> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs-dev.ltx.io/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-dev.ltx.io/_mcp/server. # Refine & Restore > Restore damaged archive footage and rebuild fine detail with LTX IC-LoRAs and the LTX-2.5 Tiled Fusion Upscale workflow in ComfyUI. Refine & Restore combines two generative video-to-video tools: * **Restore** cleans and colorizes damaged archive footage, including low-resolution transfers, compressed broadcast video, tape, sepia, and black-and-white film scans. * **Refine Details** rebuilds fine texture, edges, and grain in soft, compressed, generated, or upscaled footage. Both adapters use the LTX-2.5 [`LTX-2.5_V2V_TiledFusion_Upscale.json`](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/2.5/LTX-2.5_V2V_TiledFusion_Upscale.json) workflow. For damaged archive footage, run Restore first and Refine Details second. > **Warning** > > These are generative tools. They synthesize plausible color and detail; they do not recover the source pixel-for-pixel. Treat rebuilt objects, lettering, faces, and colors as generated interpretations, especially when the input contains little usable information. ## Choose a path | Source | Path | | --------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | | Soft, compressed, generated, or conventionally upscaled video that already has usable color and structure | Run **Refine Details**. | | Damaged, low-resolution, sepia, or black-and-white archive footage | Run **Restore**, then optionally run **Refine Details** for delivery resolution. | | Clean cinema raw or footage whose original grain must be preserved | Refine Details may denoise original grain. Plan to reintroduce grain after refinement if preservation matters. | ## Prerequisites * A current ComfyUI installation with the LTX video nodes required by the workflow, including `LTXVTiledFusionSampler` and `LTXVGetTilingSizes`. * The LTX-2.5 distilled model stack selected by the workflow. * The adapter for the selected path, placed in `ComfyUI/models/loras/`. ## Model files The Tiled Fusion Upscale workflow uses the following LTX-2.5 model stack: | File | Role | Placement | | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- | ---------------------------------- | | `ltx-2.5-22b-distilled-transformer-bf16.safetensors` | LTX-2.5 distilled transformer | `ComfyUI/models/diffusion_models/` | | `gemma4-12b-with-proj-ltx-2.5-bf16.safetensors` | LTX-2.5 text encoder | `ComfyUI/models/text_encoders/` | | `gemma4_e2b_it_bf16.safetensors` | Optional local prompt enhancer | `ComfyUI/models/text_encoders/` | | `ltx-2.5-video-vae-bf16.safetensors` | Video VAE | `ComfyUI/models/vae/` | | `ltx-2.5-audio-vae-bf16.safetensors` | Audio VAE used to preserve the source audio track | `ComfyUI/models/vae/` | | [`ltx-2.5-22b-ic-lora-refine-details-1.0.safetensors`](https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details/blob/main/ltx-2.5-22b-ic-lora-refine-details-1.0.safetensors) | Refine Details adapter | `ComfyUI/models/loras/` | | [`ltx-2.5-22b-ic-lora-restore-1.0.safetensors`](https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Restore/blob/main/ltx-2.5-22b-ic-lora-restore-1.0.safetensors) | Restore adapter | `ComfyUI/models/loras/` | The published workflow selects Refine Details. To run Restore, select the Restore adapter in **Load Models** while keeping the LTX-2.5 distilled stack. Restore was trained on LTX-2.3 and its model card documents testing on the unchanged weights with the LTX-2.5 distilled transformer, video VAE, and Gemma-4 text encoder. ## Refine Details Use Refine Details when the source composition and color are already usable but fine detail is soft or missing. ### Run the workflow 1. Load [`LTX-2.5_V2V_TiledFusion_Upscale.json`](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/2.5/LTX-2.5_V2V_TiledFusion_Upscale.json) in ComfyUI. 2. In **Load Video**, select the clip to refine. 3. Confirm **Load Models** selects `ltx-2.5-22b-ic-lora-refine-details-1.0.safetensors`. 4. In **Preprocess → Get Tiling Sizes**, choose the output size. The workflow resizes the clip to that canvas before attaching it as the IC-LoRA guide. 5. Enter a prompt about the rendering only: sharpness, texture, grain, lighting, palette, or grade. Do not name specific objects, people, or props; every spatial tile receives the complete prompt, so named content can be repeated across tiles. 6. Run the workflow and inspect fine detail, text, faces, structured edges, and tile boundaries through the full clip. The adapter is trained for a `1024 × 576` working tile and should use the tiled workflow even for a full-HD canvas. Larger canvases remain one shared latent and noise field; overlapping crops are fused after every denoising step. > **Note** > > The workflow offers an 8K output selection, but the Refine Details model card recommends a progressive path: refine to 4K first, resize that result to 8K with Lanczos, then apply an optional gentle second pass. A direct 8K pass can invent or rearrange texture because each tile sees content at a larger scale than the adapter's training window. ## Restore archive footage Use Restore for damaged archive sources that need cleanup, reconstruction, or inferred color before detail refinement. ### Prepare the source * Do not denoise or sharpen the source first. * Preserve the source aspect ratio. Do not stretch 4:3 footage to 16:9. * Use a canvas whose width and height are multiples of 32 and a frame count of the form `8n+1`. ### Run the restoration pass 1. Load the Tiled Fusion Upscale workflow and select the archive clip in **Load Video**. 2. In **Load Models**, replace the Refine Details adapter with `ltx-2.5-22b-ic-lora-restore-1.0.safetensors`. 3. Open **Preprocess** and set a custom working canvas for the source aspect ratio. The Restore model card recommends `1440 × 1056` or `1440 × 1088` for 4:3 material and `1920 × 1088` for 16:9 material, using a `960 × 544` sampling tile. 4. Describe the period, place, lighting, materials, clothing, and intended natural color in the positive prompt. Put modern objects, logos, signage, lettering, or anything else the model must not invent in the negative prompt. 5. Run the workflow and review color consistency, faces, lettering, period details, and reconstructed low-information regions. Restore is a valid result on its own. For a 4K-class delivery, run the restored output through the same workflow again with Refine Details selected, a `1024 × 576` sampling tile, and the 4K output size. The order matters: refining first can sharpen the damage and reduce color. ## How the workflow handles video The source video is resized to the output canvas and attached as an IC-LoRA guide at downscale factor 1. Tiled Fusion runs overlapping spatial crops within one shared latent canvas and merges them during every denoising step. The published workflow uses streaming guide windows for longer clips. The source audio is held fixed during generation, decoded with the audio VAE, and muxed into the saved video at the source frame rate; neither adapter is trained to generate new audio. For the full sampler contract and settings, see [`LTXVTiledFusionSampler`](/open-source-model/integration-tools/ltx-comfy-ui-nodes#ltxvtiledfusionsampler) in the nodes reference. For adapter-specific advanced techniques—including placed reference images and chained temporal windows—see the [Refine Details](https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details) and [Restore](https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Restore) model cards. ## Limitations * Restore infers color and missing structure from the source and prompt. Period-plausible content is not necessarily recovered historical truth. * Refine Details rebuilds texture; it does not guarantee pixel-accurate restoration, faithful lettering, identity preservation, or artifact removal. * Full HD, 4K, and 8K are available in the workflow selector, but higher resolutions increase memory use and runtime. Test the target size and full clip on the production hardware. * Both adapters are designed for tiled use at their trained spatial windows. A single untiled full-HD pass places them outside those training buckets. * This guide documents the ComfyUI workflow. Do not infer a native Python path from the graph. ## Related pages * [Native Resolution](/open-source-model/vfx-post-production/native-resolution) * [LTX ComfyUI Nodes](/open-source-model/integration-tools/ltx-comfy-ui-nodes) * [IC-LoRA](/open-source-model/usage-guides/ic-lo-ra) * [Prompting guide](/open-source-model/usage-guides/prompting-guide)