| --- |
| license: other |
| license_name: ltx-2-community-license |
| license_link: LICENSE |
| base_model: Lightricks/LTX-2 |
| tags: |
| - mlx |
| - apple-silicon |
| - text-to-video |
| - image-to-video |
| library_name: mlx |
| --- |
| |
| # ltx-2.3-mlx — bf16 components + distilled transformer |
|
|
| **A verbatim availability mirror.** Full-precision LTX-2.3 components (connector, video/audio VAEs, vocoder, spatial upscaler) plus the bf16 distilled transformer. |
|
|
| ## Why this repo exists |
|
|
| This is an unmodified mirror of [`dgrauet/ltx-2.3-mlx`](https://huggingface.co/dgrauet/ltx-2.3-mlx), |
| hosted so that downstream software has a weight source that does not depend on a third-party |
| namespace remaining available. It exists for **durability, not improvement** — there is nothing |
| here you cannot get upstream, and upstream is the better place to get it if you want the |
| newest revision. |
|
|
| The motivation is concrete rather than hypothetical: an unrelated model family we ship ports |
| of was relocated to a new organization without HTTP redirects, and every published package |
| referencing the old paths broke the same day. Availability is a dependency like any other. |
|
|
| ## Provenance chain |
|
|
| | Stage | Who | What | |
| |---|---|---| |
| | Original weights | **Lightricks** | [LTX-2](https://huggingface.co/Lightricks/LTX-2) — a DiT-based joint audio+video model. All model IP is theirs. | |
| | MLX conversion | **dgrauet** | Converted to MLX format with [mlx-forge](https://github.com/dgrauet/mlx-forge); published as [`dgrauet/ltx-2.3-mlx`](https://huggingface.co/dgrauet/ltx-2.3-mlx) alongside the [ltx-2-mlx](https://github.com/dgrauet/ltx-2-mlx) inference pipeline. | |
| | This mirror | xocialize | **Byte-for-byte copy. No modification of any kind.** | |
|
|
| **We did not convert, quantize, fine-tune, or otherwise alter these weights.** Every tensor |
| file here was verified by SHA-256 against the corresponding upstream file at mirror time; the |
| hashes are listed below so anyone can check that claim independently. |
|
|
| Small JSON metadata files were taken fresh from upstream at mirror time and may therefore carry |
| metadata additions relative to an older local copy; the tensor files are the verified artifacts. |
|
|
| ## Licence — read this before use |
|
|
| These weights are governed by the **LTX-2 Community License Agreement** (dated January 5, 2026), |
| included in full as [`LICENSE`](LICENSE) in this repository. Mirroring does not alter, relax, or |
| re-license anything. |
|
|
| Two obligations deserve to be called out explicitly, because they are easy to miss and they bind |
| *you* as a user of these weights, not just us as a distributor: |
|
|
| 1. **Use-based restrictions (paragraph 4 and Attachment A) apply in their entirety.** Attachment A |
| is an enforceable part of the licence and lists prohibited uses. You must comply with it, and |
| you must require the same of anyone you distribute to. |
| 2. **Attachment A item 20 is a non-compete.** Using LTX-2 or its derivatives in a product or |
| service that competes with, replaces, or substitutes Lightricks' commercial offerings requires |
| a separate commercial licence from Lightricks. There is also a revenue threshold in the |
| agreement's commercial terms. If you are building a product, read the licence yourself rather |
| than relying on this summary. |
|
|
| Any redistribution of these weights or derivatives of them must carry a complete copy of the |
| agreement and propagate these terms (§3). This summary is a courtesy pointer, **not** a substitute |
| for the licence text, and where the two differ the licence governs. |
|
|
| ## Verified file hashes (SHA-256) |
|
|
| Each matches the corresponding file at `dgrauet/ltx-2.3-mlx` as of 2026-08-03: |
|
|
| ``` |
| 442119db8eaf976f83a105cc8c5f2c930e0f625062f9776b10adcdb7bc96c416 audio_vae.safetensors |
| 5885c2bd7af4e761b3257cf5b17bc1fdb2d187cea3ca520ea723b6a129b7029f connector.safetensors |
| 755f69dcb8a3f9589045925eb4a2237e9969f9c026a016393bc395e65ebd5788 spatial_upscaler_x2_v1_1.safetensors |
| bd5c649bb658107ac73d39a9123a313c55630d3e2b7b78a5bd7d52ea782cac0e transformer-distilled.safetensors |
| f404026fe0b59418eaec4a3fcdc474125c798f0b787dc390f6eb4e79934d4160 vae_decoder.safetensors |
| 1512f5ef8387901db0baecb328690676e2667ddf2b63e28f8e6645188c1a8c06 vae_encoder.safetensors |
| 410cee86c14f76956bf487d153211ef15050fe8bf51f86d47a1d27ca6e3ba287 vocoder.safetensors |
| ``` |
|
|
| ## Credit |
|
|
| All model design, training, and weights are the work of **Lightricks**. The MLX conversion and |
| the accompanying inference pipeline are the work of **dgrauet**. This mirror contributes nothing |
| but disk space and an address that we can promise not to move. |
|
|
