P-Image LoRA · Text to Image
Text to image
Current price
$0.006 / image
Product use cases · In-product generation · Images and video
Bring each story branch to life without losing continuity.
Define the scene and recurring characters first, then choose image and video models for the visual style and inputs you need. Estimate each branch before generating variants so the story can grow without surprising costs.
- Best for
- Narrative apps, interactive fiction teams and creator tools building branching visual experiences.
- What you get
- A reusable scene plan whose images and clips can be updated without losing character or story context.
Concept illustration
A creative brief to try
Stage two choices from one invitation
A fictional 30-year-old woman with a black bob and emerald dress receives an invitation at a hotel. Branch A moves to a rooftop meeting; branch B stays in the lounge to write a reply.
- 01
Prepare separate references for her identity, the emerald dress, and the hotel setting. Reuse the same identity reference for both branches.
- 02
Build both branches as stills first. In A, change the location to the rooftop; in B, keep the lounge and change her action to writing.
- 03
Choose the branch the reader follows, then animate only that still with one small action, such as a glance or a pen stroke.
Before you keep the result
Check her face and dress in both branches. The rooftop and the written reply should make the two choices clear without extra explanation.
Start with your own reference images, follow the scene plan and review each result.
Open this scene in the Playground →Recommended models
169 matching models
Matches use the tasks and required capabilities published in the catalogue. Availability and current prices come from each model page.
FLUX.1 Schnell LoRA · Image Editing
Image editing
Current price
$0.006 / image
FLUX.1 Schnell LoRA · Text to Image
Text to image
Current price
$0.006 / image
Current price
$0.0093 / image
Z-Image · Text to Image
Text to image
Current price
$0.01 / image
Current price
$0.011 / output second
Current price
$0.011 / image
Current price
$0.011 / output second
What one run costs
Worked out from the live catalogue, at the settings named under each figure.
Catalog estimates refresh hourly. Check the estimate for your settings before running; final charges follow the model’s usage and billing policy.
How to build it
Branches are the expensive part: quote a branch before you build it, generate the clip only when a reader actually arrives there, and poll instead of holding a connection open for a scene nobody may reach.
- 01
Price the run before it exists
POST
/api/v1/jobs/quoteThe same validation and admission rules as creating the task, except nothing is created and no money is held. The signed quote lasts five minutes.
- 02
Create the task
POST
/api/v1/jobs/createTask202 means accepted, not finished. Send an Idempotency-Key, and if the price must not move, send the jobs/quote result together with the amount you agreed to.
- 03
Read the task back
GET
/api/v1/jobs/recordInfoOne task ID, one record. Queued, running and terminal states share the same shape, and this response is never cached.
- 04
Move the file into your own storage
POST
/api/v1/common/download-urlMint a short-lived download URL for the output and copy it into your own bucket within the same job. Results stay on our CDN for 14 days.
Copy a request
This example starts with the scene described on this page. Fields come from the selected endpoint’s schema. Replace any example.com reference URL with your own image or committed file URI before sending.
P-Image LoRA · Text to Image →
Where this usually snags
Platform behaviour that is cheaper to design around than to discover in production.
202 is a commitment
An accepted task runs to the end and the hold stands; there is no cancel. While the parameters are still moving, quote first — the same checks, nothing created.
The catalogue number is where the price starts
Most video endpoints bill by resolution and length, so the figure beside a model is its lowest tier, not your settings. Budget against the estimate shown before the run.
The result URL is not your archive
Generated media stays on our CDN for 14 days and uploaded sources for one day. Copy whatever you keep into your own bucket inside the same job.
Launch checklist
- 01Give every scene and branch a stable ID and define the output each one needs.
- 02Keep approved character references and model choices alongside the story plan.
- 03Review the estimate and cap variants before generating a branch; an accepted task cannot be canceled.
- 04Confirm that every depicted person meets the age, consent and likeness requirements before submission.
Models that match this workflow
Explore model families for this workflow. Open a model page to review its inputs, pricing and current availability.
Frequently asked questions
169 published models match the listed tasks and required capabilities. Compare their inputs, examples, availability and current prices before choosing one.
Prepare reference images for recurring characters and store their versions with each story branch. Reusing those references or first frames helps preserve characters and settings; prompts should still describe what changes in each shot.
You can use models that support unrestricted creative work. SpicyAPI adds no content classifier and requires no per-request declaration. For first-frame models, establish the still before generating the clip. Capabilities depend on the selected model.
Use stills to develop each branch and generate video only when a reader reaches it. Review the estimate for the selected model and settings before submission to avoid paying for content that is never used.
Use stills for background information and dialogue, and video when movement or a camera change contributes to the story. Compare the estimate and output quality to focus the budget on important scenes.
About this workflow
Combine text, images and video into a branching story: text defines the choices, images establish the scene and video develops key moments. Reusing visual references helps maintain continuity. Check each uncensored model’s supported inputs and capabilities. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.
