transform-image

An image-editing command that changes one or more source images according to a written style request, such as turning a photo into a watercolor painting.

In plain words
What is it for?
It is for applying visual styles, changing an image's look, creating an anime or cyberpunk version, or combining several images into one scene.
Why use it?
It avoids having to perform image-to-image editing manually or prepare the upload request yourself. It can also combine up to three images when using the Klein model.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/deapi-ai/claude-code-skills/transform-image
Clone the repo
git clone --depth 1 https://github.com/deapi-ai/claude-code-skills
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00989
Opus 5 $0.00005 $0.00495
Sonnet 5 $0.00002 $0.00198
Haiku 4.5 $0.00001 $0.00099

Measured 2d ago against content hash ec0b09f312bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transform-image scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /tmp/transform_image1.png "{image_url_1}"
deapi/commands/transform-image.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Transformation via deAPI

Transform image: $ARGUMENTS

Step 1: Parse arguments

Extract from $ARGUMENTS:

  • image_url: URL(s) to source image(s) - Klein supports up to 3 images (required)
  • style_prompt: Description of desired transformation (required)
  • --model: klein (default, faster, multi-image) or qwen (higher steps, more control)

Example style prompts:

  • "convert to watercolor painting"
  • "make it look like a vintage photograph"
  • "transform into anime style"
  • "add cyberpunk neon aesthetic"
  • "combine these images into one scene" (multi-image with Klein)

Step 2: Send request

Note: This endpoint requires multipart/form-data with file upload.

If user provides URL(s), first download the image(s):

curl -s -o /tmp/transform_image1.png "{image_url_1}"
curl -s -o /tmp/transform_image2.png "{image_url_2}"  # optional
curl -s -o /tmp/transform_image3.png "{image_url_3}"  # optional

Then send the transformation request:

curl -s -X POST "https://api.deapi.ai/api/v1/client/img2img" \
  -H "Authorization: Bearer $DEAPI_API_KEY" \
  -F "image=@{local_file_path_1}" \
  -F "image=@{local_file_path_2}" \
  -F "image=@{local_file_path_3}" \
  -F "prompt={style_prompt}" \
  -F "model={model_name}" \
  -F "guidance={guidance}" \
  -F "steps={steps}" \
  -F "seed={random_seed}"

Model mapping:

User flag API model name Steps Guidance Max images Info
klein (default) Flux_2_Klein_4B_BF16 4 (fixed) ignored 3 Faster, multi-image support
qwen QwenImageEdit_Plus_NF4 10-50 (default: 20) 7.5 1 More control, higher fidelity

Klein model limits:

  • Resolution: 256-1536px (step: 16)
  • Steps: 4 (fixed)
  • Guidance: not supported
  • Max input images: 3

Parameters:

Parameter Klein Qwen Description
guidance ignored 7.5 Prompt adherence (1-20)
steps 4 (fixed) 20 Inference steps
seed random random For reproducibility (0-999999)

Read the full file on GitHub · 109 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 109 lines · 11 tokens per session scan A ec0b09f312bf

Subscribe to this mod's changes

transform-image is a command published in the GitHub repository deapi-ai/claude-code-skills (21 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 989 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.