Model comparisons
At 480p, Wan 2.2 Spicy LoRA costs 15% less than LTX 2.3 Spicy LoRA. LTX 2.3 Spicy LoRA renders up to 20 seconds per request; Wan 2.2 Spicy LoRA stops at 8.
LTX 2.3 Spicy LoRA is an uncensored image-to-video build on Lightricks' LTX 2.3 with thirteen built-in LoRAs. Pick the tuned or original preset and re-weight up to three LoRAs from 0 to 4; clips run 3 to 20 seconds at 480p to 1080p.
View model details →View sample outputs →Wan 2.2 Spicy LoRA image-to-video turns an opening frame and a prompt into an uncensored clip with up to three of your own LoRAs. Clips run 5 or 8 seconds at 480p or 720p, with no content declaration in the request.
View model details →View sample outputs →Compare
Start with the input you have, the result you want and your budget. These are the differences that affect that choice.
Compare the published examples, then try the same input on both models with matching settings.
The Spicy Index and Freedom Score for both models, from the same daily calculation as the leaderboards.
| Measure | LTX 2.3 Spicy LoRA | Wan 2.2 Spicy LoRA |
|---|---|---|
| Spicy Index | 63.3 | 68.0 |
| Freedom Score | 83.8 | 74.8 |
| Evidence | Tested 6 of 6 probe types · 19 runs | Tested 6 of 6 probe types · 26 runs |
| Range if the rest pass | 83.8–83.8 | 74.8–93.8 |
| Price | $0.238 per 5-second clip | $0.24 per 5-second clip |
| Reviews | Read the LTX 2.3 Spicy LoRA review | Read the Wan 2.2 Spicy LoRA review |
Preliminary · limited independent quality evidence
See both on the leaderboard →Current price
A start price answers a different question than the one you have. These are the tiers both models publish, matched setting for setting, in US dollars per billed unit with no conversion step in between.
Swipe horizontally to compare all fields.
| Tier | LTX 2.3 Spicy LoRA | Wan 2.2 Spicy LoRA | Difference |
|---|---|---|---|
| 480p | $0.029 / output seconds | $0.024 / output seconds | Wan 2.2 Spicy LoRA −15% |
| 720p | $0.048 / output seconds | $0.048 / output seconds | LTX 2.3 Spicy LoRA −1% |
Arithmetic on the published rates at each model's own default setting, not a quote. The console prices your actual settings before a request is accepted.
About this comparison
Every row here is read from the JSON Schema the endpoint validates against, so it matches what the API will really accept rather than a feature list written by hand.
Swipe horizontally to compare all fields.
| Controls and limits | LTX 2.3 Spicy LoRA | Wan 2.2 Spicy LoRA |
|---|---|---|
| Supported tasks | image-to-video | image-to-video |
| Clip length | 3–20 seconds | 5–8 seconds |
| Resolution tiers | 480p · 720p · 1080p | 480p · 720p |
| High-resolution tier | Yes | No |
| Seed | Yes | Yes |
| Execution | Submit, then poll or take the callback | Submit, then poll or take the callback |
| Request timeout | 60 minutes | 60 minutes |
| Availability | Live | Live |
Do low-filter models allow every request?
Two separate facts sit behind these labels. The first is what we do, which is nothing: no platform content filter, and no maturity flag to set on a request. The second is what each model does on its own, and that is the only part that varies between these two.
LTX 2.3 Spicy LoRA
This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.
Usage note Only consenting adults and properly licensed material may be used. Minors, non-consensual intimate imagery, and deceptive real-person impersonation are prohibited.
Wan 2.2 Spicy LoRA
This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.
Usage note Only consenting adults and properly licensed material may be used. Minors, non-consensual intimate imagery, and deceptive real-person impersonation are prohibited.
Use these content labels to shortlist models, then open each model page for available examples and content-test details.
The label never changes your obligations. Age, consent, real-person likeness and the law where you operate stay with you, and SpicyAPI does not inspect each request.
Can I swap the model ID without changing the request body?
The task lifecycle is shared; the body is not. Each endpoint publishes its own JSON Schema and the API validates against that, so this is the list to reconcile before a switch.
How to choose
LTX 2.3 Spicy LoRA supports a high-resolution option.
Compare
The model identifiers are lightricks/ltx-2.3-spicy-lora/image-to-video and alibaba/wan-2.2-spicy-lora/image-to-video, and both go in the same field of the same request.
Both run the same way: submit the task, then poll it or take the callback. Queueing and retry logic carry over unchanged.
Both use the same submit-and-track flow, but their required inputs may differ. Check each model page before switching.
One key, one balance, one set of spend caps. Both bill to the same account in US dollars, and the per-key daily, monthly and lifetime limits apply to whichever one you call.
Questions developers ask
Wan 2.2 Spicy LoRA is 15% cheaper at 480p, the closest like-for-like setting the two publish. Prices may change; check the estimate shown for your actual settings before submitting.
LTX 2.3 Spicy LoRA allows 60 minutes per task and Wan 2.2 Spicy LoRA allows 60. Those are ceilings rather than typical times — most requests finish far sooner — but they are what your own client timeout has to survive.
Prices and capabilities shown here come from the current public model catalogue. Check each model page for its latest inputs and examples.