Downloads · 30 days
77
41% of all-time downloads
xocialize/ltx-2.3-mlx
ltx-2.3-mlx is a image-to-video model from xocialize. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as other.
A verbatim availability mirror. Full-precision LTX-2.3 components (connector, video/audio VAEs, vocoder, spatial upscaler) plus the bf16 distilled transformer.
Downloads · 30 days
77
41% of all-time downloads
All-time downloads
187
Public
Repo size
48.5 GB
Likes
0
Public
Click a slice to open those files.
.safetensors48.5 GB · 100%
From the Hugging Face model README
A verbatim availability mirror. Full-precision LTX-2.3 components (connector, video/audio VAEs, vocoder, spatial upscaler) plus the bf16 distilled transformer.
This is an unmodified mirror of 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.
| Stage | Who | What |
|---|---|---|
| Original weights | 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; published as dgrauet/ltx-2.3-mlx alongside the 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.
These weights are governed by the LTX-2 Community License Agreement (dated January 5, 2026),
included in full as 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:
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.
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
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.