> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs-dev.ltx.io/open-source-model/vfx-post-production/native-resolution/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-dev.ltx.io/_mcp/server. # Native Resolution > Use the LTX-2.5 Tiled Fusion workflow in ComfyUI for a full-frame composition pass followed by a tiled pass at the selected output size. Native Resolution is a two-stage LTX-2.5 video-to-video workflow. The first stage resizes the source video to the selected initial canvas and establishes the composition and selected IC-LoRA effect with the full frame in context. The second stage enlarges the latent to the selected output size, attaches the source video as a guide at that size, and applies the effect across overlapping tiles with Tiled Fusion. Tiled Fusion processes a canvas larger than an IC-LoRA's trained window as overlapping spatial crops, then blends the stepped crops back into one shared latent canvas. It is used in the second stage of the Native 4K/8K workflow; it does not replace the initial full-frame composition pass. The workflow is designed for a single-GPU path. Memory use and runtime still depend on the output canvas, tile size, temporal window, model stack, and decode settings, so benchmark the intended configuration on the target hardware. This is different from independently generating tiles and stitching completed results. The tiles share one latent canvas and one noise field throughout sampling, which helps reduce discontinuities between regions. Always inspect tile boundaries and low-frequency gradients across the full clip. > **Warning** > > Full HD, 4K, and 8K are available in the workflow's size selector, but the selector is not a performance guarantee. Test the target resolution, runtime, and peak VRAM on your hardware before committing a full clip. > **Note** > > [`LTXVTiledSampler`](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/tiled_sampler.py) samples and blends tiles independently. It is not the `LTXVTiledFusionSampler` described on this page and cannot be substituted into this workflow. ## When to use Native Resolution Use this workflow when: * You want a full-frame composition pass before applying an IC-LoRA effect at a larger output size. * The output canvas is larger than the IC-LoRA's trained spatial window. * Full-canvas sampling would exceed available VRAM. * You need overlapping regions to participate in the same denoising trajectory. Do not use Tiled Fusion merely to reduce VAE decode memory. For that task, use `LTXVTiledVAEDecode` or `LTXVSpatioTemporalTiledVAEDecode` after sampling. ## Example workflow The published LTX-2.5 workflow uses Load Models, Inputs, Preprocess, Generate, and Decode subgraphs. A **Get Tiling Sizes** node in **Preprocess** sets the tile and output sizes. | Workflow | What it does | | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | | [`LTX-2.5_V2V_TiledFusion_Native_4K_8K.json`](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/2.5/LTX-2.5_V2V_TiledFusion_Native_4K_8K.json) | The Native Resolution ladder: a full-frame composition pass at the initial canvas size, then a tiled pass at the selected output size. | ### The Native Resolution ladder (Native 4K/8K) `LTX-2.5_V2V_TiledFusion_Native_4K_8K.json` runs two stages: 1. **Composition** — the source is resized to `initial_canvas_size`, and a full-frame pass establishes the composition and selected IC-LoRA effect. 2. **Native-resolution pass** — the latent is enlarged with `ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors` (twice for the 8K path), then Tiled Fusion applies the effect across spatial tiles. The original clip is resized to the output size and attached as the stage-2 guide. The workflow exposes IC-LoRA selection for both stages so you can use the effect required by the shot. Keep each adapter matched to the LTX-2.5 model stack, and use the adapter's model card to confirm its supported input and training resolution. The spatial upscaler is available from the [LTX-2.5 model repository](https://huggingface.co/Lightricks/LTX-2.5/tree/main/latent_upscale_models). Use the workflow's **Model Links** note for the rest of the version-matched model stack. The source audio is encoded and held fixed during generation, then decoded and muxed into the saved output video. ### Output sizes The **Get Tiling Sizes** node emits model-legal canvases (dimensions in multiples of 32, frame count `8k+1`) from three presets: * `tile_size` — `qHD`, `HD`, or `FullHD`. The spatial tile the fusion sampler steps. Match it to the IC-LoRA's training bucket when known. If the bucket is unknown, start with `qHD` or another size below HD, then validate the result. * `initial_canvas_size` — the stage-1 composition canvas. * `output_size` — `FullHD`, `4K`, or `8K`. ## Supported surface and version | Surface | Support | | ------------- | ----------------------------- | | ComfyUI | LTX-2.5 Native 4K/8K workflow | | Native Python | Not covered by this workflow | Use only an IC-LoRA and model stack explicitly matched to the selected workflow. Do not infer LTX-2.3 support from the sampler interface or universal LTX-2.5 compatibility from one example. ## Customize safely Start with the Native 4K/8K example workflow and run it unchanged before modifying it. Keep the version-matched model and IC-LoRA together, and match the tile dimensions to the adapter's trained spatial envelope. The workflow contains coordinated guide, sampling, overlap, and streaming settings. Changing one in isolation can produce incompatible conditioning or visible seams. For the `LTXVTiledFusionSampler` interface and implementation constraints, see the [node reference](/open-source-model/integration-tools/ltx-comfy-ui-nodes#ltxvtiledfusionsampler). For longer clips, keep the temporal-window setting synchronized between the IC-LoRA guide and sampler so each window is encoded with the correct local context. Do not slice a whole-clip guide by hand. ## Output and decoding The sampler returns one latent canvas. Decode it with the VAE required by the version-matched workflow. Tiled sampling and tiled VAE decoding solve different memory problems: * **Tiled Fusion sampling** divides the diffusion-model work across overlapping canvas regions at every denoising step. * **Tiled VAE decoding** divides only the conversion from the completed latent into pixels. Using tiled VAE decoding does not turn a standard workflow into the Tiled Fusion workflow. ## Limitations * Full HD, 4K, and 8K are available in the size selector. Higher resolutions require more memory and runtime; benchmark the target resolution on the production hardware. * This guide documents the ComfyUI workflows, not a native Python path. * Tile overlap reduces boundary risk but does not prove that every output will be seam-free. * Large canvases still require memory for the shared latent canvas, noise field, conditioning, and decoded output. * Tiled Fusion does not replace an untiled composition pass when an adapter must establish a new global look across a canvas far beyond its trained window. ## Before production use 1. Run the selected workflow unchanged. 2. Verify that the model, IC-LoRA, and workflow target the same LTX version. 3. Test the intended output resolution on the target hardware. 4. Inspect structured edges, low-frequency gradients, motion, and tile boundaries through the full clip. 5. Record the workflow revision, adapter, sampler, tile settings, VRAM, runtime, and output resolution. ## Related pages * [LTX ComfyUI Nodes](/open-source-model/integration-tools/ltx-comfy-ui-nodes) * [Using ComfyUI with LTX](/open-source-model/integration-tools/comfy-ui) * [IC-LoRA](/open-source-model/usage-guides/ic-lo-ra) > Use the LTX-2.5 Tiled Fusion workflow in ComfyUI for a full-frame composition pass followed by a tiled pass at the selected output size.