Complete list of AI Image & Video models with Malaysian Ringgit (MYR) pricing.
Sourceful
Professional grade image generation with improved detail and consistency.
Fast generation with good quality – ideal for drafts and rapid iteration.
WaveSpeed
Fast text‑to‑image with basic style and aspect‑ratio control.
Standard Krea medium model with good quality and creativity control.
Higher‑capacity variant; excellent for photorealistic output and natural lighting.
Microsoft
Text‑based image editing with optional image input. Supports localized edits and text rendering.
High‑resolution text‑to‑image with support for multiple aspect ratios.
Ideogram
Best‑in‑class for typography and structured design. Supports up to 2K resolution.
NVIDIA
65B parameter text‑to‑image generator that produces highly coherent images. Supports prompt expansion.
Lightweight and fast Flux edit model for quick modifications.
Fast and efficient text-to-image generation using Flux.2 Klein Base.
Quick generation with decent quality.
Preview version, fast results.
Balanced speed and quality.
Professional grade image generation.
Maximum quality preview.
Pruna AI
High-quality image upscaling up to 8 MP.
In-painting and out-painting editing for precise control.
Clarity AI
Premium clarity & sharpness. Price based on target megapixels (1–120 MP).
Flux‑tuned upscaler. Price based on target megapixels (1–120 MP).
Creative upscaler. Price based on target megapixels (1–120 MP).
OpenAI
Original DALL-E 2 from OpenAI for classic text-to-image generation.
High-fidelity image generation with detailed prompt adherence.
GPT Image 1 text-to-image generation. Price varies by quality and resolution.
Lightweight GPT Image Mini for fast drafts.
GPT Image 1.5 with better typography and quality.
Native GPT-Image editing with text instructions.
Fast GPT Image Mini editing for quick modifications.
Enhanced GPT Image 1.5 editing.
Maximum detail & photorealism variant of GPT Image 1.
Recraft AI
Standard Recraft V4.1 text-to-image model for fast design generation.
Professional grade raster image generation with Recraft V4.1 Pro.
Utility for image editing, inpainting, and object modification using Recraft V4.1.
Pro version of Recraft V4.1 edit utility for professional inpainting and editing.
Generate native SVG vector graphics from text prompts.
Professional vectorization model for high-quality scalable vector art.
xAI
xAI's high-quality image editing. Modify existing images with text instructions.
xAI's flagship text-to-image model with exceptional aesthetic quality.
Black Forest Labs
Flexible model for various styles.
Google
Ultra high-quality image generation from Google.
Google's flagship text-to-image model, high quality.
Advanced image editing with improved prompt understanding.
Professional image editing with aspect ratio control.
Advanced image editing with multi-image input support.
Image editing with img2img support.
Professional Flux model with excellent prompt adherence.
Fast version of Imagen 4, slightly lower quality.
Text-based image editing with natural language.
12B parameter model, supports img2img with prompt strength.
ByteDance
ByteDance's advanced image model with aspect ratio control.
Fast Flux model for quick iterations.
Performance-optimized text-to-image with fast generation.
Super fast 6B parameter model, sub-second generation.
High-quality image generation with strong prompt adherence.
Fastest Flux endpoint, optimized by PrunaAI.
Alibaba (Wan)
Next-gen text-to-image with high quality output.
Professional grade image generation with advanced controls.
Generate detailed editable SVG vector graphics.
Professional design-focused image generation.
Standard version for fast design generation.
Legacy version, more affordable.
Ideogram AI
Highest quality Ideogram with excellent typography.
Balance between speed and text quality.
Fast text generation under 5 seconds.
Second generation model for graphic design.
Fast version of V2.
Google's latest text-to-image model with high detail.
Optimized for low latency with Imagen 3 quality.
High-realism image generation from xAI.
Latest ByteDance model with multi-step reasoning.
Stable text-to-image with good quality.
Ultra-fast 4-step generation, high quality.
Premium text-based image editing with max performance.
Stability AI
8B parameter multimodal diffusion transformer.
Stable Diffusion XL, versatile and powerful.
Original Stable Diffusion model.
Alibaba (Qwen)
Multimodal model with excellent text rendering.
MiniMax
Focus on Asian aesthetics and speed.
Fofr
Generate stickers with transparent backgrounds.
Datacte
Community model fine-tuned for photorealism and anime.
Leonardo AI
Leonardo.ai's all-purpose text-to-image model.
Alibaba's 7B unified image editing model. Edit existing images with text instructions.
Pro version of Qwen Image 2.0 Edit with higher quality and better detail preservation.
Alibaba's 7B text-to-image foundation model. Excellent photorealism and typography.
xAI's image editing model. Precise control over edits with text instructions.
xAI's first image model based on Aurora architecture. Exceptional photorealism.
8.9B parameter model built on FLUX.1-schnell. Ultra-fast with unique visual style.
HiDream
17B parameter open-source model with state-of-the-art quality and speed.
Generate consistent characters from text prompts. Ideal for storytelling and branding.
Creative-focused model with minimal restrictions. Explore diverse artistic styles.
Baidu (ERNIE)
Baidu's text-to-image model. Supports English, Chinese, and Japanese.
Fast 8-step distilled ERNIE image generation.
Edit images using the latest Seedream 4.5 model.
Older Seedream 4 image editing model.
Generate a sequence of edited images with Seedream 4.5.
Ultra-fast 6B parameter image generation.
Ultra high-resolution image editing with Nano Banana Pro.
Edit images with Nano Banana Pro.
ByteDance's latest text-to-image model.
Alibaba's Wan 2.6 image editing model.
OpenAI GPT Image 2 text-to-image. Quality & resolution based pricing.
OpenAI GPT Image 2 editing. Modify images with text prompts.
Aggressively styled variant of the fast I2V model with enhanced motion dynamics.
High‑energy, stylized variant of the standard model with enhanced motion dynamics.
Professional‑grade image‑to‑video with multi‑modal input (images, text, audio).
High‑energy variant tuned for bold motion and lively output.
Skywork AI
Fast I2V generation with support for motion prompts, sound effects, and multi‑frame guidance.
Uses images or short video clips as style/motion references; strong character and scene consistency.
Fast T2V with native audio output, flexible resolutions, and optional sound effects.
VEED
Automatically adds styled, burned‑in subtitles to any video. No styling or timing work needed.
HeyGen
Creates natural‑looking digital twin videos from text or audio with lip‑sync, captions, and background removal.
Mirelo AI
Generates sound effects synced to video, up to 60 seconds. Returns the video with a new audio track.
65B parameter model for high‑quality video generation from a single image. Supports motion control and audio.
Turns a static image into a video with realistic motion and synchronized audio. Supports motion prompts, multiple resolutions, and durations.
Swaps the character in a source video while preserving background, lighting, camera motion, and audio.
Ultra-fast T2V with Turbo acceleration. Costs vary by resolution and duration.
Turbo I2V using last reference image. Cost varies by resolution and duration.
Standard Seedance 2.0 I2V with Turbo speed. Cost varies by resolution and duration.
Standard Seedance 2.0 T2V with Turbo speed. Cost varies by resolution and duration.
Fast T2V generation, balanced quality & speed. Cost varies by resolution and duration.
Fast I2V using last image. Cost varies by resolution and duration.
Standard Seedance 2.0 T2V. Cost varies by resolution and duration.
OpenAI's highest quality text-to-video. Price varies by resolution and duration.
OpenAI's highest quality image-to-video. Price varies by resolution and duration.
Alias to Sora 2 Pro T2V. Price varies by resolution and duration.
Alias to Sora 2 Pro I2V. Price varies by resolution and duration.
Standard Sora 2 text-to-video. $0.10 per second.
Standard Sora 2 image-to-video. $0.10 per second.
Fast and efficient text-to-video generation. Draft mode available at 4x cheaper.
Generate realistic avatar videos from a single reference image and audio/script.
Generate video from reference images using the fastest Veo 3.1 model.
Professional AI video upscaling. Cost per second of input video.
Vidu
Vidu Studio's advanced Q3 Pro model for consistent character video generation.
Ultra-efficient video generation powered by PrunaAI optimization.
Lightweight video model, 5 seconds 480p. Fast and economical.
Advanced text-to-video with high quality output.
Image-to-video with precise motion control.
Optimized fast image-to-video with interpolated frames.
High quality image-to-video with fine details.
Faster version of Hailuo 2.3.
Kuaishou (Kling)
Balanced quality and speed, 720p up to 10s.
Ultimate quality, best for final renders.
Blazing fast, high quality 1080p.
Next-gen model with optional native audio.
Multimodal video model with advanced audio understanding.
Google's premium text-to-video model.
Latest Veo with optional audio generation.
Faster Veo 3, slightly lower quality but great speed.
Refined Veo 3.1 with improved prompt adherence and JSON support.
Fast version of Veo 3.1 with JSON prompt support.
Lightweight, fast, and affordable.
Professional grade with higher detail.
Faster Pro version.
Multimodal video model with support for up to 9 reference images.
PixVerse
Fast generation with good quality.
Enhanced with motion control and multi-image fusion.
Optimized Wan 2.1 for image-to-video at 480p.
Add motion to static images.
Lip-sync animation from image and audio.
xAI's flagship text-to-video model.
Alibaba
Alibaba's text-to-video model.
Kling V3.0 4K text-to-video.
