ios – tips on how to get actual place in video as picture view?

I wish to give picture modifying function in my app. so I’m permitting person so as to add textual content to picture and after that I wish to convert it to video utilizing Ffmpeg command.

right here is my command that provides textual content and convert picture to video.
ffmpeg -loop 1 -i /var/cellular/Containers/Information/Utility/88F535C3-A300-456C-97BB-1A9B83EAEE7B/Paperwork/Compress_Picture/enter.jpg -filter_complex "[0]scale=1080:trunc(ow/a/2)*2[video0];[video0]drawtext=textual content="Dyjfyjyrjyfjyfkyfk":fontfile=/non-public/var/containers/Bundle/Utility/DE5C8DAA-4D66-4345-834A-89F8AC19DF9B/Clear Standing.app/avenyt.ttf:fontsize=66.55112651646448:fontcolor=#FFFFFF:x=349.92:y=930.051993067591" -c:v libx264 -t 5 -pix_fmt yuv420p -y /var/cellular/Containers/Information/Utility/88F535C3-A300-456C-97BB-1A9B83EAEE7B/Paperwork/Compress_Picture/output0.mp4

right here is my swift code to generate command.

var filterComplex = ""
var inputs = ""
var audioIndex = ""

if currentPhotoTextDataArray.comprises(the place: { $0.isLocation }) {
 // No less than one factor has isLocation set to true
 // Do one thing right here
 print("There's a minimum of one factor with isLocation == true")
                            inputs = "-i (inputPath) -i (self.locImagePath)"
                            audioIndex = "2"
                            
                        } else {
                            // No components have isLocation == true
                            print("No components have isLocation set to true")
                            inputs = "-i (inputPath)"
                            audioIndex = "1"
                        }
                        
                        for (index, textData) in currentPhotoTextDataArray.enumerated() {
                            print("x: (textData.xPosition), y: (textData.yPosition)")
                            let x = (textData.xPosition) * 1080 / self.photoViewWidth
                            let y = (textData.yPosition) * 1920 / self.photoViewHeight
                            
                            let fontSizeForWidth = (textData.fontSize * 1080) / self.photoViewWidth
                            let fontSizeForHeight = (textData.fontSize * 1920) / self.photoViewHeight
                            print("fontSizeForWidth: (fontSizeForWidth)")
                            print("fontSizeForHeight: (fontSizeForHeight)")
                            
                            let fontPath = textData.font.fontPath
                            let fontColor = textData.fontColor.toHexOrASS(format: "hex")
                            let backColor = textData.backColor?.toHexOrASS(format: "hex")
                            print("fontPath: (fontPath)")
                            print("fontColor: (fontColor)")
                            
                            let breakedText = self.addBreaks(in: textData.textual content, with: UIFont(identify: textData.font.fontName, measurement: fontSizeForHeight) ?? UIFont(), forWidth: 1080, padding: Int(x))
                            
                            if textData.isLocation {
                                print("Location is there.")
                                
                                let textFont = UIFont(identify: textData.font.fontName, measurement: fontSizeForHeight)
                                let attributes: [NSAttributedString.Key: Any] = [NSAttributedString.Key.font: textFont ?? UIFont()]
                                let measurement = (textData.textual content as NSString).measurement(withAttributes: attributes)
                                let textWidth = Int(measurement.width) + 130
                                
                                var endTimeLoc = 0.0
                                if let audioData = self.audioDataArray.first(the place: { $0.photoIndex == mainIndex }) {
                                    let period = audioData.audioEndTime - audioData.audioStartTime
                                    endTimeLoc = period
                                } else {
                                    endTimeLoc = 5
                                }
                                
                                let layerFilter = "[email protected]:measurement=(textWidth)x130[layer0];[video(index)][layer0]overlay=allow="between(t,0,(endTimeLoc))":x=(x):y=((y)-(overlay_h/2))[layer1];"
                                filterComplex += layerFilter
                                let imageFilter = "[1:v]scale=80:80[image];[layer1][image]overlay=allow="between(t,0,(endTimeLoc))":x=(x)+10:y=((y)-(overlay_h/2))[v(index)];"
                                filterComplex += imageFilter
                                
                                if index == currentPhotoTextDataArray.rely - 1 {
                                    let textFilter = "[v(index)]drawtext=textual content="(breakedText)":fontfile=(fontPath):fontsize=(fontSizeForHeight):fontcolor=(fontColor):x=((x)+100):y=((y)-(text_h/2))"
                                    filterComplex += textFilter
                                } else {
                                    let textFilter = "[v(index)]drawtext=textual content="(breakedText)":fontfile=(fontPath):fontsize=(fontSizeForHeight):fontcolor=(fontColor):x=((x)+100):y=((y)-(text_h/2))[video(index + 1)];"
                                    filterComplex += textFilter
                                }
                                
                            } else {
                                
                                let textBack = textData.backColor != nil ? ":field=1:boxcolor=(backColor ?? "")@0.8:boxborderw=25" : ""
                                
                                if index == currentPhotoTextDataArray.rely - 1 {
                                    let textFilter = "[video(index)]drawtext=textual content="(breakedText)":fontfile=(fontPath):fontsize=(fontSizeForHeight):fontcolor=(fontColor):x=(x):y=(y)(textBack)"
                                    filterComplex += textFilter
                                } else {
                                    let textFilter = "[video(index)]drawtext=textual content="(breakedText)":fontfile=(fontPath):fontsize=(fontSizeForHeight):fontcolor=(fontColor):x=(x):y=(y)(textBack)[video(index + 1)];"
                                    filterComplex += textFilter
                                }
                            }
                            
                        }
                        
                        if let audioData = self.audioDataArray.first(the place: { $0.photoIndex == mainIndex }) {
                            
                            let audioSTime = self.getSTimeAudio(index: mainIndex, secondsPhoto: Int(audioData.audioStartTime))
                            let audioETime = self.getETimeAudio(index: mainIndex, secondsPhoto: Int(audioData.audioEndTime))
                            let period = audioData.audioEndTime - audioData.audioStartTime
                            
                            command = "-loop 1 (inputs) -ss (audioSTime) -to (audioETime) -i "(audioData.audioURL.path)" -filter_complex "[0]scale=1080:trunc(ow/a/2)*2[video0];(filterComplex)[final_video]" -map "[final_video]":v -map (audioIndex):a -c:v libx264 -t (period) -pix_fmt yuv420p -y (outputURL.path)"
                            
                        } else {
                            command = "-loop 1 (inputs) -filter_complex "[0]scale=1080:trunc(ow/a/2)*2[video0];(filterComplex)" -c:v libx264 -t 5 -pix_fmt yuv420p -y (outputURL.path)"
                        }
                    }

I’m not getting actual place of textual content in generated video as added by person. if anybody is aware of please assist me with this.