Views
No views yet
ComfyUI-LTX2.5-MSR — this repo just packages it into a clean, organized workflow with subgraphs, shared controls, and a stage-2 bypass toggle so it's easier to pick up and use.pic1–pic4 + background) blended into one generated video via learned MSR slot embeddings.Fast Groups Bypasser switch (via rgthree-comfy). Turn it off for quick previews, on for final renders.FPS, DURATION, and the two prompt fields (global_prompt reference descriptions + local_prompts action/narrative) are each set once and shared across both stages using Set/Get nodes, so nothing gets out of sync between stage 1 and stage 2.custom_nodes/:ComfyUI-LTX2.5-MSR — MSR LoRA loader + multi-reference guide nodesComfyUI-PromptRelay — prompt relay / temporal segment text encodingComfyUI-KJNodes — constants + Set/Get utility nodesrgthree-comfy — Fast Groups Bypasser (stage 2 toggle)ComfyUI-VideoHelperSuite — video combine/export| Type | Folder | Notes |
|---|---|---|
| LTX-2.5 diffusion model (UNET) | diffusion_models/ | distilled variant recommended for speed |
| LTX-2.5 text encoder (CLIP) | text_encoders/ | Gemma-based, per official LTX-2.5 release |
| LTX-2.5 video VAE | vae/ | |
| LTX-2.5 audio VAE | vae/ | |
| MSR LoRA | loras/ | must contain reference_slot_embedding weights — a normal LoRA will be rejected |
| LTX-2.5 latent spatial upscaler (x2) | latent_upscale_models/ | only needed if you use Stage 2 |
PIC 1–PIC 4 / Background Load Image nodes (any of pic2–pic4/background can be left empty — the MSR guide skips missing optional references).FPS and DURATION (in seconds) — video length is computed automatically.Fast Groups Bypasser node and flip the "Stage 2 Upscale" toggle off — only the fast base pass will render. Flip it back on for the full dual-stage render.--disable-pinned-memory if you get OOM errors that look inconsistent with the reported VRAM usage — pinned-memory allocation can be unreliable on some systems.DURATION (fewer frames = much lower memory for the upscale pass, since attention/FFN activations scale with frame count).use_tiled_encode on the MSR Multi-Reference Guide nodes and set a reasonable tile_overlap if you're still tight on memory.