Models Your Agent Can Use
18+ AI models for image and video generation, all accessible through a single API
Flux Dev
High-quality development model with configurable steps, guidance, and LoRA support.
/models/flux-dev/runFlux Krea Dev
Photorealistic generation that avoids the oversaturated AI look. LoRA compatible.
/models/flux-krea-dev/runFlux 1.1 Pro
Latest pro model with enhanced quality and strong prompt adherence.
/models/flux-1.1-pro/runFlux 1.1 Pro Ultra
Highest quality Flux model with raw mode for natural-looking images.
/models/flux-1.1-pro-ultra/runFlux Kontext Pro
Advanced model with state-of-the-art performance for both generation and editing.
/models/flux-kontext-pro/runFlux Kontext Max
Premium model with maximum performance and improved typography for generation and editing.
/models/flux-kontext-max/runFlux 2 Flex
Max-quality with up to 10 reference images
/models/flux-2-flex/runFlux 2 Klein 4B
Very fast generation and editing with up to 5 reference images
/models/flux-2-klein-4b/runWAN 2.6 Flash
Fast and affordable image-to-video
/models/wan-2.6-flash/runWAN 2.2 Plus
Official Alibaba model with 1080p support
/models/wan-2.2-plus/runSeedance 1.5
ByteDance Seedance 1.5 video generation with native audio, dance motion, 480p/720p resolution, and up to 12 seconds duration
/models/seedance-1.5/runxAI Video
xAI video generation with text-to-video and image-to-video support
/models/xai-video/runThree Steps to Agent-Powered Creation
Install the skill, add your key, and your agent starts creating
Install the PixelDojo skill
Add the PixelDojo agent skill from ClawHub so your AI agent can generate images and videos.
Add your API key
Store your PixelDojo API key securely. The skill passes it with every request automatically.
Your agent creates media
Your agent submits generation jobs and polls for results. Images and videos are returned as URLs.
Simple API, Powerful Results
Your agent submits a job, polls for the result, and gets back a URL
/api/v1/models/{apiId}/runGenerate an image
Your agent picks a model and submits a prompt. A job ID comes back instantly.
POST /api/v1/models/flux-1.1-pro/run
{
"prompt": "A cinematic portrait of a silver fox in neon rain"
}/api/v1/models/{apiId}/runGenerate a video
Same endpoint, different model. Add duration, aspect ratio, or a reference image.
POST /api/v1/models/wan-2.2-flash/run
{
"prompt": "Drone flight through coastal cliffs at golden hour",
"image_url": "https://example.com/reference.png",
"duration": 6,
"aspect_ratio": "16:9"
}/api/v1/jobs/{jobId}Get the result
Poll the status URL until completed. Output URLs are available for 24 hours.
GET /api/v1/jobs/job_abc123
// Response:
// { "status": "completed", "output": { "images": ["https://..."] } }Quick Start
Drop these examples into your agent's tool functions
import requests, time
API_KEY = "pd_your_api_key"
# Your agent submits a generation job
job = requests.post(
"https://pixeldojo.ai/api/v1/models/flux-1.1-pro/run",
headers={"Authorization": f"Bearer {API_KEY}"},
json={"prompt": "A fantasy castle on a cliff at sunset"}
).json()
# Poll until the image is ready
while True:
result = requests.get(
job["statusUrl"],
headers={"Authorization": f"Bearer {API_KEY}"}
).json()
if result["status"] == "completed":
print("Image URL:", result["output"]["images"][0])
break
time.sleep(2)const API_KEY = "pd_your_api_key";
// Submit a generation job
const { statusUrl } = await fetch(
"https://pixeldojo.ai/api/v1/models/flux-1.1-pro/run",
{
method: "POST",
headers: {
Authorization: `Bearer ${API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
prompt: "A fantasy castle on a cliff at sunset",
}),
}
).then(r => r.json());
// Poll for the result
const result = await fetch(statusUrl, {
headers: { Authorization: `Bearer ${API_KEY}` },
}).then(r => r.json());
console.log(result.output);# Submit a job
curl -X POST "https://pixeldojo.ai/api/v1/models/flux-1.1-pro/run" \
-H "Authorization: Bearer pd_your_api_key" \
-H "Content-Type: application/json" \
-d '{"prompt":"A fantasy castle on a cliff at sunset"}'
# Poll for results
curl "https://pixeldojo.ai/api/v1/jobs/job_abc123" \
-H "Authorization: Bearer pd_your_api_key"Works Everywhere Your Agent Does
OpenClaw / ClawHub
Install the skill directly from ClawHub and your agent gains structured tool access to every PixelDojo model.
MCP & Chat Agents
Any MCP-compatible agent, chat assistant, or orchestrator can call the same REST endpoints.
Automation & Workflows
Wire image and video generation into pipelines with async polling or webhook callbacks.