Model reference · open weights
LTX2.3-ICEd-Insight is an open-weight video model from joyfox, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
LTX2.3-ICEdit-Insight LTX2.3-ICEdit-Insight is a task-aware video restoration and editing model family developed by JoyFox Lab, built on top of the LTX-2.3 DiT-based audio-video foundation model. This release focuses on four practical video editing directions: - Video Restoration: degradation recovery, compression cleanup, blur and noise reduction, and damaged detail restoration. - Video HD Enhancement: super-resolution, detail reconstruction, texture sharpening, and perceptual quality improvement. - Watermark Removal: logo cleanup, semi-transparent overlay removal, and occlusion-aware background reconstruction. - Subtitle Removal: hard subtitle removal, caption cleanup, text overlay removal, and temporally stable inpainting. Unlike conventional frame-level enhancement pipelines, this model family operates as a generative video restoration system in latent video space. It is designed to preserve global structure, camera motion, object identity, and temporal consistency while reconstructing missing or degraded visual content. Project links: GitHub project | JoyFox on Hugging Face | Paper (Research Square) | DOI 📄 Paper - Title: LTX-Insight: Unified Video Restoration and Semantic Editing via Task-Aware Adaptation and Temporal Consistency - Authors: Fan Tang, Siyuan Li - Venue: Research Square - Posted date: May 25, 2026 - DOI: 10.21203/rs.3.rs-9775063/v1 - Paper URL: https://www.researchsquare.com/article/rs-9775063/v1 This model release corresponds to the paper's unified video post-processing framework built around three high-level settings: video super-resolution/enhancement, occlusion removal and repair, and instruction-driven semantic editing. In the currently released inference package, those ideas are exposed through four practical routes: - Video Restoration - Video HD Enhancement - Watermark Removal - Subtitle Removal The paper introduces three core components: - TADA (Task-Aware Decoupled Adapter) for separating structure restoration from texture/semantic editing under a shared backbone. - FGLC (Flow-Guided Latent Consistency) for explicit temporal consistency modeling in latent space using optical-flow alignment and cross-frame attention bias. - PMTR (Pr
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | joyfox |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | diffusers |
| Based on | Lightricks/LTX-2.3 |
| Released | 2026-04-23 |
| Popularity | 49k downloads / month |
| Likes | 169 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| LTX2.3-ICEdit-Insight | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys ltx2-3-iced-insight for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ltx2-3-iced-insight below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"ltx2-3-iced-insight","prompt":"a drone shot over a forest"}'
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore