HiDream O1 Dev
hidream-ai/hidream-o1/devHidream O1 Dev by hidream-ai - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.
- Base price
- $0.005 / run
- Execution
- async
- Model type
- image
- Input fields
- 5
Try the model
Playground
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Your output will appear here
Complete the inputs, then click Run.
Specifications
Pricing
- Base price
- $0.005 / run
Context & modalities
- Input
- Schema-defined
- Output
- image
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- HiDream
- Model ID
- hidream-ai/hidream-o1/dev
- Execution
- async
- API
- Unified Run API
- Endpoint
- /v1/run
API README
HiDream O1 Dev
HiDream O1 Dev is a distilled image foundation model that unifies text-to-image generation, instruction-based editing, and subject-driven personalization. Its pixel-level unified architecture processes text, raw image content, and task conditions together for consistent in-context visual creation.
One endpoint covers three workflows: send no reference images to create from text, one image to apply an instructed edit, or multiple images to carry subjects into a new scene. This is the O1 Dev model, distinct from the earlier HiDream I1 family.
Highlights
- One model, three workflows. Moves between text-to-image generation, single-image instruction editing, and multi-reference personalization according to the supplied references.
- Pixel-level unified generation. Treats text, image pixels, and task conditions in a shared token space instead of separating generation and editing into unrelated systems.
- Subject-driven personalization. Uses multiple references to preserve a person, character, product, or visual identity while placing it in a newly described setting.
- Long-text rendering and layout control. Creates multi-region compositions with accurate multilingual text, supporting information-dense posters, editorial layouts, and designed graphics.
Pricing
| Unit | Price |
|---|---|
| Per request | $0.005000 |
When to Use
| Good fit | Consider alternatives |
|---|---|
| Creating an image from text with zero references | A specialized text-to-image route when references will never be used |
| Applying a natural-language change to one image | Pixel-perfect masks or manual retouching |
| Personalizing a scene from multiple subject references | A single-reference task with strict reference preservation |
| Keeping a character or product recognizable in a new setting | Video, animation, or 3D generation |
| Combining generation and editing behind one integration | Workflows requiring explicit layout boxes or skeleton controls not exposed here |
Prompt Guide
Match the prompt to the reference count. With no images, fully describe the scene. With one image, state exactly what should change and what must remain. With multiple images, identify the shared subject and describe the new setting, pose, camera, and identity details to preserve.
{
"prompt": "Use the referenced ceramic mug as the exact product identity. Place it on a pale stone café table beside an open sketchbook, soft morning window light from the left, eye-level product photography, shallow depth of field. Preserve the mug's shape, glaze color, handle, and printed emblem.",
"images": [
"https://example.com/references/mug-front.png",
"https://example.com/references/mug-side.png"
],
"aspect_ratio": "4:3",
"output_format": "png",
"seed": 42
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | hidream-ai/hidream-o1/dev |
| Input | Required text prompt; optional array of reference-image URLs |
| Reference workflow | 0 images: text-to-image; 1: editing; 2 or more: subject-driven personalization |
| Aspect ratios | 21:9, 16:9 (default), 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 |
| Output format | PNG (default) or JPEG |
| Optional controls | Integer seed |
| Output | One downloadable image URL |
| Execution | Async |
Related
- HiDream O1 — Full O1 generation model
- HiDream O1 Dev Edit — Dedicated editing route for the Dev variant
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# Preserve Unicode and shell metacharacters in the request body.
result=$(printf '%s' 'ewogICJtb2RlbCI6ICJoaWRyZWFtLWFpL2hpZHJlYW0tbzEvZGV2IiwKICAiaW1hZ2VzIjogWwogICAgImh0dHBzOi8vc3RhdGljLnNhbmRiYXNlLmFpL2V4YW1wbGVzL2hpZHJlYW0tYWkvaGlkcmVhbS1vMS9kZXYvaW5wdXRfcmVmZXJlbmNlX2ltYWdlX3VybHNfMC5wbmciCiAgXSwKICAicHJvbXB0IjogIkEgY2luZW1hdGljIHByb2R1Y3QgcGhvdG8gb2YgYSBjZXJhbWljIG11ZyBvbiBhIG1hcmJsZSBjb3VudGVyLCBzb2Z0IHdpbmRvdyBsaWdodCwgc2hhbGxvdyBkZXB0aCBvZiBmaWVsZC4iLAogICJhc3BlY3RfcmF0aW8iOiAiMTY6OSIsCiAgIm91dHB1dF9mb3JtYXQiOiAicG5nIgp9' \
| base64 --decode \
| curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @-)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
HiDream O1 DevThis model HiDream | — | — | — | May 9, 2026 |
HiDream | — | — | — | May 9, 2026 |
HiDream | — | — | — | May 9, 2026 |
HiDream | — | — | — | May 9, 2026 |
HiDream | — | — | — | Apr 11, 2025 |
HiDream | — | — | — | Apr 11, 2025 |