Primary sources last checked on 13 Nov 2026. Verification freshness is tracked separately from factual change, and unknown values remain explicit rather than inferred.
NotableCurrent top-tier open-weight video family on the Artificial Analysis video leaderboard.Curation method →
Open Model Weights records LTX-2.5 as a Pending verification-parameter image to video open-weight model in the LTX-2.5 family, with Lightricks listed as the developer. The checked source repository provides 14 recognized weight artifacts, format evidence for Safetensors and a context window that is not declared in the checked standard sources. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.
The repository declares other. Commercial-use classification requires license-specific review. Open Model Weights reports the checked license evidence and classification; this is not legal advice.
No base model is declared in the checked standard lineage metadata, so Open Model Weights does not infer one. Training recipe status: training-described-in-model-card; data disclosure status: not-disclosed-in-standard-metadata-or-obvious-model-card-section.
LTX-2.5 is video-generation family with image-to-video, text-to-video and audio-related pipeline metadata. OMW checked the public source repository for Parameter total not declared in checked metadata, available weight artifacts without a verified text-style context window, and a other license declaration. The current checked record lists Safetensors files but does not expose a reliable universal parameter total or text-model context window. Those fields should stay unknown rather than become guessed deployment specifications. Its Notable badge is a separate editorial discovery signal, not a performance measurement by OMW.
Primary technical focusvideo-generation family with image-to-video, text-to-video and audio-related pipeline metadataSource ↗
Weight metadataParameter total not declared in checked metadataSource ↗
Checked context evidenceNot disclosed as a text-model context length in checked sourcesSource ↗
Runtime evidence classPublisher/source mentions only; no OMW execution testSource ↗
WHY IT MATTERS
The source repository tags include multiple video, audio and mixed-media workflows. The canonical pipeline classification is image-to-video; a workflow tag alone is not proof of tested output quality or a supported public API.
LTX-2.5 deserves evaluation for video-generation workflows with flexible conditioning. Its operational envelope should be compared by output frame count, resolution, audio coupling and video continuity, not against text-model context lengths.
MODEL-SELECTION VIEW
Strong fit when…
LTX-2.5 deserves evaluation for video-generation workflows with flexible conditioning. Its operational envelope should be compared by output frame count, resolution, audio coupling and video continuity, not against text-model context lengths.
Evaluations that require video-generation family with image-to-video, text-to-video and audio-related pipeline metadata and an inspectable original weight/source revision.
Important considerations
The recorded license ID is custom/other and commercial use remains unknown. Model-family shorthand does not establish rights for this exact checkpoint.
Reproduce a documented video workflow with versioned nodes, record rendered seconds versus wall time and check audio/video outputs for each distinct advertised mode.
Architecture and task-specific behavior
The source repository tags include multiple video, audio and mixed-media workflows. The canonical pipeline classification is image-to-video; a workflow tag alone is not proof of tested output quality or a supported public API.
The current checked record lists Safetensors files but does not expose a reliable universal parameter total or text-model context window. Those fields should stay unknown rather than become guessed deployment specifications.
Verified configuration versus usage claims
The primary registry record identifies LTX-2.5 as Image To Video. No text-style maximum context is established in the checked source record. Do not import context lengths from unrelated language models into this modality. This page treats a checked config field, the model-card prose and a deployment benchmark as three distinct kinds of evidence.
In the current checked snapshot, Parameter total not declared in checked metadata are recorded with a source repository revision. Those weight-parameter values do not determine how much GPU memory, active compute or KV-cache is required by a real application; sparse activation, quantization and runtime overhead each need separate verification.
What the actual weight repository contains
OMW checked 14 recognized weight artifacts in Safetensors format. The Parameter total not declared in checked metadata come from the published repository data, not from a newly executed OMW performance test. A file count is not a checksum audit, a full weight-binary comparison or a statement about throughput.
The source revision and exact listed weight files can be inspected through the linked OMW evidence API and the official model repository. Before distributing or deploying a model, pin the precise commit and independently validate downloaded artifact checksums where available. An upstream revision change must not automatically be described as changed weight bytes.
License and intended commercial deployment
The model's license is recorded as other, with commercial use unknown or requiring individual assessment. Public downloadable files do not confer permission for every commercial deployment.
The recorded license ID is custom/other and commercial use remains unknown. Model-family shorthand does not establish rights for this exact checkpoint. Keep publisher license declarations separate from third-party interpretations, custom usage agreements and any deployment-specific regulatory obligations. Where a permission is unknown, the registry intentionally reports unknown rather than guessing a permissive answer.
Runtime, hardware and reproduction limits
The source record includes diffusion-single-file, ComfyUI, Diffusers, Transformers as declared libraries or model-card mentions. This is provenance-aware compatibility information only: OMW has not executed a model load, generated outputs or benchmarked the exact checkpoint on a specified GPU. Runtime support for a particular version, precision and processor remains to be tested.
Reproduce a documented video workflow with versioned nodes, record rendered seconds versus wall time and check audio/video outputs for each distinct advertised mode. The generic weight-only memory estimate in the model snapshot does not include multimodal processors, activation buffers, temporary tensors, cache growth, device placement or kernel availability; these can dominate real deployments.
When to choose this model and how to compare it
LTX-2.5 deserves evaluation for video-generation workflows with flexible conditioning. Its operational envelope should be compared by output frame count, resolution, audio coupling and video continuity, not against text-model context lengths.
For a fair comparison, choose another model from the same task family and freeze the task dataset, prompt or preprocessing settings, tested checkpoint revisions and compute budget. The recorded license ID is custom/other and commercial use remains unknown. Model-family shorthand does not establish rights for this exact checkpoint. A Leading or Notable label remains a discovery cue rather than a universal model ranking or an OMW benchmark result.
IMPLEMENTATION & EVALUATION
How to evaluate LTX-2.5 before deployment
Use these as proposed acceptance tests rather than OMW-confirmed performance results. The objective is to establish whether the exact LTX-2.5 revision is legal to use and deployable for a specific workload.
STEP 01
Freeze model artifacts and license evidence
Record the official LTX-2.5 repository SHA, recognized Safetensors artifacts and the other license evidence before attempting an installation.
REPRODUCIBLE ACCEPTANCE TEST
An immutable source revision, artifact manifest, checksums where available and dated license record are saved together.
WHAT CAN GO WRONG
Mutable model branches or unreviewed third-party weight conversions can silently change the experiment or applicable terms.
STEP 02
Reproduce the documented task interface
The source repository tags include multiple video, audio and mixed-media workflows. The canonical pipeline classification is image-to-video; a workflow tag alone is not proof of tested output quality or a supported public API.
REPRODUCIBLE ACCEPTANCE TEST
The intended Image To Video workload runs under a documented processor or tokenizer path with exact dependency versions, or the failure is recorded.
WHAT CAN GO WRONG
The recorded license ID is custom/other and commercial use remains unknown. Model-family shorthand does not establish rights for this exact checkpoint.
STEP 03
Measure deployment and model-specific outputs
Reproduce a documented video workflow with versioned nodes, record rendered seconds versus wall time and check audio/video outputs for each distinct advertised mode.
REPRODUCIBLE ACCEPTANCE TEST
Raw evaluation inputs, response or media outputs, memory high-water mark, request latency and error logs are retained and the environment can be reconstructed.
WHAT CAN GO WRONG
Publisher benchmark claims and parameter-derived estimates are not interchangeable with measurements on the chosen hardware.
STEP 04
Compare against a relevant verified alternative
LTX-2.5 deserves evaluation for video-generation workflows with flexible conditioning. Its operational envelope should be compared by output frame count, resolution, audio coupling and video continuity, not against text-model context lengths.
REPRODUCIBLE ACCEPTANCE TEST
Run the same tasks and quality rubric against MiniMax-H3 and Qwen-Image-2.1, with source revisions and test limitations disclosed.
WHAT CAN GO WRONG
A different license, modality, processor or sampling budget makes a naive head-to-head score misleading.
LTX-2.5 is video-generation family with image-to-video, text-to-video and audio-related pipeline metadata. The source repository tags include multiple video, audio and mixed-media workflows. The canonical pipeline classification is image-to-video; a workflow tag alone is not proof of tested output quality or a supported public API.
What is the verified context length for LTX-2.5?
No text-style maximum context is established in the checked source record. Do not import context lengths from unrelated language models into this modality.
How big are the published LTX-2.5 weights?
Parameter total not declared in checked metadata; 14 recognized repository weight entries (Safetensors). This is a weight-metadata observation, not a GPU memory measurement.
Can LTX-2.5 be used commercially?
The model's license is recorded as other, with commercial use unknown or requiring individual assessment. Public downloadable files do not confer permission for every commercial deployment.
Which inference runtimes support LTX-2.5?
The checked model documentation mentions diffusion-single-file, ComfyUI, Diffusers, Transformers. OMW has not run this checkpoint under those runtimes; compatibility must be reproduced for the selected revision.
How should LTX-2.5 be benchmarked?
Reproduce a documented video workflow with versioned nodes, record rendered seconds versus wall time and check audio/video outputs for each distinct advertised mode. Keep environment, source commit, data and evaluation method fixed, and distinguish publisher results from your own repeatable tests.
DIRECT ANSWERS · DATED PRIMARY-SOURCE EVIDENCE
What changed in LTX-2.5?
Questions answered from the retained evidence diff, not inferred performance or release claims.
What changed in LTX-2.5 on 2026-10-11?
Open Model Weights observed a repository revision change for LTX-2.5 on 2026-10-11: 2356ce76915d → 49b093a39c19. The retained comparison records hub.last_modified, hub.sha. A changed repository revision does not by itself establish new weight bytes, a changed license or improved model quality.
Did the observed LTX-2.5 change prove new weights or licensing?
The retained comparison includes no weight-file field change and no license evidence field change. This describes only fields checked and retained by OMW, not a binary-integrity proof or legal conclusion.
How can the LTX-2.5 change history be verified?
The LTX-2.5 model history retains the observation date, compared repository SHAs, field-level before/after evidence, and the source repository link. Use the evidence JSON for a machine-readable record; unobserved states are not reconstructed.
Weight artifacts14 recognized artifacts · public access
03
License declarationotherMetadata declaration
04
Latest published source check
Repository SHA 49b093a39c19…; a source check is not an inference benchmark or legal clearance. See the per-model evidence JSON for the exact source record.
A verification check does not pretend the model changed. Open Model Weights updates the verification date after a real primary-source check, while factual-update dates move only when retained source evidence changes.
Classification describes the checked license terms; it is not legal advice.
03 · HARDWARE
Weight-memory estimate
BF16 / FP16—
FP8 / INT8—
INT4—
Total parameter count unavailable.
04 · FORMATS
Formats & precision evidence
Safetensors
BF16: observedFP16: not observedFP8: not observedINT8: observedINT4: not observedGGUF: not observed
“Not observed” means no matching repository artifact/name/dtype signal was found; it does not prove no third-party conversion exists.
05 · LINEAGE
Base model & family
FamilyLTX-2.5
VariantLTX-2.5
Declared base modelNot declared in model-card metadata
RelationNot declared
06 · TRAINING ASSETS
Recipe & data disclosure
Training recipetraining-described-in-model-card
Data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
EvaluationsNot classified by automated verifier
Intermediate checkpointsNot classified by automated verifier
07 · RUNTIME SUPPORT
Declared, mentioned and externally evidenced runtimes
Declared librarydiffusion-single-file
Declared/taggeddiffusion-single-file
Mentioned in model cardComfyUI, Diffusers, Transformers
Artifact signalsNone
External primary runtime evidenceNone
Tested by Open Model WeightsNo — source-derived support only
Open Model Weights separates model-repository evidence from external runtime-release evidence. An external support statement does not change the official model repository's weight formats and does not imply an Open Model Weights inference benchmark.
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Registry record created
Previous verification level: discovered-pending.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Registry record created
Previous verification level: discovered-pending.
licenseverified
commercial useunknown
contextnot-disclosed
weight filesverified
formatsverified
base modelnot-declared
training recipetraining-described-in-model-card
data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
runtime supportsource-derived-not-runtime-tested
MODELS FOR AI AGENTS · ROLE EVIDENCE
Where this model fits in an agent system
Video generation. A potential media-processing tool invoked by a separate controller; image/video/speech generation is not agent autonomy.
The curated notable tier is not an agent-readiness rating. Model-specific tool-call success, long-horizon task accuracy and compatible runtime configurations are not independently established here.
Source-linked license: other (unknown commercial-use classification; see original terms).