{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiggrciv23f4xcjv2454o5gxnt3d6iwttn2qgxrwbilzgytnyoyxkm",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mmog4vme6fr2"
  },
  "path": "/t/which-model-can-be-used-to-produce-lego-style-videos/176189#post_2",
  "publishedAt": "2026-05-25T11:27:01.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "Remade-AI/Lego",
    "lego_35_epochs.safetensors",
    "wan_txt2vid_lora_workflow.json",
    "Remade-AI/Lego — Lego-style Wan2.1 14B T2V LoRA",
    "Official ComfyUI Wan2.1 examples",
    "ComfyUI docs: Wan2.1 Video Examples",
    "Comfy-Org/Wan_2.1_ComfyUI_repackaged",
    "Kijai/ComfyUI-WanVideoWrapper"
  ],
  "textContent": "There seems to be a usable LoRA for this:\n\n* * *\n\nThe most practical open-source-ish route I found is probably **ComfyUI + Wan2.1 14B T2V + a Lego-style LoRA** , rather than looking for a hosted HF Space that already does it.\n\nThe relevant LoRA is:\n\n  * Remade-AI/Lego\n\n\n\nIt is described as a **“Lego Style LoRA for Wan2.1 14B T2V”**. The model card says it is trained on the **Wan2.1 14B T2V** base model, and it includes:\n\n  * the LoRA file: lego_35_epochs.safetensors\n  * a ComfyUI workflow: wan_txt2vid_lora_workflow.json\n  * a trigger phrase\n  * example prompts\n  * suggested settings\n\n\n\nThe trigger phrase is:\n\n\n    l3g0_5ty13 Lego animation style\n\n\nThe model card’s recommended starting settings are:\n\n\n    LoRA Strength: 1.0\n    Embedded Guidance Scale: 6.0\n    Flow Shift: 5.0\n\n\nSo I would start from the workflow on the LoRA page itself, then use the general Wan2.1 ComfyUI setup notes from the ComfyUI examples.\n\nUseful links:\n\n  * Remade-AI/Lego — Lego-style Wan2.1 14B T2V LoRA\n  * Official ComfyUI Wan2.1 examples\n  * ComfyUI docs: Wan2.1 Video Examples\n  * Comfy-Org/Wan_2.1_ComfyUI_repackaged\n  * Kijai/ComfyUI-WanVideoWrapper\n\n\n\nA rough ComfyUI path would be:\n\n  1. Update ComfyUI.\n  2. Set up Wan2.1 T2V in ComfyUI.\n  3. Use the workflow from the `Remade-AI/Lego` model page.\n  4. Put the Wan diffusion model, text encoder, VAE, and LoRA in the expected ComfyUI model folders.\n  5. Start prompts with the trigger phrase: `l3g0_5ty13 Lego animation style`.\n\n\n\nThe ComfyUI Wan examples say the Wan diffusion models go here:\n\n\n    ComfyUI/models/diffusion_models/\n\n\nThe common Wan2.1 supporting files are usually placed like this:\n\n\n    ComfyUI/models/text_encoders/\n    ComfyUI/models/vae/\n    ComfyUI/models/clip_vision/\n\n\nFor the LoRA, use the LoRA path expected by your workflow / custom nodes. In a normal ComfyUI LoRA setup, this is usually something like:\n\n\n    ComfyUI/models/loras/\n\n\nIf using Kijai’s WanVideoWrapper workflow, follow the node/workflow expectations there, because the Remade model card says their ComfyUI workflow is based on a modified version of Kijai’s Wan Video Wrapper workflow with a Wan LoRA node connected to the base model.\n\nA starting prompt could be:\n\n\n    l3g0_5ty13 Lego animation style, a plastic toy-brick minifigure walking through a miniature brick-built city, glossy plastic surfaces, stop-motion animation look, cinematic lighting, shallow depth of field, smooth camera movement\n\n\nAnother example:\n\n\n    l3g0_5ty13 Lego animation style, a close-up shot of a toy-brick pirate minifigure with a black tricorn hat, eye patch, and red coat, holding a tiny silver cutlass, with a colorful brick-built ocean scene in the background, glossy plastic material, cinematic lighting, shallow depth of field\n\n\nI would treat this mainly as a **text-to-video** route, because the LoRA is specifically for **Wan2.1 14B T2V**. It may or may not behave correctly if you try to use it in an image-to-video workflow without adaptation.\n\nAlso, I did not find a public HF Space that appears to run this exact LoRA out of the box. There are Wan-related Spaces, but the more reliable recommendation here seems to be **ComfyUI using the LoRA workflow from the model card**.\n\nOne caveat: for public/commercial use, it may be safer to describe the intended look as “toy-brick”, “plastic minifigure”, “brick-built”, or “stop-motion toy animation” rather than relying only on the LEGO trademark in user-facing text.",
  "title": "Which model can be used to produce Lego style videos?"
}