Private beta — onboarding developers now
Image and video generation, one simple API.
Text-to-image, image editing, and image-to-video behind a single REST endpoint. Pay only for what you generate, from a prepaid balance. Unfiltered and uncensored: prompts go to the model exactly as you send them.
- Images from
- $0.006
- Video from
- $0.05 / s
- Minimum
- $5 top-up
curl https://api.fastgencloud.com/v1/images/generations \
-H "Authorization: Bearer $FASTGEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "krea-2",
"prompt": "product photo of a ceramic mug on a wooden desk, soft window light",
"size": "1024x1024"
}'{
"id": "5f2c1e0a-…",
"object": "job",
"status": "queued",
"model": "krea-2",
"usage": { "charged_micros": 6000, "charged_usd": 0.006 },
"moderation": { "status": "pending" }
}Endpoints
Open-weight, commercially licensed models running on dedicated GPU capacity — plus train-your-own characters. Same request shape everywhere.
Text to imageKrea 2
krea-2
Krea 2 (12B) photorealistic text-to-image. Write prompts as plain sentences — subject, action, clothing, setting, light, camera. Bring your own Krea 2 LoRAs by URL. Image-to-image, inpainting and trained-character generations run on a photoreal SDXL companion under this same model id (SDXL LoRAs there).
ImageSDXL Face ID
sdxl-face-id
Identity-preserving image-to-image on SDXL (IP-Adapter FaceID): one reference photo of a person + a prompt → new images of the same person in the described scene. style: realistic (photoreal, default), anime, cartoon — likeness is strongest on realistic. Bring your own SDXL LoRAs by URL (match the style's checkpoint family).
Image editingQwen Image Edit
qwen-image-edit
Qwen-Image-Edit instruction-based editing from 1–3 reference images: change objects, poses, styles or backgrounds, or combine subjects. Bring your own Qwen-Image-Edit LoRA by URL (one, next to the built-in anatomy LoRA).
Text to imageKrea 2 Anime
krea-2-anime
Krea 2 (12B) with a dedicated anime style: anime and illustration text-to-image from plain-sentence prompts. Bring your own Krea 2 LoRAs by URL. Image-to-image, inpainting and trained-character generations run on an Illustrious SDXL companion under this same model id (Illustrious LoRAs there).
Text to imageKrea 2 Cartoon
krea-2-cartoon
Krea 2 (12B) comics / cartoon finetune: bold line work, flat colour, expressive characters, from plain-sentence prompts. Bring your own Krea 2 LoRAs by URL. Image-to-image, inpainting and trained-character generations run on a Pony SDXL companion under this same model id (Pony LoRAs there).
Wan 2.2
wan-2.2
Wan 2.2 image-to-video: animate a still image into a 5 or 8 second clip at 32 fps; the start frame's aspect ratio is preserved. Bring your own WAN 2.2 LoRAs by URL (high-noise `url` + optional low-noise `low_url`).
MiniMax H3
minimax-h3
MiniMax H3 (33B omni-modal) image-to-video with native audio: a start frame + a prompt → a 5, 8 or 10 second clip at 24 fps with a generated soundtrack. The canvas follows the start frame (768 px short edge). Bring your own MiniMax H3 LoRAs by URL (up to 3). No negative prompt.
Wan 3
wan-3
Wan 3.0 Prime image-to-video (hosted): a start frame + a prompt → a 5–15 second clip with native audio at 480p, 720p or 1080p. Prompt-only — no LoRAs, no negative prompt. Longer to render than wan-2.2; higher fidelity and sound.
Character trainingCharacters
POST /v1/characters
Train a reusable character from 4–30 photos of one person in ~10–15 minutes, then generate them on krea-2, krea-2-anime or krea-2-cartoon with the character parameter. 2 free slots; packages from $10/mo.
How it works
- 01
Create an API key
Sign up, add a prepaid balance with a card, and create a key in the console.
- 02
Submit a job
POST a prompt (and optionally an image) to /v1. You get a job id back immediately.
- 03
Poll or get a webhook
Fetch /v1/jobs/{id} or receive a signed webhook when your image or video is ready.
Guides
How to build the things people actually build with a generation API. Each one ends in code you can run.
- Unfiltered image generation APISeveral of the large hosted image APIs put a policy layer between your prompt and the sampler: they rewrite what you wrote, append rating tags you never asked for, and re-classify the result before releasing it.
- Consistent characters across generated imagesDiffusion models have no memory between calls, so the same prompt gives you a different person every time.
- AI product photography with an APIOne decent photo of a product can become an entire catalogue: different surfaces, different lighting, seasonal backgrounds, ad crops.
- Animate a still image into videoImage-to-video takes a frame you already approve of and adds motion.
Simple, prepaid pricing
Add funds by card; each job is charged from your balance at the rates below. No subscriptions, no minimum monthly spend, refunds on unused balance.
| Operation | Model | Price |
|---|---|---|
| Text to image (≤ 1 MP) | krea-2, krea-2-anime, krea-2-cartoon | $0.006 / image |
| Image edit | qwen-image-edit | $0.03 / image |
| Face ID (image to image, ≤ 1 MP) | sdxl-face-id | $0.012 / image |
| Image to image, inpaint and character generations (≤ 1 MP) | krea-2, krea-2-anime, krea-2-cartoon | $0.006 / image |
| Image to video | wan-2.2 | $0.05 / second |
| Image to video with audio | minimax-h3 | $0.06 / second |
| Image to video with audio (hosted) | wan-3 | $0.09 / second |
| Character training | characters | $0.75 / training |
| Character slots — 10 | 10 characters (2 free on every account) | $10.00 / month |
| Character slots — 100 | 100 characters | $39.00 / month |
| Character slots — 500 | 500 characters | $129.00 / month |
Your product, your policy
FastGen Cloud is a general-purpose, unfiltered image and video API for developers and businesses. We do not inject prompts, steer styles, or filter what your product allows — you decide that. One line is enforced automatically on every job and cannot be turned off: nothing involving minors. Every prompt is checked for it before the job is queued.
Read the content policy and the Acceptable Use Policy.
Get in touch
Questions about pricing, volume, or the beta? Email support@fastgencloud.com — we reply within one business day.
Contact us