Claude Code image generation
Claude Code image generation with AnyCap.
Generate and edit images from the same terminal session.
Claude can inspect uploaded images, but Anthropic does not provide a built-in image generator in Claude Code. AnyCap adds that missing execution layer through one skill and CLI. Claude Code can turn a request into a text-to-image or image-to-image command, save the result into the project, and continue the coding workflow without a separate image API integration.
Verified workflow · August 19, 2026
A real Claude Code image workflow, checked against the live AnyCap catalog.
Claude Code supplies the planning and terminal orchestration; AnyCap supplies the image runtime. The current CLI catalog exposes eight active image models and both text-to-image and image-to-image modes. Generated files can be downloaded directly into the working project with -o.
CLI checked
AnyCap CLI 0.6.0
Live catalog
8 active image models
Verified modes
text-to-image, image-to-image
Delivery
Local output path with -o
anycap image models gpt-image-2 schema --operation generateWhat “Claude Code image generation” means here
Agent skill
Best when you want Claude Code to choose the appropriate AnyCap command from a natural-language request and keep the result inside the current task.
Direct CLI
Best when you want explicit control over the model, mode, input image, parameters, and output filename. Claude Code can run the same command for you.
Install path
Step 1
npx -y skills add anycap-ai/anycap -a claude-code -y
Step 2
curl -fsSL https://anycap.ai/install.sh | sh
Step 3
anycap login
Current image models Claude Code can call
GPT Image 2
OpenAI's image family for general generation and prompt-driven image edits.
Seedream 5
A current text-to-image and image-to-image option for polished first-pass assets.
Nano Banana Pro
A strong fit when Claude Code starts from an existing image and needs iterative visual revisions.
Nano Banana 2
A faster option for generating variants and repeated image iterations.
First commands to try
Text to image
anycap image generate --model seedream-5 --prompt "launch announcement visual on off-white background" -o claude-code-launch-visual.png
Image editing
anycap image generate --model nano-banana-pro --mode image-to-image --prompt "add olive highlight accents and softer shadows" --param images=./mockup.png -o edited-mockup.png
FAQ
Is this a Claude Code skill?
Yes. AnyCap ships an agent skill for Claude Code. The skill teaches Claude Code when and how to use the AnyCap CLI for image generation and editing.
How do I install the AnyCap image generation skill in Claude Code?
Three commands. Run npx -y skills add anycap-ai/anycap -a claude-code -y to add the skill, curl -fsSL https://anycap.ai/install.sh | sh to install the AnyCap CLI binary, then anycap login. After that the skill is ready inside any Claude Code session.
Can Claude Code generate images on its own?
Not as a built-in capability. The AnyCap skill adds image generation to Claude Code through one install path and one CLI.
Which image models does the skill expose?
The live AnyCap catalog currently lists eight active image models, including GPT Image 2, Seedream 5, Nano Banana Pro, Nano Banana 2, FLUX.1 Kontext Max, Qwen Image, Seedream 4.5, and Nano Banana 2 Lite. Check anycap image models before production use because the catalog can change.
Do I need a different workflow for image editing?
No. The same anycap image command in the skill covers both text-to-image and image-to-image workflows depending on the model and flags you use.