to use for the image generation. You can use any number of control nets and they will be applied to the image at the specified timesteps. |
controlnets[].config_url | string | null | No | No documented default | optional URL to the controlnet config.json file. |
controlnets[].mask_url | string | null | No | No documented default | The mask to use for the controlnet. When using a mask, the control image size and the mask size must be the same and divisible by 32. |
controlnets[].image_url | string | Yes * | No documented default | URL of the image to be used as the control net. |
controlnets[].path | string | Yes * | No documented default | URL or the path to the control net weights. |
controlnets[].end_percentage | number | No | 1 |
The percentage of the image to end applying the controlnet in terms of the total timesteps.
minimum: 0 · maximum: 1 |
controlnets[].start_percentage | number | No | 0 |
The percentage of the image to start applying the controlnet in terms of the total timesteps.
minimum: 0 · maximum: 1 |
controlnets[].conditioning_scale | number | No | 1 |
The scale of the control net weight. This is used to scale the control net weight
before merging it with the base model.
minimum: 0 · maximum: 2 |
controlnets[].ip_adapter_index | integer | null | No | No documented default | The index of the IP adapter to be applied to the controlnet. This is only needed for InstantID ControlNets. |
controlnets[].variant | string | null | No | No documented default | The optional variant if a Hugging Face repo key is used. |
controlnet_guess_mode | boolean | No | false | If set to true, the controlnet will be applied to only the conditional predictions. |
mask_url | string | null | No | No documented default | URL of black-and-white image to use as mask during inpainting. |
image_url | string | null | No | No documented default | URL of image to use for image to image/inpainting. |
image_format | string | No | "png" | The format of the generated image. enum: ["jpeg","png"] |
ic_light_model_background_image_url | string | null | No | No documented default | The URL of the IC Light model background image to use for the image generation. Make sure to use a background compatible with the model. |
ic_light_image_url | string | null | No | No documented default | The URL of the IC Light model image to use for the image generation. |
eta | number | No | 0 | The eta value to be used for the image generation. minimum: 0 · maximum: 1 |
seed | integer | null | No | No documented default | The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time. |
unet_name | string | null | No | No documented default | URL or HuggingFace ID of the custom U-Net model to use for the image generation. |
timesteps | object | No | {"array":[],"method":"default"} | Optionally override the timesteps to use for the denoising process. Only works with schedulers which support the `timesteps` argument in their `set_timesteps` method. Defaults to not overriding, in which case the scheduler automatically sets the timesteps based on the `num_inference_steps` parameter. If set to a custom timestep schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `sigmas` is set. |
timesteps.array | array | No | [] | Timesteps schedule to be used if 'custom' method is selected. |
timesteps.method | string | No | "default" |
The method to use for the timesteps. If set to 'array', the timesteps will be set based
on the provided timesteps schedule in the `array` field.
Defaults to 'default' which means the scheduler will use the `num_inference_steps` parameter.
enum: ["default","array"] |
tile_stride_width | integer | No | 2048 | The stride of the tiles to be used for the image generation. minimum: 64 · maximum: 2048 |
embeddings | array | No | [] | The embeddings to use for the image generation. Only a single embedding is supported at the moment. The embeddings will be used to map the tokens in the prompt to the embedding weights. |
embeddings[].tokens | array | null | No | No documented default | The tokens to map the embedding weights to. Use these tokens in your prompts. When omitted, tokens are generated as <s0>, <s1>, ... to match the number of vectors in the embedding file. |
embeddings[].path | string | Yes * | No documented default | URL or the path to the embedding weights. |
tile_height | integer | No | 4096 | The size of the tiles to be used for the image generation. minimum: 128 · maximum: 4096 |
enable_safety_checker | boolean | No | false | If set to true, the safety checker will be enabled. |
debug_latents | boolean | No | false | If set to true, the latents will be saved for debugging. |
rescale_betas_snr_zero | boolean | No | false | Whether to set the rescale_betas_snr_zero option or not for the sampler |
prediction_type | string | No | "epsilon" |
The type of prediction to use for the image generation.
The `epsilon` is the default.
enum: ["v_prediction","epsilon"] |
guidance_scale | number | No | 7.5 |
The CFG (Classifier Free Guidance) scale is a measure of how close you want
the model to stick to your prompt when looking for a related image to show you.
minimum: 0 · maximum: 20 |
debug_per_pass_latents | boolean | No | false | If set to true, the latents will be saved for debugging per pass. |
negative_prompt | string | No | "" | The negative prompt to use.Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). |
variant | string | null | No | No documented default | The variant of the model to use for huggingface models, e.g. 'fp16'. |
num_inference_steps | integer | No | 30 |
Increasing the amount of steps tells Stable Diffusion that it should take more steps
to generate your final result which can increase the amount of detail in your image.
minimum: 1 · maximum: 150 |
model_name | string | Yes * | No documented default | URL or HuggingFace ID of the base model to generate the image. |
image_encoder_weight_name | string | null | No | "pytorch_model.bin" | The weight name of the image encoder model to use for the image generation. |
ic_light_model_url | string | null | No | No documented default | The URL of the IC Light model to use for the image generation. |
num_images | integer | No | 1 |
Number of images to generate in one request. Note that the higher the batch size,
the longer it will take to generate the images.
minimum: 1 · maximum: 8 |
noise_strength | number | No | 0.5 | The amount of noise to add to noise image for image. Only used if the image_url is provided. 1.0 is complete noise and values near 0 are minimal noise. maximum: 1 · exclusiveMinimum: 0 |
tile_stride_height | integer | No | 2048 | The stride of the tiles to be used for the image generation. minimum: 64 · maximum: 2048 |
clip_skip | integer | No | 0 |
Skips part of the image generation process, leading to slightly different results.
This means the image renders faster, too.
minimum: 0 · maximum: 2 |
prompt | string | Yes * | No documented default | The prompt to use for generating the image. Be as descriptive as possible for best results. |
prompt_weighting | boolean | No | false | If set to true, the prompt weighting syntax will be used. Additionally, this will lift the 77 token limit by averaging embeddings. |
image_encoder_subfolder | string | null | No | No documented default | Subfolder containing the image encoder weights in image_encoder_path. |
loras | array | No | [] | The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image. |
loras[].scale | number | No | 1 |
The scale of the LoRA weight. This is used to scale the LoRA weight
before merging it with the base model.
minimum: 0 · maximum: 4 |
loras[].path | string | Yes * | No documented default | URL or the path to the LoRA weights. |
tile_width | integer | No | 4096 | The size of the tiles to be used for the image generation. minimum: 128 · maximum: 4096 |
ip_adapter | array | No | [] | IP adapters for image generation. A non-empty list requires image_encoder_path. |
ip_adapter[].ip_adapter_mask_url | string | null | No | No documented default | The mask to use for the IP adapter. When using a mask, the ip-adapter image size and the mask size must be the same |
ip_adapter[].ip_adapter_image_url | string | array | Yes * | No documented default | URL of the image to be used as the IP adapter. |
ip_adapter[].insight_face_model_path | string | null | No | No documented default | URL or the path to the InsightFace model weights. |
ip_adapter[].path | string | Yes * | No documented default | URL or the path to the IP adapter weights. |
ip_adapter[].model_subfolder | string | null | No | No documented default | Subfolder in the model directory where the IP adapter weights are stored. |
ip_adapter[].scale | number | No | 1 |
The scale of the IP adapter weight. This is used to scale the IP adapter weight
before merging it with the base model.
minimum: 0 |
ip_adapter[].image_projection_shortcut | boolean | No | true | The value to set the image projection shortcut to. For FaceID plus V1 models, this should be set to False. For FaceID plus V2 models, this should be set to True. Default is True. |
ip_adapter[].unconditional_noising_factor | number | No | 0 | The factor to apply to the unconditional noising of the IP adapter. minimum: 0 · maximum: 1 |
ip_adapter[].scale_json | object | null | No | No documented default | The scale of the IP adapter weight. This is used to scale the IP adapter weight before merging it with the base model. |
ip_adapter[].weight_name | string | null | No | No documented default | Name of the weight file. |
scheduler | string | null | No | No documented default | Scheduler / sampler to use for the image denoising process. |
image_encoder_path | string | null | No | No documented default | Hugging Face ID or HTTPS URL of the image encoder; required when ip_adapter is non-empty. Choose an encoder compatible with the IP-Adapter weights. For h94/IP-Adapter SDXL weights, use h94/IP-Adapter with image_encoder_subfolder='sdxl_models/image_encoder'; for SD1.5 weights, use image_encoder_subfolder='models/image_encoder'. |
sigmas | object | No | {"array":[],"method":"default"} | Optionally override the sigmas to use for the denoising process. Only works with schedulers which support the `sigmas` argument in their `set_sigmas` method. Defaults to not overriding, in which case the scheduler automatically sets the sigmas based on the `num_inference_steps` parameter. If set to a custom sigma schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `timesteps` is set. |
sigmas.array | array | No | [] | Sigmas schedule to be used if 'custom' method is selected. |
sigmas.method | string | No | "default" |
The method to use for the sigmas. If set to 'custom', the sigmas will be set based
on the provided sigmas schedule in the `array` field.
Defaults to 'default' which means the scheduler will use the sigmas of the scheduler.
enum: ["default","array"] |
{
"then": {
"required": [
"image_encoder_path"
],
"properties": {
"image_encoder_path": {
"minLength": 1,
"type": "string"
}
}
},
"type": "object",
"properties": {
"controlnets": {
"items": {
"required": [
"path",
"image_url"
],
"type": "object",
"properties": {
"config_url": {
"title": "Config Url",
"description": "optional URL to the controlnet config.json file.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"mask_url": {
"title": "Mask Url",
"description": "\n The mask to use for the controlnet. When using a mask, the control image size and the mask size must be the same and divisible by 32.\n ",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"image_url": {
"type": "string",
"title": "Image Url",
"description": "URL of the image to be used as the control net."
},
"path": {
"type": "string",
"title": "Path",
"description": "URL or the path to the control net weights."
},
"end_percentage": {
"maximum": 1,
"default": 1,
"type": "number",
"title": "End Percentage",
"description": "\n The percentage of the image to end applying the controlnet in terms of the total timesteps.\n ",
"minimum": 0
},
"start_percentage": {
"maximum": 1,
"default": 0,
"type": "number",
"title": "Start Percentage",
"description": "\n The percentage of the image to start applying the controlnet in terms of the total timesteps.\n ",
"minimum": 0
},
"conditioning_scale": {
"maximum": 2,
"default": 1,
"type": "number",
"title": "Conditioning Scale",
"description": "\n The scale of the control net weight. This is used to scale the control net weight\n before merging it with the base model.\n ",
"minimum": 0
},
"ip_adapter_index": {
"title": "Ip Adapter Index",
"description": "\n The index of the IP adapter to be applied to the controlnet. This is only needed for InstantID ControlNets.\n ",
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"variant": {
"title": "Variant",
"description": "The optional variant if a Hugging Face repo key is used.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"title": "ControlNet",
"x-webot-order-properties": [
"path",
"config_url",
"variant",
"image_url",
"mask_url",
"conditioning_scale",
"start_percentage",
"end_percentage",
"ip_adapter_index"
],
"allOf": [
{
"if": {
"required": [
"mask_url"
],
"properties": {
"mask_url": {
"type": "string",
"minLength": 1
}
}
},
"then": {
"required": [
"image_url"
],
"properties": {
"image_url": {
"type": "string",
"minLength": 1
}
}
},
"x-webot-message": "mask url requires image url."
}
]
},
"type": "array",
"title": "Controlnets",
"description": "\n The control nets to use for the image generation. You can use any number of control nets\n and they will be applied to the image at the specified timesteps.\n ",
"default": []
},
"controlnet_guess_mode": {
"type": "boolean",
"title": "Controlnet Guess Mode",
"description": "\n If set to true, the controlnet will be applied to only the conditional predictions.\n ",
"default": false
},
"mask_url": {
"title": "Mask Url",
"description": "URL of black-and-white image to use as mask during inpainting.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"image_url": {
"title": "Image Url",
"description": "URL of image to use for image to image/inpainting.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"image_format": {
"description": "The format of the generated image.",
"default": "png",
"type": "string",
"title": "Image Format",
"examples": [
"jpeg"
],
"enum": [
"jpeg",
"png"
]
},
"ic_light_model_background_image_url": {
"title": "Ic Light Model Background Image Url",
"description": "\n The URL of the IC Light model background image to use for the image generation.\n Make sure to use a background compatible with the model.\n ",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"ic_light_image_url": {
"title": "Ic Light Image Url",
"description": "\n The URL of the IC Light model image to use for the image generation.\n ",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"eta": {
"maximum": 1,
"default": 0,
"type": "number",
"title": "Eta",
"description": "The eta value to be used for the image generation.",
"minimum": 0
},
"seed": {
"title": "Seed",
"description": "\n The same seed and the same prompt given to the same version of Stable Diffusion\n will output the same image every time.\n ",
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"unet_name": {
"title": "Unet Name",
"description": "URL or HuggingFace ID of the custom U-Net model to use for the image generation.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"timesteps": {
"type": "object",
"properties": {
"array": {
"items": {
"type": "integer"
},
"type": "array",
"title": "Array",
"description": "\n Timesteps schedule to be used if 'custom' method is selected.\n ",
"default": []
},
"method": {
"default": "default",
"type": "string",
"title": "Method",
"description": "\n The method to use for the timesteps. If set to 'array', the timesteps will be set based\n on the provided timesteps schedule in the `array` field.\n Defaults to 'default' which means the scheduler will use the `num_inference_steps` parameter.\n ",
"enum": [
"default",
"array"
]
}
},
"title": "TimestepsInput",
"x-webot-order-properties": [
"method",
"array"
],
"default": {
"array": [],
"method": "default"
},
"description": "\n Optionally override the timesteps to use for the denoising process. Only works with schedulers which support the `timesteps` argument in their `set_timesteps` method.\n Defaults to not overriding, in which case the scheduler automatically sets the timesteps based on the `num_inference_steps` parameter.\n If set to a custom timestep schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `sigmas` is set.\n "
},
"tile_stride_width": {
"maximum": 2048,
"default": 2048,
"type": "integer",
"title": "Tile Stride Width",
"description": "The stride of the tiles to be used for the image generation.",
"minimum": 64
},
"embeddings": {
"items": {
"required": [
"path"
],
"type": "object",
"properties": {
"tokens": {
"title": "Tokens",
"description": "\n The tokens to map the embedding weights to. Use these tokens in your\n prompts. When omitted, tokens are generated as <s0>, <s1>, ... to\n match the number of vectors in the embedding file.\n ",
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
]
},
"path": {
"type": "string",
"title": "Path",
"description": "URL or the path to the embedding weights."
}
},
"title": "Embedding",
"x-webot-order-properties": [
"path",
"tokens"
]
},
"type": "array",
"title": "Embeddings",
"description": "\n The embeddings to use for the image generation. Only a single embedding is supported at the moment.\n The embeddings will be used to map the tokens in the prompt to the embedding weights.\n ",
"default": []
},
"tile_height": {
"maximum": 4096,
"default": 4096,
"type": "integer",
"title": "Tile Height",
"description": "The size of the tiles to be used for the image generation.",
"minimum": 128
},
"enable_safety_checker": {
"type": "boolean",
"title": "Enable Safety Checker",
"description": "If set to true, the safety checker will be enabled.",
"default": false
},
"debug_latents": {
"type": "boolean",
"title": "Debug Latents",
"description": "If set to true, the latents will be saved for debugging.",
"default": false
},
"rescale_betas_snr_zero": {
"type": "boolean",
"title": "Rescale Betas Snr Zero",
"description": "\n Whether to set the rescale_betas_snr_zero option or not for the sampler\n ",
"default": false
},
"prediction_type": {
"default": "epsilon",
"type": "string",
"title": "Prediction Type",
"description": "\n The type of prediction to use for the image generation.\n The `epsilon` is the default.\n ",
"enum": [
"v_prediction",
"epsilon"
]
},
"guidance_scale": {
"maximum": 20,
"default": 7.5,
"type": "number",
"title": "Guidance scale (CFG)",
"description": "\n The CFG (Classifier Free Guidance) scale is a measure of how close you want\n the model to stick to your prompt when looking for a related image to show you.\n ",
"minimum": 0
},
"debug_per_pass_latents": {
"type": "boolean",
"title": "Debug Per Pass Latents",
"description": "If set to true, the latents will be saved for debugging per pass.",
"default": false
},
"negative_prompt": {
"default": "",
"type": "string",
"title": "Negative Prompt",
"examples": [
"cartoon, painting, illustration, worst quality, low quality, normal quality"
],
"description": "\n The negative prompt to use.Use it to address details that you don't want\n in the image. This could be colors, objects, scenery and even the small details\n (e.g. moustache, blurry, low resolution).\n "
},
"variant": {
"title": "Variant",
"description": "The variant of the model to use for huggingface models, e.g. 'fp16'.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"num_inference_steps": {
"maximum": 150,
"default": 30,
"type": "integer",
"title": "Number of inference steps",
"description": "\n Increasing the amount of steps tells Stable Diffusion that it should take more steps\n to generate your final result which can increase the amount of detail in your image.\n ",
"minimum": 1
},
"model_name": {
"type": "string",
"title": "Model Name",
"examples": [
"stabilityai/stable-diffusion-xl-base-1.0",
"runwayml/stable-diffusion-v1-5",
"SG161222/Realistic_Vision_V2.0"
],
"description": "URL or HuggingFace ID of the base model to generate the image."
},
"image_encoder_weight_name": {
"description": "\n The weight name of the image encoder model to use for the image generation.\n ",
"default": "pytorch_model.bin",
"title": "Image Encoder Weight Name",
"examples": [
"pytorch_model.bin"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"ic_light_model_url": {
"title": "Ic Light Model Url",
"description": "\n The URL of the IC Light model to use for the image generation.\n ",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"num_images": {
"maximum": 8,
"default": 1,
"type": "integer",
"title": "Number of images",
"description": "\n Number of images to generate in one request. Note that the higher the batch size,\n the longer it will take to generate the images.\n ",
"minimum": 1
},
"noise_strength": {
"maximum": 1,
"exclusiveMinimum": 0,
"type": "number",
"title": "Noise Strength",
"description": "The amount of noise to add to noise image for image. Only used if the image_url is provided. 1.0 is complete noise and values near 0 are minimal noise.",
"default": 0.5
},
"tile_stride_height": {
"maximum": 2048,
"default": 2048,
"type": "integer",
"title": "Tile Stride Height",
"description": "The stride of the tiles to be used for the image generation.",
"minimum": 64
},
"clip_skip": {
"maximum": 2,
"default": 0,
"type": "integer",
"title": "Clip Skip",
"description": "\n Skips part of the image generation process, leading to slightly different results.\n This means the image renders faster, too.\n ",
"minimum": 0
},
"prompt": {
"type": "string",
"title": "Prompt",
"examples": [
"Photo of a european medieval 40 year old queen, silver hair, highly detailed face, detailed eyes, head shot, intricate crown, age spots, wrinkles",
"Photo of a classic red mustang car parked in las vegas strip at night"
],
"description": "The prompt to use for generating the image. Be as descriptive as possible for best results."
},
"prompt_weighting": {
"default": false,
"type": "boolean",
"title": "Prompt Weighting",
"examples": [
true
],
"description": "\n If set to true, the prompt weighting syntax will be used.\n Additionally, this will lift the 77 token limit by averaging embeddings.\n "
},
"image_encoder_subfolder": {
"description": "Subfolder containing the image encoder weights in image_encoder_path.",
"title": "Image Encoder Subfolder",
"examples": [],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"loras": {
"items": {
"required": [
"path"
],
"type": "object",
"properties": {
"scale": {
"maximum": 4,
"default": 1,
"type": "number",
"title": "Scale",
"description": "\n The scale of the LoRA weight. This is used to scale the LoRA weight\n before merging it with the base model.\n ",
"minimum": 0
},
"path": {
"type": "string",
"title": "Path",
"description": "URL or the path to the LoRA weights."
}
},
"title": "LoraWeight",
"x-webot-order-properties": [
"path",
"scale"
]
},
"type": "array",
"title": "Loras",
"description": "\n The LoRAs to use for the image generation. You can use any number of LoRAs\n and they will be merged together to generate the final image.\n ",
"default": []
},
"tile_width": {
"maximum": 4096,
"default": 4096,
"type": "integer",
"title": "Tile Width",
"description": "The size of the tiles to be used for the image generation.",
"minimum": 128
},
"ip_adapter": {
"items": {
"required": [
"ip_adapter_image_url",
"path"
],
"type": "object",
"properties": {
"ip_adapter_mask_url": {
"title": "Ip Adapter Mask Url",
"description": "\n The mask to use for the IP adapter. When using a mask, the ip-adapter image size and the mask size must be the same\n ",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"ip_adapter_image_url": {
"title": "Ip Adapter Image Url",
"description": "URL of the image to be used as the IP adapter.",
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
},
"insight_face_model_path": {
"title": "Insight Face Model Path",
"description": "URL or the path to the InsightFace model weights.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"path": {
"type": "string",
"title": "Path",
"description": "URL or the path to the IP adapter weights."
},
"model_subfolder": {
"title": "Model Subfolder",
"description": "Subfolder in the model directory where the IP adapter weights are stored.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"scale": {
"default": 1,
"type": "number",
"title": "Scale",
"description": "\n The scale of the IP adapter weight. This is used to scale the IP adapter weight\n before merging it with the base model.\n ",
"minimum": 0
},
"image_projection_shortcut": {
"type": "boolean",
"title": "Image Projection Shortcut",
"description": "\n The value to set the image projection shortcut to. For FaceID plus V1 models,\n this should be set to False. For FaceID plus V2 models, this should be set to True.\n Default is True.\n ",
"default": true
},
"unconditional_noising_factor": {
"maximum": 1,
"default": 0,
"type": "number",
"title": "Unconditional Noising Factor",
"description": "The factor to apply to the unconditional noising of the IP adapter.",
"minimum": 0
},
"scale_json": {
"title": "Scale Json",
"description": "\n The scale of the IP adapter weight. This is used to scale the IP adapter weight\n before merging it with the base model.\n ",
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
]
},
"weight_name": {
"title": "Weight Name",
"description": "Name of the weight file.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"title": "IPAdapter",
"x-webot-order-properties": [
"ip_adapter_image_url",
"ip_adapter_mask_url",
"path",
"model_subfolder",
"weight_name",
"insight_face_model_path",
"scale",
"scale_json",
"unconditional_noising_factor",
"image_projection_shortcut"
],
"allOf": [
{
"if": {
"required": [
"ip_adapter_mask_url"
],
"properties": {
"ip_adapter_mask_url": {
"type": "string",
"minLength": 1
}
}
},
"then": {
"required": [
"ip_adapter_image_url"
],
"properties": {
"ip_adapter_image_url": {
"type": "string",
"minLength": 1
}
}
},
"x-webot-message": "ip adapter mask url requires ip adapter image url."
}
]
},
"type": "array",
"title": "Ip Adapter",
"description": "IP adapters for image generation. A non-empty list requires image_encoder_path.",
"default": []
},
"scheduler": {
"title": "Scheduler",
"description": "Scheduler / sampler to use for the image denoising process.",
"anyOf": [
{
"type": "string",
"enum": [
"DPM++ 2M",
"DPM++ 2M Karras",
"DPM++ 2M SDE",
"DPM++ 2M SDE Karras",
"Euler",
"Euler A",
"Euler (trailing timesteps)",
"LCM",
"LCM (trailing timesteps)",
"DDIM",
"TCD"
]
},
{
"type": "null"
}
]
},
"image_encoder_path": {
"title": "Image Encoder Path",
"description": "Hugging Face ID or HTTPS URL of the image encoder; required when ip_adapter is non-empty. Choose an encoder compatible with the IP-Adapter weights. For h94/IP-Adapter SDXL weights, use h94/IP-Adapter with image_encoder_subfolder='sdxl_models/image_encoder'; for SD1.5 weights, use image_encoder_subfolder='models/image_encoder'.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"sigmas": {
"type": "object",
"properties": {
"array": {
"items": {
"type": "number"
},
"type": "array",
"title": "Array",
"description": "\n Sigmas schedule to be used if 'custom' method is selected.\n ",
"default": []
},
"method": {
"default": "default",
"type": "string",
"title": "Method",
"description": "\n The method to use for the sigmas. If set to 'custom', the sigmas will be set based\n on the provided sigmas schedule in the `array` field.\n Defaults to 'default' which means the scheduler will use the sigmas of the scheduler.\n ",
"enum": [
"default",
"array"
]
}
},
"title": "SigmasInput",
"x-webot-order-properties": [
"method",
"array"
],
"default": {
"array": [],
"method": "default"
},
"description": "\n Optionally override the sigmas to use for the denoising process. Only works with schedulers which support the `sigmas` argument in their `set_sigmas` method.\n Defaults to not overriding, in which case the scheduler automatically sets the sigmas based on the `num_inference_steps` parameter.\n If set to a custom sigma schedule, the `num_inference_steps` parameter will be ignored. Cannot be set if `timesteps` is set.\n "
}
},
"if": {
"required": [
"ip_adapter"
],
"properties": {
"ip_adapter": {
"minItems": 1
}
}
},
"title": "InpaintInput",
"x-webot-order-properties": [
"model_name",
"unet_name",
"variant",
"prompt",
"negative_prompt",
"prompt_weighting",
"image_url",
"mask_url",
"noise_strength",
"loras",
"embeddings",
"controlnets",
"controlnet_guess_mode",
"ip_adapter",
"image_encoder_path",
"image_encoder_subfolder",
"image_encoder_weight_name",
"ic_light_model_url",
"ic_light_model_background_image_url",
"ic_light_image_url",
"seed",
"num_inference_steps",
"guidance_scale",
"clip_skip",
"scheduler",
"timesteps",
"sigmas",
"prediction_type",
"rescale_betas_snr_zero",
"image_format",
"num_images",
"enable_safety_checker",
"tile_width",
"tile_height",
"tile_stride_width",
"tile_stride_height",
"eta",
"debug_latents",
"debug_per_pass_latents"
],
"required": [
"model_name",
"prompt"
],
"allOf": [
{
"not": {
"allOf": [
{
"required": [
"sigmas"
],
"properties": {
"sigmas": {
"required": [
"method"
],
"properties": {
"method": {
"const": "array"
}
}
}
}
},
{
"required": [
"timesteps"
],
"properties": {
"timesteps": {
"required": [
"method"
],
"properties": {
"method": {
"const": "array"
}
}
}
}
}
]
},
"x-webot-message": "Choose a custom sigma schedule or custom timesteps, not both."
},
{
"if": {
"required": [
"ip_adapter"
],
"properties": {
"ip_adapter": {
"type": "array",
"minItems": 1
}
}
},
"then": {
"required": [
"image_encoder_path"
],
"properties": {
"image_encoder_path": {
"type": "string",
"minLength": 1
}
}
},
"x-webot-message": "Choose an image encoder path when using IP adapters."
}
],
"x-webot-media-rules": [
{
"kind": "same_dimensions",
"source": "input.controlnets[].mask_url",
"target": "input.controlnets[].image_url",
"multiple": 32,
"message": "The mask and source image must have matching dimensions."
},
{
"kind": "same_dimensions",
"source": "input.ip_adapter[].ip_adapter_mask_url",
"target": "input.ip_adapter[].ip_adapter_image_url",
"multiple": 1,
"message": "The mask and source image must have matching dimensions."
}
]
}Output (inside result.output) schema · fields, constraints and defaults
| Parameter | Type | Required | Default when omitted | Description / constraints |
|---|---|---|---|---|
images | array | Yes * | No documented default | The generated image files info. |
images[].file_size | integer | null | No | No documented default | The size of the file in bytes. |
images[].content_type | string | null | No | No documented default | The mime type of the file. |
images[].file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
images[].url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
images[].width | integer | null | No | No documented default | The width of the image in pixels. |
images[].height | integer | null | No | No documented default | The height of the image in pixels. |
debug_latents | object | null | Yes * | No documented default | The latents saved for debugging. |
debug_latents.variant0.file_size | integer | null | No | No documented default | The size of the file in bytes. |
debug_latents.variant0.content_type | string | null | No | No documented default | The mime type of the file. |
debug_latents.variant0.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
debug_latents.variant0.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
has_nsfw_concepts | array | Yes * | No documented default | Whether the generated images contain NSFW concepts. |
seed | integer | Yes * | No documented default | Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed. |
debug_per_pass_latents | object | null | Yes * | No documented default | The latents saved for debugging per pass. |
debug_per_pass_latents.variant0.file_size | integer | null | No | No documented default | The size of the file in bytes. |
debug_per_pass_latents.variant0.content_type | string | null | No | No documented default | The mime type of the file. |
debug_per_pass_latents.variant0.file_name | string | null | No | No documented default | The name of the file. It will be auto-generated if not provided. |
debug_per_pass_latents.variant0.url | string | Yes * | No documented default | The URL where the file can be downloaded from. |
{
"required": [
"images",
"seed",
"has_nsfw_concepts",
"debug_latents",
"debug_per_pass_latents"
],
"type": "object",
"properties": {
"images": {
"items": {
"required": [
"url"
],
"type": "object",
"properties": {
"file_size": {
"description": "The size of the file in bytes.",
"title": "File Size",
"examples": [
4404019
],
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"content_type": {
"description": "The mime type of the file.",
"title": "Content Type",
"examples": [
"image/png"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"file_name": {
"description": "The name of the file. It will be auto-generated if not provided.",
"title": "File Name",
"examples": [
"z9RV14K95DvU.png"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"url": {
"type": "string",
"title": "Url",
"description": "The URL where the file can be downloaded from."
},
"width": {
"description": "The width of the image in pixels.",
"title": "Width",
"examples": [
1024
],
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"height": {
"description": "The height of the image in pixels.",
"title": "Height",
"examples": [
1024
],
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
}
},
"title": "Image",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size",
"width",
"height"
],
"description": "Represents an image file."
},
"type": "array",
"title": "Images",
"description": "The generated image files info."
},
"debug_latents": {
"anyOf": [
{
"required": [
"url"
],
"type": "object",
"properties": {
"file_size": {
"description": "The size of the file in bytes.",
"title": "File Size",
"examples": [
4404019
],
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"content_type": {
"description": "The mime type of the file.",
"title": "Content Type",
"examples": [
"image/png"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"file_name": {
"description": "The name of the file. It will be auto-generated if not provided.",
"title": "File Name",
"examples": [
"z9RV14K95DvU.png"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"url": {
"type": "string",
"title": "Url",
"description": "The URL where the file can be downloaded from."
}
},
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
]
},
{
"type": "null"
}
],
"description": "The latents saved for debugging."
},
"has_nsfw_concepts": {
"items": {
"type": "boolean"
},
"type": "array",
"title": "Has Nsfw Concepts",
"description": "Whether the generated images contain NSFW concepts."
},
"seed": {
"type": "integer",
"title": "Seed",
"description": "\n Seed of the generated Image. It will be the same value of the one passed in the\n input or the randomly generated that was used in case none was passed.\n "
},
"debug_per_pass_latents": {
"anyOf": [
{
"required": [
"url"
],
"type": "object",
"properties": {
"file_size": {
"description": "The size of the file in bytes.",
"title": "File Size",
"examples": [
4404019
],
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
]
},
"content_type": {
"description": "The mime type of the file.",
"title": "Content Type",
"examples": [
"image/png"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"file_name": {
"description": "The name of the file. It will be auto-generated if not provided.",
"title": "File Name",
"examples": [
"z9RV14K95DvU.png"
],
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"url": {
"type": "string",
"title": "Url",
"description": "The URL where the file can be downloaded from."
}
},
"title": "File",
"x-webot-order-properties": [
"url",
"content_type",
"file_name",
"file_size"
]
},
{
"type": "null"
}
],
"description": "The latents saved for debugging per pass."
}
},
"title": "OutputParameters",
"x-webot-order-properties": [
"images",
"seed",
"has_nsfw_concepts",
"debug_latents",
"debug_per_pass_latents"
]
}Errors and limits
401 invalid/expired/revoked key · 403 key scope or domain mismatch · 404 unavailable model or unowned request · 409 quote changed, balance, concurrency or idempotency conflict · 413 JSON exceeds 2 MB · 415 wrong content type · 422 invalid fields/media · 429 rate limit · 503 temporary/ambiguous submission. Respect Retry-After. Current limits per account: 12 quotes/submissions, 120 result reads and 8 stream connections per minute. One submission preparation at a time per account. Do not automatically regenerate failed jobs.
Your requests
LoRA - Inpainting · Your account only
Select Requests to load your history.
| Request ID | Created at (IST) | Status | Credits used | Refunded | Processing time | Report |
|---|
Your model analytics
LoRA - Inpainting · Request dates in IST
Select Analytics to load your metrics.
Request counts
Daily requests by their current status
Request outcomes
Completed, failed and pending requests
Credits used
Daily recorded charges before refunds
Processing time
Daily average for completed requests with recorded timing
Processing percentiles
Completed requests only · Time from submission to recorded completion
How to use LoRA — Inpainting
Mark the part you want changed, where a mask is supported. The model fills or edits that area using the surrounding scene and your instructions.
Required inputs
- Model Name: The model variant or processing mode. Names such as fast or pro indicate different variants, not a universal quality scale. Use the options listed here and compare a small sample.
- Prompt: Your instructions to the model. Say what you want, include the important details and avoid contradictory directions. For a video, describe the action as well as the scene.
Workflow
- Prepare your source material and fill the required inputs above. Review the supported settings for this model.
- Sign in to calculate the credit estimate. Review the estimate before choosing Generate.
- Keep this model page open while the request runs. Completed results arrive in the result area; use the available player or download controls to review the output.
When to use this workflow
- Remove or replace an unwanted part.
- Repair a selected area while guiding the edit.
Key settings
- Model Name
- The model variant or processing mode. Names such as fast or pro indicate different variants, not a universal quality scale. Use the options listed here and compare a small sample.
- Prompt
- Your instructions to the model. Say what you want, include the important details and avoid contradictory directions. For a video, describe the action as well as the scene.
- Unet Name
- A compatible saved model or learned adapter file. This is not an ordinary picture. Use the exact format and base-model compatibility required by this tool.
- Variant
- The model variant or processing mode. Names such as fast or pro indicate different variants, not a universal quality scale. Use the options listed here and compare a small sample.
- Negative Prompt
- Describe things you would prefer the model to avoid, such as unwanted blur or objects. This guides the result but is not a guarantee that those things will never appear.
- Prompt Weighting
- Allow the model’s syntax for giving some prompt words extra or reduced emphasis. Use only its documented notation; punctuation alone does not have the same effect in every model.