flux-image · acedatacloud — Claude Code skill: Flux image generation and editing
flux-image is a Claude Code skill for generating and editing images through the AceDataCloud Flux API, including text-to-image, instruction-based edits, and FLUX 3 video.
Apache-2.0 238 installs ★ 17 updated 2026-11-07
npx skills add AceDataCloud/Skills --skill flux-image -a claude-codeWhat flux-image does
The skill calls Flux models (flux-dev, flux-2-pro, flux-2-max, flux-kontext-pro) to create images from prompts or edit uploaded files. For generation, set action: generate, pick a model and size — pixel dimensions for flux-dev and flux-2-klein (1024x1024, 768x1344), aspect ratios for the rest (1:1, 16:9, 3:2). Editing (action: edit) needs image_url and a kontext model. All requests are async: set async: true, get a task ID, poll POST /flux/tasks with {"id": "..."} — do not start a second billable generation just to check the first.
For video, use POST /flux/videos with mode=t2v (text to video), i2v (image to video) or v2v (video to video). Duration 5–20 seconds, resolution hd/fhd/qhd/uhd. Without an API key in ~/.openclaw/.env, the skill will not start — grab it from the Applications section on platform.acedata.cloud, confirm access to /flux/images and /flux/tasks, never commit .env.
The count parameter multiplies cost by the number of images per request. flux-2-klein is fastest but generation-only. flux-2-max delivers top quality but is slower: iterate on dev/klein/flex, run final output on max.
What it helps with
- generate an image from a text description
- edit background or details in an uploaded photo
- create a video from a prompt or keyframes
- get multiple variations in one request
- pick a model by speed-quality tradeoff
Example prompts for the agent
- Generate a minimalist mountain logo with
flux-2-pro, aspect ratio1:1 - Replace the background in this photo with a beach sunset using
flux-kontext-pro - Generate a 10-second video of a cat in a space helmet,
t2vmode,fhdresolution
How to install flux-image
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill flux-image -a claude-code2Manually: put the files in place
~/.claude/skills/flux-image/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/flux-image/
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill flux-image -a codex2Manually: put the files in place
.agents/skills/flux-image/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill flux-image -a cursor2Manually: put the files in place
.cursor/skills/flux-image/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install AceDataCloud/Skills skills/flux-image2Manually: put the files in place
.github/skills/flux-image/SKILL.md1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill flux-image -a gemini-cli2Platform CLI
gemini skills install https://github.com/AceDataCloud/Skills --path skills/flux-imageManually: put the files in place
.devin/skills/flux-image/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill flux-image -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about flux-image
How to install flux-image in Claude Code?
Run npx skills add AceDataCloud/Skills --skill flux-image -a claude-code. The skill will appear in ~/.claude/skills/flux-image/SKILL.md.
What does flux-image do?
Generates images from text and edits uploaded pictures via Flux API. Supports models from flux-dev to flux-2-max and kontext for editing, plus FLUX 3 video creation.
Which key does flux-image need?
An ACEDATACLOUD_API_TOKEN from the Applications section on platform.acedata.cloud. Put it in ~/.openclaw/.env, restart Gateway, never commit the .env file. Confirm access to /flux/images and /flux/tasks in the key settings.
Source text
SKILL.md · Apache-2.0
---
name: flux-image
description: Generate and edit Flux images or generate FLUX 3 videos via AceDataCloud API. Use when creating images from text prompts, editing existing images with text instructions, or when high-quality image generation is needed. Supports image models plus text/image/video generation and temporary owned video drafts.
license: Apache-2.0
metadata:
author: acedatacloud
version: "1.0"
compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (get an API key at https://platform.acedata.cloud/console/applications). Optionally pair with mcp-flux-pro for tool-use.
---
# Flux Image Generation
Generate and edit images through AceDataCloud's Flux API.
## First-time setup
1. Install the official Skill with `clawhub install @acedatacloud/flux`. Check that the ClawHub publisher is **@acedatacloud**.
2. Sign in at [AceDataCloud → Applications](https://platform.acedata.cloud/console/applications), open **General application**, and check Flux access, balance, and current pricing. Copy its API key, or select **Manage Keys → Create** for a separate key. Copy the key value without `Bearer `; a `platform-...` management token is not a service API key.
3. If you enable **Allowed APIs** restrictions, include `/flux/images` and `/flux/tasks`. Advanced workflows below may call additional routes.
4. On the OpenClaw Gateway host, put `ACEDATACLOUD_API_TOKEN=your_api_key_here` in `~/.openclaw/.env`, then restart the Gateway and start a new session. For a direct terminal test, run `export ACEDATACLOUD_API_TOKEN="your_api_key_here"` in that shell. Never put the key in a prompt or commit an `.env` file.
5. Run the **Quick Start** below. If it returns a task ID, query that same task until it finishes; do not submit a second billable generation just to check progress.
[Illustrated key setup, first run, and troubleshooting](https://github.com/AceDataCloud/Skills#first-run-with-clawhub-and-openclaw) · [Token details](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/authentication.md)
## Quick Start
```bash
curl -X POST https://api.acedata.cloud/flux/images \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"action": "generate", "prompt": "a cat wearing a space helmet, photorealistic", "model": "flux-dev", "size": "1024x1024", "async": true}'
```
> **Async:** See [async task polling](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/async-tasks.md). Poll via `POST /flux/tasks` with `{"id": "..."}`.
## Models
| Model | Quality | Speed | Sizes | Best For |
|-------|---------|-------|-------|----------|
| `flux-dev` | Good | Fast | 256–1440px | Quick generation (default) |
| `flux-pro` | High | Medium | 256–1440px | Production work |
| `flux-2-klein` | Good | Fastest | 256–1440px | Compact / lowest-latency Flux 2 generation |
| `flux-2-flex` | High | Fast | Aspect ratios | Faster high-quality generation |
| `flux-2-pro` | Higher | Medium | Aspect ratios | Better prompt following |
| `flux-2-max` | Highest | Slow | Aspect ratios | Maximum quality generation |
| `flux-kontext-pro` | High | Medium | Aspect ratios | Image editing |
| `flux-kontext-max` | Highest | Slow | Aspect ratios | Complex editing |
## Generate Images
```json
POST /flux/images
{
"prompt": "a minimalist logo of a mountain",
"action": "generate",
"model": "flux-2-pro",
"size": "1:1",
"count": 1
}
```
### Size Options
**For `flux-dev`, `flux-pro`, and `flux-2-klein`** (pixel dimensions):
- `"1024x1024"`, `"1344x768"`, `"768x1344"`, `"1024x576"`, `"576x1024"`
**For `flux-2-flex`, `flux-2-pro`, `flux-2-max`, and Kontext models** (aspect ratios, not pixel dimensions):
- `"1:1"`, `"16:9"`, `"9:16"`, `"4:3"`, `"3:4"`, `"3:2"`, `"2:3"`, `"21:9"`, `"9:21"`
## Edit Images
Use kontext models for text-guided image editing:
```json
POST /flux/images
{
"prompt": "change the background to a beach sunset",
"action": "edit",
"image_url": "https://example.com/photo.jpg",
"model": "flux-kontext-pro",
"size": "1:1"
}
```
## Gotchas
- Send `size` explicitly: pixel dimensions for `flux-dev`, `flux-pro`, and `flux-2-klein`; aspect ratios for `flux-2-flex`, `flux-2-pro`, `flux-2-max`, and Kontext
- For MCP `flux_edit_image`, select a model from its live schema; `flux-2-klein` supports generation only and is not an edit-model choice
- `count` parameter generates multiple images in one request (increases cost proportionally)
- `flux-2-klein` is the lightest Flux 2 model — useful when latency matters more than peak quality
- `flux-2-max` produces highest quality but is slowest — use dev/klein/flex for iteration and max for final output
- All generation is async — always set `"callback_url"` to get a task id immediately, then poll `/flux/tasks` using `{"id":"<task_id>"}` or `{"ids":[...],"action":"retrieve_batch"}`
> **MCP:** `pip install mcp-flux-pro` | Hosted: `https://flux.mcp.acedata.cloud/mcp` | See [all MCP servers](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/mcp-servers.md)
## FLUX 3 video tools
`POST /flux/videos` generates videos with `action=generate` (default). Use `mode=t2v/i2v/v2v/draft_enhance`. T2V needs prompt; I2V also needs keyframes; V2V also needs start_video. Normal video requests support hd/fhd/qhd/uhd, integer duration 5–20 seconds (V2V up to 15) or auto, draft and generate_audio flags. Preserve explicit false.
Draft enhancement uses an owned platform draft_task_id and requires its temporary cache to remain available. It does not promise indefinite retention.
Companion MCP tool: flux_generate_video. CLI command: flux video --request-file. MCP/CLI requests submit asynchronously by default and are polled through the existing /flux/tasks endpoint. For raw HTTP requests, set async=true to receive a task ID immediately. Generation charges use actual output seconds; do not substitute requested duration for measured final usage.
© acedatacloud · Apache-2.0 · AceDataCloud/Skills
Similar skills
All skills for AI and ML →flux-image by other authors comes first.