# AI Image Editing API

> Edit images with natural-language instructions using Flux Kontext, GPT-Image, Reve, Seededit, Qwen Edit and more — single MuApi.ai endpoint.

## Overview

Send an image and an instruction ("change the background to a beach", "swap the jacket for a leather one", "remove the man on the left") and get an edited image back. Flux Kontext Pro/Max are the new standard for instruction-following edits; GPT-Image handles compositional rewrites; Seededit and Qwen Edit are cost-efficient alternatives. All exposed through the same JSON API.

- Natural-language image edits — no masks needed
- Models: Flux Kontext Dev/Pro/Max, GPT-Image Edit, Reve, Seededit, Qwen Edit, Midjourney i2i
- Mask-based inpainting also supported on select models
- Style transfer, object insertion, background swap, and outpainting all in one category

## API Pattern

Every model in this category uses the same submit-then-poll API:

```http
POST https://api.muapi.ai/api/v1/{model}
x-api-key: YOUR_API_KEY
Content-Type: application/json
```

Response: `{ "request_id": "abc123", "status": "processing" }`. Poll `GET https://api.muapi.ai/api/v1/predictions/{request_id}/result` until `status` is `completed` — the result URLs are in the `outputs[]` array. Optionally pass `?webhook=https://your-server` on the submit call to receive a callback instead of polling.

Get an API key at https://muapi.ai/access-keys.

## Quick Start

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/flux-kontext-pro-i2i \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"change the sky to a sunset"}' | jq -r .request_id)

# 2. Poll
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

## Models in This Category

- [bytedance-seedream-v4.5-edit](https://muapi.ai/playground/bytedance-seedream-v4.5-edit): Seedream-v4.5 Edit allows you to transform an existing image using natural-language instructions. It preserves the core composition, lighting, and style of the…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v4.5-edit`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v4.5-edit/llms.txt
  - Cost: 0.050 credits per call
- [nano-banana-2-edit](https://muapi.ai/playground/nano-banana-2-edit): Nano Banana 2 (Gemini 3.1 Flash Image) is Google's most advanced image generation model, combining speed with high-fidelity 4K output and revolutionary charact…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana-2-edit`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana-2-edit/llms.txt
  - Cost: 0.060 credits per call
- [nano-banana-edit](https://muapi.ai/playground/nano-banana-edit): Nano Banana is a mysterious, high-performance image model. It excels at precise, language-driven edits and consistent character preservation, allowing users to…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana-edit`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana-edit/llms.txt
  - Cost: 0.030 credits per call
- [nano-banana-pro-edit](https://muapi.ai/playground/nano-banana-pro-edit): Nano Banana 2 Edit is the next-generation image editing model developed by Google DeepMind, following the original Nano Banana (also known as Gemini 2.5 Flash…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana-pro-edit`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana-pro-edit/llms.txt
  - Cost: 0.120 credits per call
- [bytedance-seedream-v4-edit](https://muapi.ai/playground/bytedance-seedream-v4-edit): Seedream v4 Edit refines or transforms existing images based on a new prompt and a reference. Instead of masking, you provide a source image and describe how i…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v4-edit`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v4-edit/llms.txt
  - Cost: 0.040 credits per call
- [gpt-image-2-image-to-image](https://muapi.ai/playground/gpt-image-2-image-to-image): Transform and edit existing images using GPT Image 2 with text instructions. Supports up to 16 input images for precise style transfer, editing, and image tran…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-image-2-image-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-image-2-image-to-image/llms.txt
  - Cost: 0.090 credits per call
- [wan2.5-image-edit](https://muapi.ai/playground/wan2.5-image-edit): The Wan2.5 Edit Image model allows you to transform existing images with precision and creativity. By providing an image along with an edit prompt, you can mak…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.5-image-edit`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.5-image-edit/llms.txt
  - Cost: 0.040 credits per call
- [ai-image-face-swap](https://muapi.ai/playground/ai-image-face-swap): Advanced facial recognition and blending algorithms enable precise face swaps while preserving skin tone, lighting, and facial geometry.
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-image-face-swap`
  - Per-model llms.txt: https://muapi.ai/playground/ai-image-face-swap/llms.txt
  - Cost: 0.020 credits per call
- [bytedance-seedream-v5.0-edit](https://muapi.ai/playground/bytedance-seedream-v5.0-edit): Seedream 5.0 Lite Edit is an advanced image transformation model by ByteDance, enabling precise, controllable edits using natural language. It specializes in h…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v5.0-edit`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v5.0-edit/llms.txt
  - Cost: 0.033 credits per call
- [ai-background-remover](https://muapi.ai/playground/ai-background-remover): Instantly remove image backgrounds with pixel-perfect precision. Ideal for product photos, profile pictures, and creative projects.
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-background-remover`
  - Per-model llms.txt: https://muapi.ai/playground/ai-background-remover/llms.txt
  - Cost: 0.010 credits per call
- [kling-o1-edit-image](https://muapi.ai/playground/kling-o1-edit-image): Kling O1 Image Edit applies targeted transformations to an existing image while preserving composition, lighting, and visual consistency. Use it to replace obj…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-o1-edit-image`
  - Per-model llms.txt: https://muapi.ai/playground/kling-o1-edit-image/llms.txt
  - Cost: 0.036 credits per call
- [wan2.6-image-edit](https://muapi.ai/playground/wan2.6-image-edit): WAN 2.6 Image Edit applies targeted, instruction-based edits to an existing image while preserving composition, perspective, and lighting. It’s ideal for objec…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.6-image-edit`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.6-image-edit/llms.txt
  - Cost: 0.045 credits per call
- [bytedance-seededit-v3](https://muapi.ai/playground/bytedance-seededit-v3): Seededit allows precise edits to images using masks and prompt guidance. Whether you're replacing backgrounds, changing clothing, or inpainting missing areas,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seededit-v3`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seededit-v3/llms.txt
  - Cost: 0.030 credits per call
- [wan2.7-image-edit-pro](https://muapi.ai/playground/wan2.7-image-edit-pro): Alibaba WAN 2.7 Image Edit Pro performs prompt-driven image editing with multi-image reference support and up to 2K output.
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.7-image-edit-pro`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.7-image-edit-pro/llms.txt
  - Cost: 0.100 credits per call
- [qwen-image-2.0-pro-edit](https://muapi.ai/playground/qwen-image-2.0-pro-edit): Qwen 2.0 Pro Image Edit model with maximum precision and modifications.
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-2.0-pro-edit`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-2.0-pro-edit/llms.txt
  - Cost: 0.090 credits per call
- [qwen-image-edit-plus](https://muapi.ai/playground/qwen-image-edit-plus): Qwen Image Edit Plus is an upgraded image-editing model that supports multiple image references and superior text editing. Powered by the 20B-parameter Qwen ar…
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-edit-plus`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-edit-plus/llms.txt
  - Cost: 0.030 credits per call
- [ai-image-upscaler](https://muapi.ai/playground/ai-image-upscaler): Transform blurry or pixelated images into high-definition visuals. Our AI Image Upscaler uses deep learning to reconstruct details and bring your visuals to li…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-image-upscaler`
  - Per-model llms.txt: https://muapi.ai/playground/ai-image-upscaler/llms.txt
  - Cost: 0.020 credits per call
- [grok-imagine-image-to-image](https://muapi.ai/playground/grok-imagine-image-to-image): Grok Imagine Image-to-Image transforms an existing image using natural language instructions while preserving scene structure, perspective, and lighting. It is…
  - Endpoint: `POST https://api.muapi.ai/api/v1/grok-imagine-image-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/grok-imagine-image-to-image/llms.txt
  - Cost: 0.050 credits per call
- [wan2.7-image-edit](https://muapi.ai/playground/wan2.7-image-edit): Alibaba WAN 2.7 Image Edit performs prompt-driven image editing with support for multiple-image references.
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.7-image-edit`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.7-image-edit/llms.txt
  - Cost: 0.050 credits per call
- [sd-2-character](https://muapi.ai/playground/sd-2-character): [Beta] Turn fictional character references into reusable video characters. Upload reference images and describe the outfit to get a character_id you can use in…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sd-2-character`
  - Per-model llms.txt: https://muapi.ai/playground/sd-2-character/llms.txt
  - Cost: 0.180 credits per call
- [qwen-image-edit-2511](https://muapi.ai/playground/qwen-image-edit-2511): Qwen Image Edit 2511 performs precise, instruction-driven edits on an existing image while preserving composition, lighting, and overall style. It’s well-suite…
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-edit-2511`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-edit-2511/llms.txt
  - Cost: 0.040 credits per call
- [flux-kontext-pro-i2i](https://muapi.ai/playground/flux-kontext-pro-i2i): Flux Kontext Pro I2I variant enables transforming base images into refined artwork while keeping structure intact. It’s useful for sketch refinement, visual st…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-pro-i2i`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-pro-i2i/llms.txt
  - Cost: 0.030 credits per call
- [flux-kontext-max-i2i](https://muapi.ai/playground/flux-kontext-max-i2i): Flux Kontext Max I2I in Max mode allows precise image enhancement and visual transformations while retaining the source layout. It’s powerful for retouching, p…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-max-i2i`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-max-i2i/llms.txt
  - Cost: 0.060 credits per call
- [qwen-image-edit-plus-lora](https://muapi.ai/playground/qwen-image-edit-plus-lora): Qwen-Image-Edit-Plus (2509) is 20B MMDiT image-to-image editor supporting multi-image edits, single-image consistency, and native ControlNet. Ready-to-use REST…
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-edit-plus-lora`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-edit-plus-lora/llms.txt
  - Cost: 0.040 credits per call
- [gpt4o-image-to-image](https://muapi.ai/playground/gpt4o-image-to-image): Transform an input image based on a new prompt — like changing style, lighting, or composition. Useful for reinterpreting visuals while keeping structure.
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt4o-image-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/gpt4o-image-to-image/llms.txt
  - Cost: 0.040 credits per call
- [gpt-image-1.5-edit](https://muapi.ai/playground/gpt-image-1.5-edit): GPT-Image-1.5 Edit applies precise, instruction-based modifications to an existing image while preserving composition, lighting, perspective, and visual cohere…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-image-1.5-edit`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-image-1.5-edit/llms.txt
  - Cost: 0.054 credits per call
- [flux-kontext-dev-i2i](https://muapi.ai/playground/flux-kontext-dev-i2i): Takes an input images and transforms it based on a new prompt. Keeps structure or pose while changing style, appearance, or details.
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-dev-i2i`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-dev-i2i/llms.txt
  - Cost: 0.020 credits per call
- [seedvr2-image-upscale](https://muapi.ai/playground/seedvr2-image-upscale): SeedVR2 is a one-step diffusion-transformer model designed for image restoration, super-resolution, deblurring, and artifact removal. It enhances low-quality o…
  - Endpoint: `POST https://api.muapi.ai/api/v1/seedvr2-image-upscale`
  - Per-model llms.txt: https://muapi.ai/playground/seedvr2-image-upscale/llms.txt
  - Cost: 0.020 credits per call
- [flux-2-klein-9b-edit](https://muapi.ai/playground/flux-2-klein-9b-edit): Flux-2-Klein-9B Edit performs higher-quality image edits with better detail retention, lighting consistency, and texture handling compared to smaller variants.…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-9b-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-9b-edit/llms.txt
  - Cost: 0.021 credits per call
- [ideogram-character](https://muapi.ai/playground/ideogram-character): Ideogram’s Character Reference model enables consistent character generation using just one reference image. Upload a clear character portrait—and you can plac…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ideogram-character`
  - Per-model llms.txt: https://muapi.ai/playground/ideogram-character/llms.txt
  - Cost: 0.150 credits per call
- [flux-2-pro-edit](https://muapi.ai/playground/flux-2-pro-edit): Flux-2-Pro Edit enables precise, high-fidelity modifications to an existing image while preserving its lighting, style, mood, and composition. It’s ideal for r…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-pro-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-pro-edit/llms.txt
  - Cost: 0.032 credits per call
- [ai-dress-change](https://muapi.ai/playground/ai-dress-change): Instantly change outfits in images using AI. Visualize different clothing styles without the need for physical trials—perfect for fashion, e-commerce, and virt…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-dress-change`
  - Per-model llms.txt: https://muapi.ai/playground/ai-dress-change/llms.txt
  - Cost: 0.100 credits per call
- [flux-pulid](https://muapi.ai/playground/flux-pulid): Flux PuLID is an innovative image-to-image model that enables consistent face rendering across different styles or scenes—without needing any model fine-tuning…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-pulid`
  - Per-model llms.txt: https://muapi.ai/playground/flux-pulid/llms.txt
  - Cost: 0.040 credits per call
- [flux-2-dev-edit](https://muapi.ai/playground/flux-2-dev-edit): Flux 2 Dev Edit takes an existing image and applies transformations, replacements, or style changes based on a text instruction. It preserves composition, ligh…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-dev-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-dev-edit/llms.txt
  - Cost: 0.031 credits per call
- [flux-2-klein-9b-turbo-edit](https://muapi.ai/playground/flux-2-klein-9b-turbo-edit): Flux-2-Klein-9B Turbo Edit offers high-quality, ultra-fast image editing with superior detail retention. This high-efficiency version of Klein 9B Edit handles…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-9b-turbo-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-9b-turbo-edit/llms.txt
  - Cost: 0.010 credits per call
- [topaz-image-upscale](https://muapi.ai/playground/topaz-image-upscale): Topaz Image Upscale is a high-quality image-to-image enhancement model that increases resolution, sharpness, and detail using AI super-resolution. It improves…
  - Endpoint: `POST https://api.muapi.ai/api/v1/topaz-image-upscale`
  - Per-model llms.txt: https://muapi.ai/playground/topaz-image-upscale/llms.txt
  - Cost: 0.075 credits per call
- [minimax-image-01-subject-reference](https://muapi.ai/playground/minimax-image-01-subject-reference): Minimax’s I2I “Subject Reference” model enables you to transform images while preserving the appearance of a subject using a single reference image. Ideal for…
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-image-01-subject-reference`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-image-01-subject-reference/llms.txt
  - Cost: 0.010 credits per call
- [flux-2-klein-4b-edit](https://muapi.ai/playground/flux-2-klein-4b-edit): Flux-2-Klein-4B Edit applies lightweight, instruction-based edits to an existing image. It’s best for clear object swaps, small visual changes, and cute enhanc…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-4b-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-4b-edit/llms.txt
  - Cost: 0.016 credits per call
- [flux-redux](https://muapi.ai/playground/flux-redux): Flux Redux is a transformation model that reimagines or enhances your input images while preserving their main structure and subject. It’s built for creative r…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-redux`
  - Per-model llms.txt: https://muapi.ai/playground/flux-redux/llms.txt
  - Cost: 0.010 credits per call
- [ai-product-shot](https://muapi.ai/playground/ai-product-shot): Instantly generate studio-quality product images with AI. Upload your item photo and get clean, stylized shots perfect for e-commerce, ads, and catalogs.
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-product-shot`
  - Per-model llms.txt: https://muapi.ai/playground/ai-product-shot/llms.txt
  - Cost: 0.060 credits per call
- [flux-2-flex-edit](https://muapi.ai/playground/flux-2-flex-edit): Flux-2-Flex Edit allows flexible transformation of an existing image: object replacement, material changes, lighting adjustments, style shifts, or localized ed…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-flex-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-flex-edit/llms.txt
  - Cost: 0.090 credits per call
- [ai-skin-enhancer](https://muapi.ai/playground/ai-skin-enhancer): Smooth skin, reduce blemishes, and enhance complexion with natural-looking results. Perfect for portraits, selfies, and professional photo retouching.
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-skin-enhancer`
  - Per-model llms.txt: https://muapi.ai/playground/ai-skin-enhancer/llms.txt
  - Cost: 0.010 credits per call
- [qwen-text-to-image-2512](https://muapi.ai/playground/qwen-text-to-image-2512): Qwen Image Text-to-Image 2512 generates high-resolution, visually consistent images from text prompts. It focuses on strong scene structure, clean composition,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-text-to-image-2512`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-text-to-image-2512/llms.txt
  - Cost: 0.040 credits per call
- [vidu-q2-reference-to-image](https://muapi.ai/playground/vidu-q2-reference-to-image): VIDU Reference-to-Image Q2 generates new high-quality images based on one or more reference images. It preserves the key identity, structure, or style of the r…
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-q2-reference-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-q2-reference-to-image/llms.txt
  - Cost: 0.032 credits per call
- [ai-image-extension](https://muapi.ai/playground/ai-image-extension): Expand the edges of any image with AI. This model continues your original photo or artwork beyond its borders while matching style, lighting, and content.
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-image-extension`
  - Per-model llms.txt: https://muapi.ai/playground/ai-image-extension/llms.txt
  - Cost: 0.030 credits per call
- [ai-product-photography](https://muapi.ai/playground/ai-product-photography): Create professional-grade product photos using AI. Upload your item image and describe it with a prompt, and get studio-style, lifestyle, or creative backgroun…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-product-photography`
  - Per-model llms.txt: https://muapi.ai/playground/ai-product-photography/llms.txt
  - Cost: 0.050 credits per call
- [hf-soul-image-to-image](https://muapi.ai/playground/hf-soul-image-to-image): SOUL is an AI image model focused on hyper-realistic, magazine or editorial-style visuals, especially for fashion, portraits, lifestyle, and commercial content…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hf-soul-image-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/hf-soul-image-to-image/llms.txt
  - Cost: 0.033 credits per call
- [nano-banana-effects](https://muapi.ai/playground/nano-banana-effects): Nano Banana Effects is a creative visual effects model designed to transform ordinary images into fun, stylized, and eye-catching results. It applies artistic…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana-effects`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana-effects/llms.txt
  - Cost: 0.030 credits per call
- [qwen-image-2.0-edit](https://muapi.ai/playground/qwen-image-2.0-edit): Qwen 2.0 Image Edit model with precise background modification and enhancements.
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-2.0-edit`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-2.0-edit/llms.txt
  - Cost: 0.040 credits per call
- [image-effects](https://muapi.ai/playground/image-effects): AI Image Effects applies advanced visual transformations, color grading, and cinematic filters to create stunning images from a image.
  - Endpoint: `POST https://api.muapi.ai/api/v1/image-effects`
  - Per-model llms.txt: https://muapi.ai/playground/image-effects/llms.txt
  - Cost: 0.030 credits per call
- [ai-ghibli-style](https://muapi.ai/playground/ai-ghibli-style): Bring your imagination to life with art inspired by the enchanting world of Studio Ghibli. This AI model generates dreamy, hand-drawn visuals with soft colors,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-ghibli-style`
  - Per-model llms.txt: https://muapi.ai/playground/ai-ghibli-style/llms.txt
  - Cost: 0.050 credits per call
- [flux-2-klein-4b-turbo-edit](https://muapi.ai/playground/flux-2-klein-4b-turbo-edit): Flux-2-Klein-4B Turbo Edit provides ultra-fast, instruction-based image editing. This high-efficiency variant of Klein 4B Edit is optimized for near-instant sw…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-4b-turbo-edit`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-4b-turbo-edit/llms.txt
  - Cost: 0.008 credits per call
- [flux-kontext-effects](https://muapi.ai/playground/flux-kontext-effects): Flux Kontext Effects is a creative image and video model that applies stylized transformations, cinematic filters, and artistic reinterpretations to your input…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-effects`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-effects/llms.txt
  - Cost: 0.040 credits per call
- [reve-image-edit](https://muapi.ai/playground/reve-image-edit): ReVE Edit is a next-generation image editing model that allows users to apply detailed visual transformations through natural language. Whether you want to res…
  - Endpoint: `POST https://api.muapi.ai/api/v1/reve-image-edit`
  - Per-model llms.txt: https://muapi.ai/playground/reve-image-edit/llms.txt
  - Cost: 0.050 credits per call
- [portrait-stylist](https://muapi.ai/playground/portrait-stylist): Professional AI portrait styles including hair, makeup, style, and fashion transformations.
  - Endpoint: `POST https://api.muapi.ai/api/v1/portrait-stylist`
  - Per-model llms.txt: https://muapi.ai/playground/portrait-stylist/llms.txt
  - Cost: 0.010 credits per call
- [ai-color-photo](https://muapi.ai/playground/ai-color-photo): Automatically add lifelike colors to black-and-white images. Our AI brings history to life with natural tones, accurate shading, and context-aware colorization.
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-color-photo`
  - Per-model llms.txt: https://muapi.ai/playground/ai-color-photo/llms.txt
  - Cost: 0.010 credits per call
- [photo-pack](https://muapi.ai/playground/photo-pack): Generate a pack of high-quality, professional portraits in various styles (LinkedIn, CEO, Tinder, etc.) while preserving your facial features.
  - Endpoint: `POST https://api.muapi.ai/api/v1/photo-pack`
  - Per-model llms.txt: https://muapi.ai/playground/photo-pack/llms.txt
  - Cost: 0.300 credits per call
- [ideogram-v3-reframe](https://muapi.ai/playground/ideogram-v3-reframe): Ideogram V3 Reframe is a specialized image-to-image model built on Ideogram 3.0, designed to intelligently extend and adapt images across diverse aspect ratios…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ideogram-v3-reframe`
  - Per-model llms.txt: https://muapi.ai/playground/ideogram-v3-reframe/llms.txt
  - Cost: 0.150 credits per call
- [add-image-watermark](https://muapi.ai/playground/add-image-watermark): Add custom watermark to images with adjustable position, opacity, and size. Free local processing using PIL.
  - Endpoint: `POST https://api.muapi.ai/api/v1/add-image-watermark`
  - Per-model llms.txt: https://muapi.ai/playground/add-image-watermark/llms.txt
- [ai-object-eraser](https://muapi.ai/playground/ai-object-eraser): Easily remove unwanted objects, people, or text from any image using AI. Just select the area you want to erase, and the model will intelligently fill the spac…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-object-eraser`
  - Per-model llms.txt: https://muapi.ai/playground/ai-object-eraser/llms.txt
  - Cost: 0.050 credits per call
- [gpt4o-edit](https://muapi.ai/playground/gpt4o-edit): Edit a specific part of an image using natural language. Ideal for object removal, replacement, or content-aware filling.
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt4o-edit`
  - Per-model llms.txt: https://muapi.ai/playground/gpt4o-edit/llms.txt
  - Cost: 0.040 credits per call
- [qwen-image-edit](https://muapi.ai/playground/qwen-image-edit): The Qwen Edit Image Model allows you to modify existing images using text-based editing prompts. Instead of generating from scratch, you can upload a base imag…
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-edit`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-edit/llms.txt
  - Cost: 0.030 credits per call

## FAQ

**How is this different from text-to-image?**

Image editing models take an existing image plus an instruction and preserve composition where possible. Text-to-image regenerates from scratch. For consistent edits across a series, image-edit models are usually the right tool.

**Do I need to provide a mask?**

No — Flux Kontext, GPT-Image, and Reve all do mask-free instruction edits. Mask-based inpainting is also available if you need pixel-precise control.

**Which model is best for product photography edits?**

Flux Kontext Pro for high-fidelity background swaps and lighting changes; the dedicated `product-shot` endpoint for standardized e-commerce flows.

## Agent Integration

MuApi ships an MCP server so agents (Claude Code, Cursor, custom) can call every model in this category as a tool:

```bash
npm install -g muapi-cli
muapi auth login
muapi mcp serve  # exposes all MuApi models as MCP tools
```

## Resources

- Category page: https://muapi.ai/playground/group/image-edit
- Global llms.txt: https://muapi.ai/llms.txt
- API docs: https://muapi.ai/docs
- OpenAPI spec: https://api.muapi.ai/openapi.json