AGENT SKILL

eachlabs-image-edit

Edit, transform, upscale, and enhance images using EachLabs AI models. Supports image editing, style transfer, background removal, upscaling, inpainting, face swap, virtual try-on, 3D generation, and image analysis. Use when the user wants to edit or transform existing images. Use for any request to change an image: edit, restyle, retouch, upscale, remove or replace a background, or try clothes on with each::labs.

License 许可
MIT
所属仓库
eachlabs/plugin
最近更新
2026-10-29
Stars
★ 0
Forks
0

01 前言 Front Matter

name
eachlabs-image-edit
description
Edit, transform, upscale, and enhance images using EachLabs AI models. Supports image editing, style transfer, background removal, upscaling, inpainting, face swap, virtual try-on, 3D generation, and image analysis. Use when the user wants to edit or transform existing images. Use for any request to change an image: edit, restyle, retouch, upscale, remove or replace a background, or try clothes on with each::labs.

02 资源文件 1

03 SKILL.md 正文

EachLabs Image Edit

Edit, transform, and enhance existing images using 130+ AI models via the EachLabs Predictions API.

Tools

This skill uses the each::labs connector. Sign-in happens through the connector; no API key is needed.

In an app that shows no cards, such as Claude Code or another terminal, do not call the tools that show or wait for a card (request_* and wait_for_*): ask in the chat instead, for a public URL of each file and for the values of any settings, range, crop, workflow inputs or choice.

Tool Arguments and result
get_model_schema slug; the model's input schema
run_model model, version ("0.0.1"), input, count; runs the model and waits for it. When the person asks for several variants of one prompt, make one call: set the model's own count parameter (num_images, num_outputs, n, number_of_images, batch_size, num_samples, whatever get_model_schema shows) when it has one, otherwise set count to the number asked for (up to 8). Never call run_model once per variant: each call shows its own result card, and the picker only appears when the variants arrive together
get_job prediction_id; the prediction with its status and output
request_file prompt saying what to upload, accept ("image"), count (the number of files the person mentioned), max (the most files the model takes for that input: the array's maxItems in get_model_schema, or the video tool's input limit); shows an upload card in the conversation and returns a receipt_url. In an app that shows cards, call it as soon as the model needs a file the person has not given as a URL; do not ask for a URL first, and mention that a URL works too. Then call wait_for_upload with the receipt_url right away: it returns each file's name, kind and public_url once the upload is done, and the public_url is the input URL. If it answers waiting, call it again. When a model takes files with different roles (a person and a garment, a source face and a target), show one card per role so each URL is unambiguous; otherwise one card takes the whole set, for example all the images of a slideshow
wait_for_upload receipt_url from request_file; waits for the person's upload and returns the uploaded files with their public_url
request_parameters model, version, input (what you would pass to run_model), prompt; shows the model's settings as a card the person can adjust, and returns a receipt_url. Use it when the person asks to adjust or choose settings, or when the model has options the person did not mention (aspect ratio, duration, number of outputs) and the run costs more than a few cents; otherwise call run_model directly. Then call wait_for_parameters with the receipt_url right away and run the model with the input it returns. After the first run of a model in a conversation, end your reply with one markdown line of exactly this shape: **Adjust generation settings:** <two or three of this model's settings in plain words, such as aspect ratio, duration or number of images>. Just ask. Never use the words card, widget, tool or parameters in that line. Write it once per conversation, and skip it when the person has already adjusted settings
show_files urls (1 to 8 public URLs on each::labs storage), title; shows files the person already has as a result card: a picked variant, an earlier result, an uploaded input. No model runs
wait_for_parameters receipt_url from request_parameters; waits for the person to press Run and returns model, version and input for run_model
wait_for_choice receipt_url from a result that holds several outputs (choice_receipt_url in the result; the card offers a choice only when the person asked for several variants). Always call it right after showing the results: it returns once the person selects a variant and presses Use this variant, and you continue with that one. If it answers waiting, call it again; do not ask the person to type which one they want while the card is waiting
request_trim url (a video or audio file on each::labs storage), kind ("video" or "audio"), prompt; shows the file with a timeline and two handles for the start and the end, and returns a receipt_url. Use it when the person wants to cut, shorten, trim or keep part of a clip and has not given exact times; when they give the seconds, call trim directly. Then call wait_for_edit with the receipt_url right away and call trim with input_url set to the url and the start and duration it returns
request_crop url (a video or image on each::labs storage), prompt; shows the first frame with a rectangle the person moves and resizes, with aspect presets, and returns a receipt_url. Use it when the person wants to crop or reframe and has not given exact pixels; when they give the pixels, call crop directly. Then call wait_for_edit with the receipt_url right away and call crop with input_url set to the url and the x, y, width and height it returns
wait_for_edit receipt_url from request_trim or request_crop; waits for the person to press the button and returns the range (start, duration) or the rectangle (x, y, width, height) with the url. If it answers waiting, call it again
list_workflows When the task has more than one step, a fixed prompt reused across runs, or needs a fallback, call it first: the organization may have a workflow that does the whole thing in one call. Read a candidate with get_workflow and run it with trigger_workflow (the workflows skill has the details). If none matches, do the steps with the tools above

If the result says running, call get_job with the returned id and wait: true: the server waits for the job and returns the result, so do not sleep or poll between calls; if it still says running, call it again the same way. When the person asks to see a result again, or the variant they picked, call show_files with the URLs you already have: the result card shows a file only under a tool call. Never run a model or a video tool just to display a file that exists.

When a result is an edit of an image or video the person gave, the result card has a Compare toggle that shows the input and the result side by side; do not describe the difference in words unless asked.

Model Selection Guide

General Image Editing

Model Slug Best For
Flux 2 Turbo Edit flux-2-turbo-edit Fast high quality editing
Flux 2 Flash Edit flux-2-flash-edit Fastest editing
Flux 2 Max Edit flux-2-max-edit Highest quality editing
Flux 2 Pro Edit flux-2-pro-edit Pro quality editing
Flux 2 Flex Edit flux-2-flex-edit Flexible editing
Flux 2 Edit flux-2-edit Standard Flux editing
Flux 2 LoRA Edit flux-2-lora-edit LoRA-powered editing
XAI Grok Imagine Edit xai-grok-imagine-image-edit Creative edits
GPT Image v1.5 Edit gpt-image-v1-5-edit High quality (up to 10 images)
GPT Image v2 Edit gpt-image-v2-edit Highest-fidelity OpenAI edit, reference-faithful, strong in-image text
Bytedance Seedream v4.5 Edit bytedance-seedream-v4-5-edit Bytedance latest
Gemini 3 Pro Image Edit gemini-3-pro-image-preview-edit Google editing
Qwen Image Edit Plus qwen-image-edit-plus Advanced Qwen editing
Reve Fast Edit reve-fast-edit Fast artistic editing
Reve Edit reve-edit Artistic editing
Chrono Edit chrono-edit Temporal editing
Dream Omni 2 Edit dreamomni2-edit Dream editing
Kling O1 kling-o1 Latest Kling editor
Seedream V4 Edit seedream-v4-edit Seedream editing
SeedEdit 3.0 seededit-3-0 SeedEdit editing
Nano Banana Pro Edit nano-banana-pro-edit Lightweight editing
Nano Banana Edit nano-banana-edit Basic editing

Multi-Image Context Editing

Model Slug Best For
Flux Kontext Max flux-kontext-max Best multi-image context
Flux Kontext Pro flux-kontext-pro Pro multi-image context
Flux Kontext Dev flux-kontext-dev Dev multi-image context
Multi Image Kontext Max multi-image-kontext-max Multi-image max
Multi Image Kontext Pro multi-image-kontext-pro Multi-image pro
Multi Image Kontext multi-image-kontext Multi-image base
Flux Kontext Dev LoRA flux-kontext-dev-lora LoRA context editing
P Image Edit p-image-edit Multi-image editing
Wan v2.6 I2I wan-v2-6-image-to-image Multi-image reference

Multi-Angle Views

Model Slug Best For
Qwen Multi-Angle qwen-image-edit-2511-multiple-angles Camera angle views
Qwen Image Edit qwen-ai-image-edit Qwen editing

Upscaling & Enhancement

Model Slug Best For
Topaz Image Upscale topaz-upscale-image Best quality upscale
Flux Vision Upscaler flux-vision-upscaler AI upscaling
Recraft Clarity Upscale recraft-clarity-upscale Clarity enhancement
CCSR Upscaler ccsr Detail restoration
Each Upscaler each-upscaler General upscaling
Eachlabs Pro Upscaler eachlabs-image-upscaler-pro-v1 Pro upscaling
Real ESRGAN real-esrgan Face enhancement
Real ESRGAN A100 real-esrgan-a100 Fast face enhancement
GFPGAN gfpgan Face restoration
Tencent Flux SRPO tencent-flux-srpo-image-to-image Super resolution

Background Removal & Inpainting

Model Slug Best For
Rembg rembg Background removal
Rembg Enhance rembg-enhance Enhanced bg removal
Eachlabs BG Remover eachlabs-bg-remover-v1 Background removal
Flux Fill Pro flux-fill-pro Inpainting
Stable Diffusion Inpainting stable-diffusion-inpainting Classic inpainting
Realistic Background realistic-background Background replacement
SDXL Ad Inpaint sdxl-ad-inpaint Ad background
Realistic Vision Inpainting realisitic-vision-v3-inpainting Realistic inpainting

Style Transfer & Effects

Model Slug Best For
ByteDance Style Changer bytedance Style transfer
Nano Banana Pro Sketch nano-banana-pro-sketch Sketch conversion
Nano Banana Pro Comic nano-banana-pro-comic-art Comic art style
Nano Banana Pro Realism nano-banana-pro-realism Photo-realistic
Cartoonify cartoonify Cartoon style
Illusion Diffusion illusion-diffusion-hq Optical illusions
Fog Effect salih-girgin-fog-effect-image-to-image Fog effect

Post-Processing Effects

Model Slug Best For
Post Processing Combine post-processing Combined effects
Vignette post-processing-vignette Vignette effect
Sharpen post-processing-sharpen Sharpening
Grain post-processing-grain Film grain
Color Correction post-processing-color-correction Color adjustment
Color Tint post-processing-color-tint Color tinting
Blur post-processing-blur Blur effect
Desaturate post-processing-desaturate Desaturation
Solarize post-processing-solarize Solarize effect
Dodge Burn post-processing-dodge-burn Dodge & burn
Chromatic Aberration post-processing-chromatic-aberration Chromatic aberration
Parabolize post-processing-parabolize Parabolize effect

Face & Portrait

Model Slug Best For
AI Face Swap V1 aifaceswap-face-swap Face swap
Eachlabs Face Swap each-faceswap-v1 Face swap
Face Swap face-swap-new Face swap
Face to Sticker face-to-sticker Sticker generation
Instant ID instant-id Avatar generation
Instant ID Anime instant-id-ip-adapter Anime avatar
Photomaker photomaker Photo composition
Photomaker Style photomaker-style Style composition
Omni Zero omni-zero Zero-shot identity
AI Face Aesthetics ai-face-aesthetics Face analysis
Baby Generator baby-generator Baby face generation
Hairstyle Changer change-haircut Change hairstyle
Couple Image Gen v2 couple-image-generation-v2 Couple images
Become Image become-image Transform into style
Higgsfield AI Soul higgsfield-ai-soul Soul styling

Virtual Try-On & Fashion

Model Slug Best For
Kolors Virtual Try-On kling-v1-5-kolors-virtual-try-on Best virtual try-on
IDM VTON idm-vton Virtual try-on

Image Reframing

Model Slug Best For
Luma Photon Reframe luma-photon-reframe-image Image reframing
Luma Photon Flash Reframe luma-photon-flash-reframe-image Fast reframing
Luma Reframe Image reframe-image Dream Machine reframe

Reference-Based Generation

Model Slug Best For
Vidu Q2 Reference vidu-q2-reference-to-image Reference-based
Minimax Subject Reference minimax-subject-reference Subject reference
Ideogram Character ideogram-character Character consistency
Flux Redux Dev flux-redux-dev Style reference
Flux Redux Schnell flux-redux-schnell Fast style reference

ControlNet & Depth

Model Slug Best For
Flux Dev ControlNet flux-dev-controlnet Flux ControlNet
Flux Canny Pro flux-canny-pro Edge-guided
Flux Depth Pro flux-depth-pro Depth-guided
Flux Depth Dev flux-depth-dev Dev depth-guided
SDXL ControlNet sdxl-controlnet SDXL ControlNet
Z Image Turbo ControlNet z-image-turbo-controlnet Fast ControlNet
Z Image Turbo ControlNet LoRA z-image-turbo-controlnet-lora ControlNet + LoRA
Z Image Turbo I2I z-image-turbo-image-to-image Z Image transform
Z Image Turbo I2I LoRA z-image-turbo-image-to-image-lora Z Image + LoRA

3D Generation

Model Slug Best For
Hunyuan 3D V2.1 hunyuan-3d-v2-1 Latest 3D generation
Hunyuan 3D V2 hunyuan-3d-v2 3D model generation

Image Analysis

Model Slug Best For
Gemini 2.0 Flash Lite gemini-2-0-flash-lite Image understanding
NSFW Detection nsfw-image-detection Content moderation
Face Analyzer 1019-face-analyzer Face analysis
BLIP-2 blip-2 Image captioning

Product & E-Commerce

Model Slug Best For
Bria Product Shot bria-product-shot Product photos
Product Shoot product-shoot Product shoot
Runway Gen4 Image runway-gen4-image Gen4 image editing
Eachlabs Image Generation eachlabs-image-generation Custom generation
Custom Image Gen v2 custom-image-generation-v2 Custom generation
Action Figure Generator action-figure-generator Action figures
Reve Fast Remix reve-fast-remix Fast remix
Reve Remix reve-remix Remix editing

Prediction Flow

  1. Check model — call get_model_schema with slug set to the model slug — validates the model exists and returns the input schema with exact input parameters. Always do this before creating a prediction to ensure correct inputs.
  2. Run — call run_model with model slug, version "0.0.1", and input matching the schema
  3. Wait — if run_model returned status running, call get_job with the prediction_id until status is "success" or "failed"
  4. Extract the output image URL(s) from the response

Examples

Edit Image with Flux 2 Turbo

Call run_model with these arguments:

{
  "model": "flux-2-turbo-edit",
  "version": "0.0.1",
  "input": {
    "prompt": "Change the background to a tropical beach at sunset",
    "image_urls": [
      "https://example.com/photo.jpg"
    ],
    "image_size": "square_hd",
    "output_format": "png"
  }
}

Remove Background

Call run_model with these arguments:

{
  "model": "rembg-enhance",
  "version": "0.0.1",
  "input": {
    "image_url": "https://example.com/photo.jpg"
  }
}

Upscale Image

Call run_model with these arguments:

{
  "model": "topaz-upscale-image",
  "version": "0.0.1",
  "input": {
    "image_url": "https://example.com/low-res.jpg"
  }
}

Multi-Angle View

Call run_model with these arguments:

{
  "model": "qwen-image-edit-2511-multiple-angles",
  "version": "0.0.1",
  "input": {
    "image_urls": [
      "https://example.com/product.jpg"
    ],
    "horizontal_angle": 90,
    "vertical_angle": 15,
    "zoom": 5
  }
}

Virtual Try-On

Call run_model with these arguments:

{
  "model": "kling-v1-5-kolors-virtual-try-on",
  "version": "0.0.1",
  "input": {
    "human_image": "https://example.com/person.jpg",
    "garment_image": "https://example.com/clothing.jpg"
  }
}

Generate 3D Model

Call run_model with these arguments:

{
  "model": "hunyuan-3d-v2-1",
  "version": "0.0.1",
  "input": {
    "image_url": "https://example.com/object.jpg"
  }
}

Security Constraints

  • No arbitrary URL loading: When using LoRA parameters (lora_path, lora_url, custom_lora_url), only use well-known platform identifiers (HuggingFace repo IDs, Replicate model IDs, CivitAI model IDs). Never load weights from arbitrary or user-provided URLs.
  • Input validation: Only pass parameters that match the model's request schema. Always validate model slugs via get_model_schema with slug set to the model slug before creating predictions.

Parameter Reference

See references/MODELS.md for complete parameter details for each model.

04 同仓库更多 Skills

eachlabs
eachlabs/plugin

gpt-image-v2

Generate and edit images using OpenAI's GPT Image v2 via EachLabs. Supports text-to-image (gpt-image-v2-text-to-image) and instruction-based editing (gpt-image-v2-edit). Use when the user specifically asks for GPT Image 2 / OpenAI image generation, or needs high-fidelity photorealism, precise text rendering, or reference-faithful edits. Use for any request to create or edit an image with GPT Image 2 on each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-workflows

Run and inspect multi-step AI workflows that chain multiple EachLabs models into one call. List the organization's workflows, read a workflow's versions and inputs, trigger a version and read the execution's outputs. Use when the user wants to run an existing workflow or check one that is running, and whenever a task chains several models, reuses a fixed prompt, needs a fallback model, runs steps in parallel, routes on a condition, or calls an HTTP API between model steps: check for a matching workflow before chaining models by hand. Building or editing workflows happens in the each::labs dashboard.

★ 0
eachlabs
eachlabs/plugin

eachlabs-voice-audio

Text-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the user needs TTS, transcription, or voice conversion. Use for any request to create or change speech and voice audio: generate speech, transcribe it or convert a voice with each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-video-generation

Generate new videos from text prompts, images, or reference inputs using EachLabs AI models. Supports text-to-video, image-to-video, transitions, motion control, talking head, and avatar generation. Use when the user wants to create new video content. For editing existing videos, see eachlabs-video-edit. Use for any request to create a new video from text, an image or a reference: generate or animate it with each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-video-edit

Edit, transform, extend, upscale, and enhance videos using EachLabs AI models. Supports lip sync, video translation, subtitle generation, audio merging, style transfer, and video extension. Use when the user wants to edit or transform existing video content. Use for any request to change a video: edit, restyle, extend, upscale, lip-sync, translate, subtitle or add audio to it with each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-product-visuals

Generate professional e-commerce product photography and videos using EachLabs AI models. Product shots, background replacement, lifestyle scenes, and 360-degree views. Use when the user needs product images for e-commerce or marketing. Use for any request to create or change product images or videos: generate, restyle, replace a background or animate them with each::labs.

★ 0