--- url: /orchestration/recipes/training-ltx2.md --- > Documentation index: https://developer.civitai.com/llms.txt — every page on this site has a markdown version at its URL + `.md`. # LTX2 video LoRA training Train a Lightricks LTX video LoRA on a small set of source video clips using AI Toolkit. The output LoRA is usable in [LTX2 video generation](https://developer.civitai.com/orchestration/recipes/ltx2.md). | `ecosystem` | Base | Default price | Notes | |-------------|------|---------------|-------| | `ltx2` | `Lightricks/LTX-2` (19B) | 2750 Buzz | Original LTX2. | | `ltx23` | `Lightricks/LTX-2.3` (22B) | 2750 Buzz | Newer LTX 2.3. | The base checkpoint is fixed by `ecosystem`; there's no `model` field on the input. Video training is the slowest training mode on the platform — video needs a longer run, so the LTX **default is 3000 steps** (vs 2000 for image ecosystems). Submit with `wait=0`. The request fields, training data, continuing a run and live progress are shared by every ecosystem — see the [LoRA training overview](https://developer.civitai.com/orchestration/recipes/training.md). ## The request shape ```json { "$type": "training", "input": { "engine": "ai-toolkit", "ecosystem": "ltx2" // ltx2 | ltx23 } } ``` ## Prerequisites * A training-data zip of images, video clips, or a mix — addressed by an AIR ([accepted sources](https://developer.civitai.com/orchestration/recipes/training.md#training-data)), with an accurate `count` of items ## LTX2 Original 19B-parameter LTX video model. `resolution: 768` is the typical training resolution. ```http POST https://orchestration.civitai.com/v2/consumer/workflows?wait=0 Authorization: Bearer Content-Type: application/json { "tags": ["training", "video"], "steps": [{ "$type": "training", "priority": "normal", "retries": 2, "input": { "engine": "ai-toolkit", "ecosystem": "ltx2", "steps": 3000, "resolution": 768, "lr": 0.0002, "trainTextEncoder": false, "lrScheduler": "cosine", "optimizerType": "adamw8bit", "networkDim": 32, "networkAlpha": 32, "trainingData": { "type": "zip", "sourceUrl": "urn:air:other:other:huggingface:datasets/Civitai/orchestration-samples@e86d025874700507615ae8ef74937c319ea41dfe/sample-training-dataset.zip", "count": 15 }, "samples": { "prompts": ["a video of TOK", "TOK moving in a garden"] } } }] } ``` ## LTX 2.3 Newer 22B model. Same shape as LTX2; `lr` is typically lower. Both LTX ecosystems share the same rates and 3000-step default, so the default price matches (2750 Buzz). ```http POST https://orchestration.civitai.com/v2/consumer/workflows?wait=0 Authorization: Bearer Content-Type: application/json { "tags": ["training", "video"], "steps": [{ "$type": "training", "priority": "normal", "retries": 2, "input": { "engine": "ai-toolkit", "ecosystem": "ltx23", "steps": 3000, "lr": 0.0001, "trainTextEncoder": false, "lrScheduler": "cosine", "optimizerType": "adamw8bit", "networkDim": 32, "networkAlpha": 32, "trainingData": { "type": "zip", "sourceUrl": "urn:air:other:other:huggingface:datasets/Civitai/orchestration-samples@e86d025874700507615ae8ef74937c319ea41dfe/sample-training-dataset.zip", "count": 15 }, "samples": { "prompts": ["a video of TOK", "TOK moving in a garden"] } } }] } ``` ## LTX parameters {#common-parameters} Defaults apply to both LTX ecosystems. Fields and defaults not listed here are as in the overview's [common parameters](https://developer.civitai.com/orchestration/recipes/training.md#common-parameters). | Field | LTX default | Notes | |-------|-------------|-------| | `steps` | `3000` | Video needs a longer run, hence the higher default. | | `epochs` | `round(steps / 200)` | `15` for `steps: 3000`; `10` if `steps` is omitted too. **Each adds 50 Buzz** — LTX preview samples are videos and costly to compute. | | `batchSize` | `1` | Fixed at 1 for this ecosystem. | | `continueFrom` | *(none)* | A LoRA of the same ecosystem (`urn:air:ltx2:lora:...` / `urn:air:ltx23:lora:...`) to resume from. | | `lr` | `0.0001` | LTX2 examples often use `0.0002`; LTX 2.3 typically `0.0001`. | | `trainTextEncoder` | `false` | Leave off — LTX text encoder is not retrained by AI Toolkit. | | `trainingData` | ✅ | Images, video clips, or a mix; the example uses an image dataset. | | `samples.prompts[]` | `[]` | Preview videos rendered at each saved checkpoint. | ## Reading the result The [standard training output](https://developer.civitai.com/orchestration/recipes/training.md#reading-the-result): each saved checkpoint yields a video LoRA `.safetensors` blob plus any sample `.mp4` files. Use the trained LoRA in [LTX2 video generation](https://developer.civitai.com/orchestration/recipes/ltx2.md) by referencing it in the workflow's `loras` field. ## Runtime Wall time, default settings on a 4-clip dataset: | Ecosystem | Per 100 steps | Typical full run | |-----------|---------------|-------------------| | `ltx2` | ~1–2 min | 30–60 min for 3000 steps | | `ltx23` | ~2–3 min | 60–90 min for 3000 steps | ## Cost The [training cost formula](https://developer.civitai.com/orchestration/recipes/training.md#cost) with LTX rates: ``` price = steps × costPerStep + epochs × 50 (rounded) costPerStep = 0.75 (ltx2 and ltx23) floor: never less than 80% of the default-configuration price ``` Each epoch adds 50 Buzz. With both `steps` and `epochs` omitted the run is **3000 steps / 10 epochs** → `3000 × 0.75 + 10 × 50 = 2250 + 500 = 2750 Buzz`. The **floor** is 80% of that price (2200 Buzz). The examples at the top of the page send `steps: 3000` with no `epochs`, so they get `round(3000 / 200) = 15` epochs: `15 × (200 × 0.75 + 50) = 15 × 200 = 3000 Buzz`. Send `epochs: 10` alongside `steps: 3000` to get the 2750 price. | Configuration | Buzz (training only) | |---------------|---------------------| | LTX2 / LTX 2.3, default (`steps: 3000`, `epochs: 10`) | 2750 + samples | | LTX2 / LTX 2.3, `steps: 3000`, `epochs: 20` | 3250 + samples (+500 for 10 more checkpoints) | | LTX2 / LTX 2.3, `steps: 2000`, `epochs: 10` | 2200 + samples (floor) | Sample-prompt rendering uses LTX2 video-generation rates and is billed separately. Preview the exact charge with `whatif=true` ([Payments (Buzz)](https://developer.civitai.com/orchestration/guide/submitting-work.md#payments-buzz)). ## Troubleshooting `steps` out of range, an unresolvable `sourceUrl`, a `count` mismatch and a rejected dataset are covered in the [overview's troubleshooting](https://developer.civitai.com/orchestration/recipes/training.md#troubleshooting). | Symptom | Likely cause | Fix | |---------|--------------|-----| | Step `failed` with VRAM-related error | Resolution × clip length too high | Lower `resolution` (e.g. to `512`), shorten clips. | | Training cost surprises you | Video defaults to 3000 steps, so the floor is higher than image ecosystems | Check `whatif=true` before submitting. Lowering `steps`/`epochs` saves at most 20% (the floor). | | Trained LoRA produces no motion | Too few steps / static reference clips | Raise `steps`, ensure clips show the motion you want learned. | ## Related * [LoRA training overview](https://developer.civitai.com/orchestration/recipes/training.md) — shared parameters, training data, live progress and cost formula * [Wan video LoRA training](https://developer.civitai.com/orchestration/recipes/training-wan.md) — Wan video LoRA training (preview) * [LTX2 video generation](https://developer.civitai.com/orchestration/recipes/ltx2.md) — use a trained LoRA in LTX2 inference * [Flux 2 Klein LoRA training](https://developer.civitai.com/orchestration/recipes/training-flux2-klein.md) — image-side counterpart * [Results & webhooks](https://developer.civitai.com/orchestration/guide/results-and-webhooks.md) * [`SubmitWorkflow`](https://developer.civitai.com/orchestration/reference/operations/SubmitWorkflow.md) · [`GetWorkflow`](https://developer.civitai.com/orchestration/reference/operations/GetWorkflow.md) * [`training` OpenAPI spec](https://orchestration.civitai.com/v2/consumer/recipes/training/openapi.yaml)