Duplicate from FuzzPuppy/LTX-2.3-Foley-Workflow

Co-authored-by: FuzzPuppy <FuzzPuppy@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tennis-no-sound.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,200 @@
+---
+license: apache-2.0
+tags:
+  - comfyui
+  - ltx-video
+  - ltx-2.3
+  - foley
+  - video-to-audio
+  - audio-generation
+  - workflow
+---
+
+# LTX 2.3 Foley V2A ComfyUI Workflow
+
+This repository contains a ready-to-test ComfyUI workflow for the
+[`FuzzPuppy/LTX-2.3-Foley-LoRA`](https://huggingface.co/FuzzPuppy/LTX-2.3-Foley-LoRA)
+LoRA. The LoRA adds Foley sound effects to a silent input video using LTX-2.3:
+given a short video and a prompt describing the visible action, the workflow
+generates matching non-speech, non-music sound effects and saves a new MP4.
+
+The workflow is intentionally small: it takes one short video clip, keeps the
+first `89` frames, generates matching Foley audio, and saves an MP4 with the
+source frames plus generated audio. It is meant as the fastest public ComfyUI
+test for `FuzzPuppy/LTX-2.3-Foley-LoRA`, not as a full long-video stitching
+pipeline.
+
+## Tutorial
+
+[![Watch the tutorial: using the LTX-2.3 Foley LoRA in ComfyUI](https://img.youtube.com/vi/qnHFDlrySmw/hqdefault.jpg)](https://youtu.be/qnHFDlrySmw)
+
+[Watch the tutorial on YouTube](https://youtu.be/qnHFDlrySmw)
+
+## What Is Included
+
+- `ltx_23_foley_v2a.json`: ComfyUI workflow.
+- `setup_runpod_ltx_foley.sh`: one-command RunPod setup script.
+- `ltx_foley_v2a`: small helper-node package.
+- `tennis-no-sound.mp4`: default silent test video for RunPod setup.
+
+The helper-node package handles the workflow-specific pieces that stock ComfyUI
+does not currently cover cleanly:
+
+- freezes the uploaded video as LTX video latents while leaving matching audio
+  latents empty for Foley generation
+- trims or pads the saved video frames to the same generation window
+- decodes LTX audio VAE output into the Comfy audio tensor layout expected by
+  current video saving nodes
+
+Prompt text, model loading, LoRA loading, sampling, video creation, and MP4
+saving use normal ComfyUI/LTXVideo nodes.
+
+## Fastest RunPod Test
+
+Use the official RunPod **ComfyUI - CUDA 12.8** template:
+
+https://console.runpod.io/deploy?template=cw3nka7d08&ref=k7b1cgii
+
+
+1. In RunPod, under "Additional Filters" filter CUDA versions to CUDA 12.8.
+2. Select a 48 GB GPU: A40, RTX A6000, L40/L40S, or A100.
+3. Make sure the `ComfyUI - CUDA 12.8` template is selected.
+4. The template's default volume disk is `50 GB`, which is enough for the core
+   workflow files, but tight once caches and reruns accumulate. Change the volume
+   disk to `100 GB` if you want more breathing room.
+5. Start the pod and open a terminal.
+6. Run:
+
+```bash
+cd /workspace && curl -L https://huggingface.co/FuzzPuppy/LTX-2.3-Foley-Workflow/resolve/main/setup_runpod_ltx_foley.sh -o setup_runpod_ltx_foley.sh && bash setup_runpod_ltx_foley.sh
+```
+
+The setup script installs the nodes and models, downloads the tennis test video
+as `input.mp4`, restarts ComfyUI without stopping the pod, and waits until the UI
+responds on port `8188`.
+
+After the script finishes:
+
+1. Open ComfyUI from the RunPod web UI.
+2. Under workflows, select `ltx_23_foley_v2a.json`.
+3. Hit `Run`.
+
+The default input video and prompt are already set:
+
+```text
+Two men are playing tennis. No speech is present. No music is present.
+```
+
+## What The Script Installs
+
+The script assumes the official CUDA 12.8 template layout from
+`runpod-workers/comfyui-base`:
+
+- ComfyUI: `/workspace/runpod-slim/ComfyUI`
+- Python environment: `/workspace/runpod-slim/ComfyUI/.venv-cu128`
+- ComfyUI port: `8188`
+
+It installs or refreshes:
+
+- `Lightricks/ComfyUI-LTXVideo`
+- `ltx_foley_v2a` helper nodes
+- `ltx_23_foley_v2a.json`
+- `tennis-no-sound.mp4`
+
+It downloads these model files:
+
+- Base checkpoint:
+  [`Lightricks/LTX-2.3-fp8/ltx-2.3-22b-dev-fp8.safetensors`](https://huggingface.co/Lightricks/LTX-2.3-fp8/blob/main/ltx-2.3-22b-dev-fp8.safetensors)
+- Text encoder:
+  [`Comfy-Org/ltx-2/split_files/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors`](https://huggingface.co/Comfy-Org/ltx-2/blob/main/split_files/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors)
+- Foley LoRA:
+  [`FuzzPuppy/LTX-2.3-Foley-LoRA/ltx-2.3-foley-400-steps.safetensors`](https://huggingface.co/FuzzPuppy/LTX-2.3-Foley-LoRA/blob/main/ltx-2.3-foley-400-steps.safetensors)
+
+Large model downloads are SHA-256 verified. Completed files are skipped on
+rerun, interrupted downloads resume from `*.part` files, and corrupt partials
+are retried once from scratch.
+
+## Manual ComfyUI Install
+
+If you are not using the RunPod script:
+
+1. Install or update ComfyUI.
+2. Install the official LTXVideo custom nodes:
+   `https://github.com/Lightricks/ComfyUI-LTXVideo`
+3. Copy or symlink `ltx_foley_v2a` into:
+   `ComfyUI/custom_nodes/ltx_foley_v2a`
+4. Put the model files in:
+   - checkpoint:
+     [`ltx-2.3-22b-dev-fp8.safetensors`](https://huggingface.co/Lightricks/LTX-2.3-fp8/blob/main/ltx-2.3-22b-dev-fp8.safetensors)
+     in `ComfyUI/models/checkpoints`
+   - text encoder:
+     [`gemma_3_12B_it_fp8_scaled.safetensors`](https://huggingface.co/Comfy-Org/ltx-2/blob/main/split_files/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors)
+     in `ComfyUI/models/text_encoders`
+   - Foley LoRA:
+     [`ltx-2.3-foley-400-steps.safetensors`](https://huggingface.co/FuzzPuppy/LTX-2.3-Foley-LoRA/blob/main/ltx-2.3-foley-400-steps.safetensors)
+     in `ComfyUI/models/loras`
+5. Restart ComfyUI.
+6. Under workflows, select `ltx_23_foley_v2a.json`.
+7. Hit `Run`.
+
+## Workflow Defaults
+
+- Input video: `input.mp4`
+- Prompt: `Two men are playing tennis. No speech is present. No music is present.`
+- Negative prompt: anti-music/anti-vocal prompt
+- Conditioning size: `576x576`
+- Frame window: `89` frames
+- Sampling steps: `30`
+- Guidance: `4.0`
+- STG blocks: `14, 19`
+- LoRA strength: `1.0`
+
+The workflow uses the first `89` frames of the uploaded video. Shorter videos are
+padded by repeating the last frame. The saved video is trimmed or padded to the
+same frame count so the output video duration matches the generated audio.
+
+## VRAM Notes
+
+Sampling is the VRAM peak. Start with a 48 GB GPU for the first reliable test.
+If you need to reduce memory use, try these changes in order:
+
+- reduce frames from `89` to `57`, `41`, or `25`
+- reduce conditioning size from `576x576` to `448x448` or `384x384`
+- reduce sampling steps from `30` to `20`
+- lower or disable STG if quality is acceptable
+
+Frame counts should stay one more than a multiple of 8:
+
+```text
+9, 17, 25, 33, 41, 49, 57, ..., 89, ..., 257
+```
+
+## Troubleshooting RunPod Setup
+
+If you rerun setup after a workflow or node update:
+
+```bash
+cd /workspace && bash setup_runpod_ltx_foley.sh
+```
+
+The script will skip verified model files, refresh the workflow/helper nodes,
+and restart ComfyUI.
+
+If model downloads fail with authorization errors, accept the relevant Hugging
+Face model terms and rerun with `HF_TOKEN` set.
+
+Logs from the script-managed ComfyUI restart are written to:
+
+```text
+/workspace/runpod-slim/comfyui-restart.log
+```
+
+## License Scope
+
+The files in this workflow repository are released under the Apache-2.0 license.
+That applies to the workflow JSON, setup script, helper-node code, README/model
+card text, and bundled test assets in this repository.
+
+This workflow downloads and uses third-party model files that are governed by
+their own licenses and terms, including LTX-2.3, the Gemma text encoder, and the
+`FuzzPuppy/LTX-2.3-Foley-LoRA` weights. 

ltx_23_foley_v2a.json

@@ -0,0 +1,1275 @@
+{
+  "last_node_id": 22,
+  "last_link_id": 38,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "LoadVideo",
+      "pos": [
+        -1280,
+        -160
+      ],
+      "size": [
+        320,
+        90
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "video",
+          "type": "VIDEO",
+          "links": [
+            1
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadVideo"
+      },
+      "widgets_values": [
+        "input.mp4"
+      ]
+    },
+    {
+      "id": 2,
+      "type": "GetVideoComponents",
+      "pos": [
+        -920,
+        -160
+      ],
+      "size": [
+        220,
+        120
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "video",
+          "type": "VIDEO",
+          "link": 1
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            2,
+            29
+          ]
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "links": null
+        },
+        {
+          "name": "fps",
+          "type": "FLOAT",
+          "links": [
+            3,
+            30
+          ]
+        },
+        {
+          "name": "bit_depth",
+          "type": "INT",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetVideoComponents"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 3,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        -1280,
+        120
+      ],
+      "size": [
+        360,
+        110
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            6
+          ]
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": null
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            7
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "ltx-2.3-22b-dev-fp8.safetensors"
+      ]
+    },
+    {
+      "id": 4,
+      "type": "LTXVAudioVAELoader",
+      "pos": [
+        -1280,
+        280
+      ],
+      "size": [
+        360,
+        80
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "Audio VAE",
+          "type": "VAE",
+          "links": [
+            8,
+            36
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXVAudioVAELoader"
+      },
+      "widgets_values": [
+        "ltx-2.3-22b-dev-fp8.safetensors"
+      ]
+    },
+    {
+      "id": 5,
+      "type": "LTXAVTextEncoderLoader",
+      "pos": [
+        -1280,
+        420
+      ],
+      "size": [
+        360,
+        120
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            9,
+            10
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXAVTextEncoderLoader"
+      },
+      "widgets_values": [
+        "gemma_3_12B_it_fp8_scaled.safetensors",
+        "ltx-2.3-22b-dev-fp8.safetensors",
+        "default"
+      ]
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": [
+        -850,
+        380
+      ],
+      "size": [
+        420,
+        180
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 9
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            11
+          ]
+        }
+      ],
+      "title": "Positive Prompt",
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "Two men are playing tennis. No speech is present. No music is present."
+      ]
+    },
+    {
+      "id": 7,
+      "type": "CLIPTextEncode",
+      "pos": [
+        -850,
+        600
+      ],
+      "size": [
+        420,
+        160
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 10
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            12
+          ]
+        }
+      ],
+      "title": "Negative Prompt",
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "music, melody, song, singing, vocals, score, soundtrack, beat, rhythm bed, instrumental backing, tinny, thin, harsh, clipped, distorted, low bitrate"
+      ]
+    },
+    {
+      "id": 8,
+      "type": "LTXVConditioning",
+      "pos": [
+        -360,
+        470
+      ],
+      "size": [
+        220,
+        90
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 11
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 12
+        },
+        {
+          "name": "frame_rate",
+          "type": "FLOAT",
+          "link": 3
+        }
+      ],
+      "outputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "links": [
+            13
+          ]
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "links": [
+            14
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXVConditioning"
+      },
+      "widgets_values": [
+        25.0
+      ]
+    },
+    {
+      "id": 9,
+      "type": "LTXFoleyVideoToAudioLatent",
+      "pos": [
+        -360,
+        -170
+      ],
+      "size": [
+        360,
+        340
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 2
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 13
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 14
+        },
+        {
+          "name": "video_vae",
+          "type": "VAE",
+          "link": 7
+        },
+        {
+          "name": "audio_vae",
+          "type": "VAE",
+          "link": 8
+        },
+        {
+          "name": "frame_rate",
+          "type": "FLOAT",
+          "link": 35
+        }
+      ],
+      "outputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "links": [
+            15
+          ]
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "links": [
+            16
+          ]
+        },
+        {
+          "name": "av_latent",
+          "type": "LATENT",
+          "links": [
+            17,
+            25,
+            37
+          ]
+        },
+        {
+          "name": "preview_images",
+          "type": "IMAGE",
+          "links": null
+        },
+        {
+          "name": "frame_rate",
+          "type": "FLOAT",
+          "links": null
+        },
+        {
+          "name": "frames",
+          "type": "INT",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXFoleyVideoToAudioLatent"
+      },
+      "widgets_values": [
+        25.0,
+        576,
+        576,
+        89
+      ]
+    },
+    {
+      "id": 10,
+      "type": "LoraLoaderModelOnly",
+      "pos": [
+        -850,
+        120
+      ],
+      "size": [
+        360,
+        90
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 6
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            20
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoraLoaderModelOnly"
+      },
+      "widgets_values": [
+        "ltx-2.3-foley-400-steps.safetensors",
+        1.0
+      ]
+    },
+    {
+      "id": 11,
+      "type": "ModelSamplingLTXV",
+      "pos": [
+        -420,
+        220
+      ],
+      "size": [
+        260,
+        120
+      ],
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 20
+        },
+        {
+          "name": "latent",
+          "type": "LATENT",
+          "link": 17
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            21
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ModelSamplingLTXV"
+      },
+      "widgets_values": [
+        2.05,
+        0.95
+      ]
+    },
+    {
+      "id": 12,
+      "type": "STGGuiderNode",
+      "pos": [
+        40,
+        240
+      ],
+      "size": [
+        240,
+        150
+      ],
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 38
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 15
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 16
+        }
+      ],
+      "outputs": [
+        {
+          "name": "GUIDER",
+          "type": "GUIDER",
+          "links": [
+            22
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "STGGuiderNode"
+      },
+      "widgets_values": [
+        4.0,
+        1.0,
+        0.7
+      ]
+    },
+    {
+      "id": 13,
+      "type": "RandomNoise",
+      "pos": [
+        40,
+        -100
+      ],
+      "size": [
+        240,
+        90
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "NOISE",
+          "type": "NOISE",
+          "links": [
+            23
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "RandomNoise"
+      },
+      "widgets_values": [
+        42,
+        "fixed"
+      ]
+    },
+    {
+      "id": 14,
+      "type": "KSamplerSelect",
+      "pos": [
+        40,
+        30
+      ],
+      "size": [
+        240,
+        80
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "SAMPLER",
+          "type": "SAMPLER",
+          "links": [
+            24
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSamplerSelect"
+      },
+      "widgets_values": [
+        "euler_ancestral_cfg_pp"
+      ]
+    },
+    {
+      "id": 15,
+      "type": "LTXVScheduler",
+      "pos": [
+        40,
+        430
+      ],
+      "size": [
+        240,
+        160
+      ],
+      "flags": {},
+      "order": 15,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "latent",
+          "type": "LATENT",
+          "link": 25
+        }
+      ],
+      "outputs": [
+        {
+          "name": "SIGMAS",
+          "type": "SIGMAS",
+          "links": [
+            26
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXVScheduler"
+      },
+      "widgets_values": [
+        30,
+        2.05,
+        0.95,
+        true,
+        0.1
+      ]
+    },
+    {
+      "id": 16,
+      "type": "SamplerCustomAdvanced",
+      "pos": [
+        360,
+        120
+      ],
+      "size": [
+        230,
+        130
+      ],
+      "flags": {},
+      "order": 16,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "noise",
+          "type": "NOISE",
+          "link": 23
+        },
+        {
+          "name": "guider",
+          "type": "GUIDER",
+          "link": 22
+        },
+        {
+          "name": "sampler",
+          "type": "SAMPLER",
+          "link": 24
+        },
+        {
+          "name": "sigmas",
+          "type": "SIGMAS",
+          "link": 26
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 37
+        }
+      ],
+      "outputs": [
+        {
+          "name": "output",
+          "type": "LATENT",
+          "links": [
+            27
+          ]
+        },
+        {
+          "name": "denoised_output",
+          "type": "LATENT",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "SamplerCustomAdvanced"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 17,
+      "type": "LTXVSeparateAVLatent",
+      "pos": [
+        650,
+        120
+      ],
+      "size": [
+        220,
+        80
+      ],
+      "flags": {},
+      "order": 17,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "av_latent",
+          "type": "LATENT",
+          "link": 27
+        }
+      ],
+      "outputs": [
+        {
+          "name": "video_latent",
+          "type": "LATENT",
+          "links": null
+        },
+        {
+          "name": "audio_latent",
+          "type": "LATENT",
+          "links": [
+            28
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXVSeparateAVLatent"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 18,
+      "type": "LTXFoleyAudioVAEDecode",
+      "pos": [
+        920,
+        120
+      ],
+      "size": [
+        240,
+        90
+      ],
+      "flags": {},
+      "order": 18,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 28
+        },
+        {
+          "name": "audio_vae",
+          "type": "VAE",
+          "link": 36
+        }
+      ],
+      "outputs": [
+        {
+          "name": "Audio",
+          "type": "AUDIO",
+          "links": [
+            31
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXFoleyAudioVAEDecode"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 19,
+      "type": "LTXFoleyTrimImages",
+      "pos": [
+        920,
+        -120
+      ],
+      "size": [
+        260,
+        140
+      ],
+      "flags": {},
+      "order": 19,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 29
+        },
+        {
+          "name": "frame_rate",
+          "type": "FLOAT",
+          "link": 30
+        }
+      ],
+      "outputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "links": [
+            32
+          ]
+        },
+        {
+          "name": "frame_rate",
+          "type": "FLOAT",
+          "links": [
+            33
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXFoleyTrimImages"
+      },
+      "widgets_values": [
+        25.0,
+        89
+      ]
+    },
+    {
+      "id": 20,
+      "type": "CreateVideo",
+      "pos": [
+        1220,
+        0
+      ],
+      "size": [
+        260,
+        140
+      ],
+      "flags": {},
+      "order": 20,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 32
+        },
+        {
+          "name": "fps",
+          "type": "FLOAT",
+          "link": 33
+        },
+        {
+          "name": "audio",
+          "type": "AUDIO",
+          "link": 31
+        }
+      ],
+      "outputs": [
+        {
+          "name": "video",
+          "type": "VIDEO",
+          "links": [
+            34
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CreateVideo"
+      },
+      "widgets_values": [
+        25.0,
+        8
+      ]
+    },
+    {
+      "id": 21,
+      "type": "SaveVideo",
+      "pos": [
+        1530,
+        0
+      ],
+      "size": [
+        260,
+        110
+      ],
+      "flags": {},
+      "order": 21,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "video",
+          "type": "VIDEO",
+          "link": 34
+        }
+      ],
+      "outputs": [
+        {
+          "name": "video",
+          "type": "VIDEO",
+          "links": null
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "SaveVideo"
+      },
+      "widgets_values": [
+        "ltx_foley",
+        "auto",
+        "auto"
+      ]
+    },
+    {
+      "id": 22,
+      "type": "LTXVApplySTG",
+      "pos": [
+        -260,
+        260
+      ],
+      "size": [
+        240,
+        80
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 21
+        }
+      ],
+      "outputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "links": [
+            38
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LTXVApplySTG"
+      },
+      "widgets_values": [
+        "14, 19"
+      ]
+    }
+  ],
+  "links": [
+    [
+      1,
+      1,
+      0,
+      2,
+      0,
+      "VIDEO"
+    ],
+    [
+      2,
+      2,
+      0,
+      9,
+      0,
+      "IMAGE"
+    ],
+    [
+      3,
+      2,
+      2,
+      8,
+      2,
+      "FLOAT"
+    ],
+    [
+      6,
+      3,
+      0,
+      10,
+      0,
+      "MODEL"
+    ],
+    [
+      7,
+      3,
+      2,
+      9,
+      3,
+      "VAE"
+    ],
+    [
+      8,
+      4,
+      0,
+      9,
+      4,
+      "VAE"
+    ],
+    [
+      9,
+      5,
+      0,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      10,
+      5,
+      0,
+      7,
+      0,
+      "CLIP"
+    ],
+    [
+      11,
+      6,
+      0,
+      8,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      12,
+      7,
+      0,
+      8,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      13,
+      8,
+      0,
+      9,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      14,
+      8,
+      1,
+      9,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      15,
+      9,
+      0,
+      12,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      16,
+      9,
+      1,
+      12,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      17,
+      9,
+      2,
+      11,
+      1,
+      "LATENT"
+    ],
+    [
+      20,
+      10,
+      0,
+      11,
+      0,
+      "MODEL"
+    ],
+    [
+      21,
+      11,
+      0,
+      22,
+      0,
+      "MODEL"
+    ],
+    [
+      22,
+      12,
+      0,
+      16,
+      1,
+      "GUIDER"
+    ],
+    [
+      23,
+      13,
+      0,
+      16,
+      0,
+      "NOISE"
+    ],
+    [
+      24,
+      14,
+      0,
+      16,
+      2,
+      "SAMPLER"
+    ],
+    [
+      25,
+      9,
+      2,
+      15,
+      0,
+      "LATENT"
+    ],
+    [
+      26,
+      15,
+      0,
+      16,
+      3,
+      "SIGMAS"
+    ],
+    [
+      27,
+      16,
+      0,
+      17,
+      0,
+      "LATENT"
+    ],
+    [
+      28,
+      17,
+      1,
+      18,
+      0,
+      "LATENT"
+    ],
+    [
+      29,
+      2,
+      0,
+      19,
+      0,
+      "IMAGE"
+    ],
+    [
+      30,
+      2,
+      2,
+      19,
+      1,
+      "FLOAT"
+    ],
+    [
+      31,
+      18,
+      0,
+      20,
+      2,
+      "AUDIO"
+    ],
+    [
+      32,
+      19,
+      0,
+      20,
+      0,
+      "IMAGE"
+    ],
+    [
+      33,
+      19,
+      1,
+      20,
+      1,
+      "FLOAT"
+    ],
+    [
+      34,
+      20,
+      0,
+      21,
+      0,
+      "VIDEO"
+    ],
+    [
+      35,
+      2,
+      2,
+      9,
+      5,
+      "FLOAT"
+    ],
+    [
+      36,
+      4,
+      0,
+      18,
+      1,
+      "VAE"
+    ],
+    [
+      37,
+      9,
+      2,
+      16,
+      4,
+      "LATENT"
+    ],
+    [
+      38,
+      22,
+      0,
+      12,
+      0,
+      "MODEL"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.75,
+      "offset": [
+        1530,
+        390
+      ]
+    }
+  },
+  "models": [
+    {
+      "name": "ltx-2.3-22b-dev-fp8.safetensors",
+      "url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors",
+      "directory": "checkpoints"
+    },
+    {
+      "name": "gemma_3_12B_it_fp8_scaled.safetensors",
+      "url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors",
+      "directory": "text_encoders"
+    },
+    {
+      "name": "ltx-2.3-foley-400-steps.safetensors",
+      "url": "https://huggingface.co/FuzzPuppy/LTX-2.3-Foley/resolve/main/ltx-2.3-foley-400-steps.safetensors",
+      "directory": "loras"
+    }
+  ],
+  "version": 0.4
+}

ltx_foley_v2a/__init__.py

@@ -0,0 +1,3 @@
+from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
+
+__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]

ltx_foley_v2a/nodes.py

@@ -0,0 +1,180 @@
+from __future__ import annotations
+
+def _common_upscale(images, width: int, height: int):
+    import comfy.utils
+
+    return comfy.utils.common_upscale(images.movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+
+
+def _intermediate_device():
+    import comfy.model_management
+
+    return comfy.model_management.intermediate_device()
+
+
+def _conditioning_set_values(conditioning, values):
+    import node_helpers
+
+    return node_helpers.conditioning_set_values(conditioning, values)
+
+
+def _audio_vae_model(audio_vae):
+    return getattr(audio_vae, "first_stage_model", audio_vae)
+
+
+class LTXFoleyVideoToAudioLatent:
+    CATEGORY = "LTX/Foley"
+    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT", "IMAGE", "FLOAT", "INT")
+    RETURN_NAMES = ("positive", "negative", "av_latent", "preview_images", "frame_rate", "frames")
+    FUNCTION = "prepare"
+
+    @classmethod
+    def INPUT_TYPES(cls) -> dict[str, object]:
+        return {
+            "required": {
+                "images": ("IMAGE",),
+                "positive": ("CONDITIONING",),
+                "negative": ("CONDITIONING",),
+                "video_vae": ("VAE",),
+                "audio_vae": ("VAE",),
+                "frame_rate": ("FLOAT", {"default": 25.0, "min": 1.0, "max": 120.0, "step": 0.01}),
+                "width": ("INT", {"default": 576, "min": 256, "max": 2048, "step": 32}),
+                "height": ("INT", {"default": 576, "min": 256, "max": 2048, "step": 32}),
+                "frames": ("INT", {"default": 89, "min": 9, "max": 257, "step": 8}),
+            }
+        }
+
+    def prepare(
+        self,
+        images,
+        positive,
+        negative,
+        video_vae,
+        audio_vae,
+        frame_rate: float,
+        width: int,
+        height: int,
+        frames: int,
+    ):
+        import torch
+
+        if frames % 8 != 1:
+            raise ValueError("frames must satisfy frames % 8 == 1")
+        if images.shape[0] == 0:
+            raise ValueError("No video frames were provided")
+
+        source = images[:frames]
+        if source.shape[0] < frames:
+            pad = source[-1:].repeat((frames - source.shape[0], 1, 1, 1))
+            source = torch.cat([source, pad], dim=0)
+
+        resized = _common_upscale(source, width, height).clamp(0.0, 1.0)
+        video_latent = video_vae.encode(resized[:, :, :, :3])
+        video_noise_mask = torch.zeros(
+            (1, 1, video_latent.shape[2], 1, 1),
+            dtype=torch.float32,
+            device=video_latent.device,
+        )
+
+        audio_model = _audio_vae_model(audio_vae)
+        z_channels = getattr(audio_vae, "latent_channels", audio_model.latent_channels)
+        audio_freq = audio_model.latent_frequency_bins
+        audio_latents = audio_model.num_of_latents_from_frames(frames, int(round(frame_rate)))
+        audio_latent = torch.zeros(
+            (1, z_channels, audio_latents, audio_freq),
+            device=_intermediate_device(),
+        )
+        audio_noise_mask = torch.ones_like(audio_latent)
+
+        import comfy.nested_tensor
+
+        av_latent = {
+            "samples": comfy.nested_tensor.NestedTensor((video_latent, audio_latent)),
+            "noise_mask": comfy.nested_tensor.NestedTensor((video_noise_mask, audio_noise_mask)),
+        }
+        values = {"frame_rate": frame_rate}
+        return (
+            _conditioning_set_values(positive, values),
+            _conditioning_set_values(negative, values),
+            av_latent,
+            resized,
+            float(frame_rate),
+            int(frames),
+        )
+
+
+class LTXFoleyTrimImages:
+    CATEGORY = "LTX/Foley"
+    RETURN_TYPES = ("IMAGE", "FLOAT")
+    RETURN_NAMES = ("images", "frame_rate")
+    FUNCTION = "trim"
+
+    @classmethod
+    def INPUT_TYPES(cls) -> dict[str, object]:
+        return {
+            "required": {
+                "images": ("IMAGE",),
+                "frame_rate": ("FLOAT", {"default": 25.0, "min": 1.0, "max": 120.0, "step": 0.01}),
+                "frames": ("INT", {"default": 89, "min": 9, "max": 257, "step": 8}),
+            }
+        }
+
+    def trim(self, images, frame_rate: float, frames: int):
+        import torch
+
+        if images.shape[0] == 0:
+            raise ValueError("No video frames were provided")
+        trimmed = images[:frames]
+        if trimmed.shape[0] < frames:
+            pad = trimmed[-1:].repeat((frames - trimmed.shape[0], 1, 1, 1))
+            trimmed = torch.cat([trimmed, pad], dim=0)
+        return (trimmed, float(frame_rate))
+
+
+class LTXFoleyAudioVAEDecode:
+    CATEGORY = "LTX/Foley"
+    RETURN_TYPES = ("AUDIO",)
+    RETURN_NAMES = ("audio",)
+    FUNCTION = "decode"
+
+    @classmethod
+    def INPUT_TYPES(cls) -> dict[str, object]:
+        return {
+            "required": {
+                "samples": ("LATENT",),
+                "audio_vae": ("VAE",),
+            }
+        }
+
+    def decode(self, samples, audio_vae):
+        audio_latent = samples["samples"]
+        if audio_latent.is_nested:
+            audio_latent = audio_latent.unbind()[-1]
+
+        audio = audio_vae.decode(audio_latent).to(audio_latent.device)
+        if audio.ndim == 2:
+            audio = audio.unsqueeze(1)
+        elif audio.ndim != 3:
+            raise ValueError(f"Expected decoded audio to have 2 or 3 dimensions, got shape {tuple(audio.shape)}")
+
+        if audio.shape[1] in (1, 2, 6):
+            waveform = audio
+        elif audio.shape[2] in (1, 2, 6):
+            waveform = audio.movedim(-1, 1)
+        else:
+            raise ValueError(f"Could not infer audio channel dimension from decoded shape {tuple(audio.shape)}")
+
+        output_sample_rate = _audio_vae_model(audio_vae).output_sample_rate
+        return ({"waveform": waveform, "sample_rate": int(output_sample_rate)},)
+
+
+NODE_CLASS_MAPPINGS = {
+    "LTXFoleyVideoToAudioLatent": LTXFoleyVideoToAudioLatent,
+    "LTXFoleyTrimImages": LTXFoleyTrimImages,
+    "LTXFoleyAudioVAEDecode": LTXFoleyAudioVAEDecode,
+}
+NODE_DISPLAY_NAME_MAPPINGS = {
+    "LTXFoleyVideoToAudioLatent": "LTX Foley Video To Audio Latent",
+    "LTXFoleyTrimImages": "LTX Foley Trim Images",
+    "LTXFoleyAudioVAEDecode": "LTX Foley Audio VAE Decode",
+}

setup_runpod_ltx_foley.sh

@@ -0,0 +1,218 @@
+#!/usr/bin/env bash
+set -Eeuo pipefail
+
+LTXVIDEO_REPO="${LTXVIDEO_REPO:-https://github.com/Lightricks/ComfyUI-LTXVideo.git}"
+WORKFLOW_REPO="${WORKFLOW_REPO:-FuzzPuppy/LTX-2.3-Foley-Workflow}"
+WORKFLOW_BASE_URL="${WORKFLOW_BASE_URL:-https://huggingface.co/${WORKFLOW_REPO}/resolve/main}"
+
+log() {
+  printf '\n[%s] %s\n' "$(date +%H:%M:%S)" "$*"
+}
+
+die() {
+  printf '\nERROR: %s\n' "$*" >&2
+  exit 1
+}
+
+download_file() {
+  local url="$1"
+  local target="$2"
+  local token="${HF_TOKEN:-${HUGGINGFACE_TOKEN:-}}"
+  local curl_args=(-fL --retry 5 --retry-delay 2)
+
+  mkdir -p "$(dirname "$target")"
+  if [[ -n "$token" ]]; then
+    curl_args+=(-H "Authorization: Bearer $token")
+  fi
+  curl "${curl_args[@]}" "$url" -o "$target"
+}
+
+download_model_file() {
+  local url="$1"
+  local target_path="$2"
+  local expected_sha256="$3"
+  local partial_path="${target_path}.part"
+  local token="${HF_TOKEN:-${HUGGINGFACE_TOKEN:-}}"
+  local curl_args=(-fL --retry 5 --retry-delay 2 -C -)
+  local attempt
+
+  if [[ -s "$target_path" ]]; then
+    if printf '%s  %s\n' "$expected_sha256" "$target_path" | sha256sum -c - >/dev/null 2>&1; then
+      printf 'verified: %s\n' "$target_path"
+      return
+    fi
+    printf 'hash mismatch, redownloading: %s\n' "$target_path"
+    rm -f "$target_path"
+  fi
+
+  mkdir -p "$(dirname "$target_path")"
+  if [[ -n "$token" ]]; then
+    curl_args+=(-H "Authorization: Bearer $token")
+  fi
+
+  for attempt in 1 2; do
+    curl "${curl_args[@]}" "$url" -o "$partial_path"
+    if printf '%s  %s\n' "$expected_sha256" "$partial_path" | sha256sum -c -; then
+      mv "$partial_path" "$target_path"
+      [[ -s "$target_path" ]] || die "Expected download missing: $target_path"
+      return
+    fi
+
+    rm -f "$partial_path"
+    curl_args=(-fL --retry 5 --retry-delay 2)
+    if [[ -n "$token" ]]; then
+      curl_args+=(-H "Authorization: Bearer $token")
+    fi
+    printf 'hash mismatch, retrying clean download: %s\n' "$target_path"
+  done
+
+  die "Downloaded file failed SHA-256 verification: $target_path"
+}
+
+build_comfyui_args() {
+  COMFYUI_ARGS=(--listen 0.0.0.0 --port 8188 --enable-cors-header)
+
+  if [[ -s "$ARGS_FILE" ]]; then
+    local line
+    local line_args
+    while IFS= read -r line; do
+      [[ -z "$line" || "$line" == \#* ]] && continue
+      read -r -a line_args <<< "$line"
+      COMFYUI_ARGS+=("${line_args[@]}")
+    done < "$ARGS_FILE"
+  fi
+}
+
+restart_comfyui() {
+  log "Restarting ComfyUI"
+  build_comfyui_args
+
+  local pid
+  while IFS= read -r pid; do
+    [[ -z "$pid" ]] && continue
+    kill "$pid" 2>/dev/null || true
+  done < <(pgrep -f "python.*${COMFYUI_DIR}/main.py|python.*main.py.*--port 8188" || true)
+
+  local attempt
+  for attempt in {1..20}; do
+    if ! pgrep -f "python.*${COMFYUI_DIR}/main.py|python.*main.py.*--port 8188" >/dev/null; then
+      break
+    fi
+    sleep 1
+  done
+
+  if pgrep -f "python.*${COMFYUI_DIR}/main.py|python.*main.py.*--port 8188" >/dev/null; then
+    die "Timed out waiting for the old ComfyUI process to stop."
+  fi
+
+  (
+    cd "$COMFYUI_DIR"
+    nohup "$PYTHON_BIN" main.py "${COMFYUI_ARGS[@]}" > "$LOG_FILE" 2>&1 &
+    printf '%s\n' "$!" > "$PID_FILE"
+  )
+
+  sleep 2
+  if ! kill -0 "$(cat "$PID_FILE")" 2>/dev/null; then
+    die "ComfyUI failed to start. Check $LOG_FILE"
+  fi
+
+  for attempt in {1..60}; do
+    if curl -fsS http://127.0.0.1:8188/ >/dev/null 2>&1; then
+      log "ComfyUI restarted with pid $(cat "$PID_FILE"). Logs: $LOG_FILE"
+      return
+    fi
+    sleep 1
+  done
+
+  die "ComfyUI process started, but port 8188 did not become ready. Check $LOG_FILE"
+}
+
+COMFYUI_DIR="${COMFYUI_DIR:-/workspace/runpod-slim/ComfyUI}"
+[[ -f "$COMFYUI_DIR/main.py" ]] || die "Could not find ComfyUI at $COMFYUI_DIR. Use RunPod's official ComfyUI - CUDA 12.8 template or set COMFYUI_DIR=/path/to/ComfyUI."
+CUSTOM_NODES_DIR="$COMFYUI_DIR/custom_nodes"
+MODELS_DIR="$COMFYUI_DIR/models"
+INPUT_DIR="$COMFYUI_DIR/input"
+VENV_DIR="$COMFYUI_DIR/.venv-cu128"
+ARGS_FILE="/workspace/runpod-slim/comfyui_args.txt"
+LOG_FILE="/workspace/runpod-slim/comfyui-restart.log"
+PID_FILE="/workspace/runpod-slim/comfyui-restart.pid"
+PYTHON_BIN="$VENV_DIR/bin/python"
+
+if [[ ! -x "$PYTHON_BIN" ]]; then
+  PYTHON_BIN="$COMFYUI_DIR/venv/bin/python"
+fi
+if [[ ! -x "$PYTHON_BIN" ]]; then
+  PYTHON_BIN="$(command -v python3.12 || command -v python3 || true)"
+fi
+[[ -x "$PYTHON_BIN" ]] || die "Could not find Python. Expected $COMFYUI_DIR/.venv-cu128/bin/python or python3 on PATH."
+
+log "Using ComfyUI at $COMFYUI_DIR"
+log "Using Python at $PYTHON_BIN"
+
+mkdir -p "$CUSTOM_NODES_DIR" "$MODELS_DIR/checkpoints" "$MODELS_DIR/loras" "$MODELS_DIR/text_encoders" "$INPUT_DIR"
+
+command -v curl >/dev/null 2>&1 || die "curl is required. RunPod's official ComfyUI - CUDA 12.8 template includes it."
+command -v git >/dev/null 2>&1 || die "git is required. RunPod's official ComfyUI - CUDA 12.8 template includes it."
+command -v ffmpeg >/dev/null 2>&1 || die "ffmpeg is required. RunPod's official ComfyUI - CUDA 12.8 template includes it."
+command -v sha256sum >/dev/null 2>&1 || die "sha256sum is required. RunPod's official ComfyUI - CUDA 12.8 template includes it."
+
+if [[ "${UPDATE_COMFYUI:-0}" == "1" ]]; then
+  log "Updating ComfyUI"
+  git -C "$COMFYUI_DIR" pull --ff-only || log "ComfyUI git pull was skipped or failed; continuing with the installed version."
+else
+  log "Keeping the RunPod template's pinned ComfyUI install"
+fi
+
+log "Installing official LTXVideo custom nodes"
+if [[ -d "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo/.git" ]]; then
+  git -C "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo" pull --ff-only || log "LTXVideo git pull was skipped or failed; continuing with the installed version."
+else
+  rm -rf "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo"
+  git clone --depth 1 "$LTXVIDEO_REPO" "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo"
+fi
+
+if [[ -f "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo/requirements.txt" ]]; then
+  "$PYTHON_BIN" -m pip install -r "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo/requirements.txt"
+fi
+if [[ -f "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo/install.py" ]]; then
+  "$PYTHON_BIN" "$CUSTOM_NODES_DIR/ComfyUI-LTXVideo/install.py" || log "LTXVideo install.py returned non-zero; continuing after requirements install."
+fi
+
+log "Installing LTX Foley helper node and workflow from $WORKFLOW_REPO"
+NODE_DEST="$CUSTOM_NODES_DIR/ltx_foley_v2a"
+WORKFLOW_DEST="$COMFYUI_DIR/user/default/workflows"
+rm -rf "$NODE_DEST"
+mkdir -p "$NODE_DEST" "$WORKFLOW_DEST"
+download_file "$WORKFLOW_BASE_URL/ltx_foley_v2a/__init__.py" "$NODE_DEST/__init__.py"
+download_file "$WORKFLOW_BASE_URL/ltx_foley_v2a/nodes.py" "$NODE_DEST/nodes.py"
+download_file "$WORKFLOW_BASE_URL/ltx_23_foley_v2a.json" "$WORKFLOW_DEST/ltx_23_foley_v2a.json"
+download_file "$WORKFLOW_BASE_URL/tennis-no-sound.mp4" "$INPUT_DIR/input.mp4"
+
+log "Downloading LTX 2.3 Foley model files"
+download_model_file \
+  "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors" \
+  "$MODELS_DIR/checkpoints/ltx-2.3-22b-dev-fp8.safetensors" \
+  "28606c5b5a06ce56f896d4dfcb20f212739e07a68fbe48e53638188449d26450"
+download_model_file \
+  "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors" \
+  "$MODELS_DIR/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors" \
+  "60216ce97c01c3a8753c2dfd0a89fc76e16fbe446d1a32ef8f1b528ac8bae466"
+download_model_file \
+  "https://huggingface.co/FuzzPuppy/LTX-2.3-Foley/resolve/main/ltx-2.3-foley-400-steps.safetensors" \
+  "$MODELS_DIR/loras/ltx-2.3-foley-400-steps.safetensors" \
+  "12b37ffff8444ac1348a8c9fb24843a6bd70e77cf4202ac39b1d056b81fa41c9"
+
+log "Done"
+restart_comfyui
+
+cat <<EOF
+
+Next steps:
+1. Open the RunPod HTTP service on port 8188.
+2. Load workflow: user/default/workflows/ltx_23_foley_v2a.json
+3. Queue the workflow. The tennis test video is already installed as input.mp4 and the prompt is prefilled.
+
+If model download fails with 401/403, accept the model licenses on Hugging Face and rerun with:
+  export HF_TOKEN=hf_...
+  bash $0
+EOF

tennis-no-sound.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eaf7a21d6cb6f061ca368921152b7dc7164a21cd88b25c4b72c1654ebeb49a2
+size 413412