nodes/Lightricks-ComfyUI-LTXVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Automated PR - 2026-08-20

Browse Source
This commit is contained in:
github-actions[bot]
2026-08-20 13:55:32 +00:00
parent ac4d998390
commit b9446f5972
12 changed files with 10049 additions and 146 deletions
Download Patch File Download Diff File Expand all files Collapse all files
embeddings_connector.py
+25 -2
View File
@@ -13,8 +13,19 @@ from comfy.ldm.lightricks.model import (
)
from torch import nn
try:
# New core (since ComfyUI PR #15056) replaced interleaved_freqs_cis/split_freqs_cis
# with a single freqs_cis_matrix helper.
from comfy.ldm.lightricks.model import freqs_cis_matrix
_USE_FREQS_CIS_MATRIX = True
except ImportError:
# Legacy core: cos/sin freqs consumed as a (cos, sin, split) tuple.
from .rope_utils import interleaved_freqs_cis, split_freqs_cis
_USE_FREQS_CIS_MATRIX = False
from .pos_embedding_exp_values import POS_EMBEDDING_EXP_VALUES
from .rope_utils import interleaved_freqs_cis, split_freqs_cis
class BasicTransformerBlock1D(nn.Module):
@@ -250,11 +261,23 @@ class Embeddings1DConnector(nn.Module):
expected_freqs = dim // 2
current_freqs = freqs.shape[-1]
pad_size = expected_freqs - current_freqs
else:
pad_size = dim % n_elem
if _USE_FREQS_CIS_MATRIX:
# New core takes (rotation_matrix, split_pe); let it build the matrix so
# this cannot drift from the transformer again.
return freqs_cis_matrix(
freqs, pad_size, self.split_rope, self.num_attention_heads, self.dtype
)
# Legacy core: returns (cos, sin, split_rope).
if self.split_rope:
cos_freq, sin_freq = split_freqs_cis(
freqs, pad_size, self.num_attention_heads
)
else:
cos_freq, sin_freq = interleaved_freqs_cis(freqs, dim % n_elem)
cos_freq, sin_freq = interleaved_freqs_cis(freqs, pad_size)
return cos_freq.to(self.dtype), sin_freq.to(self.dtype), self.split_rope
def forward(
example_workflows/2.5/LTX-2.5_A2V_Two_Stage_Distilled.json
+9123
View File
File diff suppressed because it is too large Load Diff
example_workflows/2.5/LTX-2.5_ICLoRA_Ingredients_Single_Stage_Distilled.json
+77 -15
View File
@@ -61,7 +61,7 @@
"title": "Save video",
"properties": {},
"widgets_values": [
"## Save video\n\nThis is your output preview 🎉🥳"
"## Save video\n\nThis is your output preview \ud83c\udf89\ud83e\udd73"
],
"color": "#432",
"bgcolor": "#653"
@@ -223,7 +223,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Ingredients - ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ ├── 📂 loras/\n│ │ └── ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Ingredients - ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 loras/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -751,7 +751,7 @@
"",
24,
"",
"ltx-2.4-22b-distilled-rc2.safetensors"
"ltx-2.5-22b-distilled-transformer-bf16.safetensors"
]
},
{
@@ -882,7 +882,34 @@
"properties": {
"cnr_id": "comfy-core",
"ver": "0.25.0",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients/resolve/main/ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
@@ -890,7 +917,7 @@
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors",
1.2
1.3
]
},
{
@@ -1400,7 +1427,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -1443,7 +1477,14 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-video-vae-bf16.safetensors"
@@ -1485,7 +1526,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -1529,10 +1577,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -1631,7 +1686,14 @@
}
],
"properties": {
"Node name for S&R": "LTXICLoRALoaderModelOnly"
"Node name for S&R": "LTXICLoRALoaderModelOnly",
"models": [
{
"name": "ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients/resolve/main/ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.3-22b-ic-lora-ingredients-0.9.safetensors",
@@ -2454,7 +2516,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -2462,7 +2524,7 @@
"",
"",
false,
"ltx-2.4-22b-distilled-rc2.safetensors"
"ltx-2.5-22b-distilled-transformer-bf16.safetensors"
]
},
{
@@ -2599,7 +2661,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -2607,7 +2669,7 @@
"",
"",
false,
"ltx-2.4-22b-distilled-rc2.safetensors"
"ltx-2.5-22b-distilled-transformer-bf16.safetensors"
]
},
{
example_workflows/2.5/LTX-2.5_ICLoRA_Inpaint_Two_Stage_Distilled.json
+105 -19
View File
@@ -500,10 +500,10 @@
"mode": 0,
"inputs": [],
"outputs": [],
"title": "How to use — Inpainting",
"title": "How to use \u2014 Inpainting",
"properties": {},
"widgets_values": [
"# How to Use Inpainting\n\nThis workflow supports **inpainting** within a source video. You provide a mask video, telling the model where to generate, and optional prompt & image describing what should be there.\n\n## 1. No prompt = the simple case\n\n- without a prompt → the model fills the new area to match the surrounding scene.\n\n\n## 2. Prompts describe the scene, not the edit\n\nIt's not an edit tool. Write a regular T2V-style prompt describing the in-painting region.\n\n\n## 3. Green leftovers\n\nThe pipeline composites green under the mask before diffusion — sometimes traces leak through at mask edges. Try a bigger dilation, a different seed, or re-encode the mask losslessly or the blending parameter is very important.\n\n## Mask video\n\n**B&W mask video** (white = inpaint, black = keep) that matches the source video's frame count and aspect ratio.\n\n**Input nodes**: start image (optional first frame), the **original video**, the **mask video** and an optional prompt.\n\n**bypass_i2v**: when OFF, the start image is used as the first frame (image-to-video); turn it ON for a purely text/mask-driven generation with no image conditioning."
"# How to Use Inpainting\n\nThis workflow supports **inpainting** within a source video. You provide a mask video, telling the model where to generate, and optional prompt & image describing what should be there.\n\n## 1. No prompt = the simple case\n\n- without a prompt \u2192 the model fills the new area to match the surrounding scene.\n\n\n## 2. Prompts describe the scene, not the edit\n\nIt's not an edit tool. Write a regular T2V-style prompt describing the in-painting region.\n\n\n## 3. Green leftovers\n\nThe pipeline composites green under the mask before diffusion \u2014 sometimes traces leak through at mask edges. Try a bigger dilation, a different seed, or re-encode the mask losslessly or the blending parameter is very important.\n\n## Mask video\n\n**B&W mask video** (white = inpaint, black = keep) that matches the source video's frame count and aspect ratio.\n\n**Input nodes**: start image (optional first frame), the **original video**, the **mask video** and an optional prompt.\n\n**bypass_i2v**: when OFF, the start image is used as the first frame (image-to-video); turn it ON for a purely text/mask-driven generation with no image conditioning."
],
"color": "#432",
"bgcolor": "#653"
@@ -527,7 +527,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA In/Outpainting - ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/blob/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.3-spatial-upscaler-x2-1.1.safetensors ](https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 loras/\n│ │ └── ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n│ ├── 📂 latent_upscale_models/\n│ └── ltx-2.3-spatial-upscaler-x2-1.1.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA In/Outpainting - ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/blob/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 loras/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 latent_upscale_models/\n\u2502 \u2514\u2500\u2500 ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -611,7 +611,7 @@
"title": "Preprocess",
"properties": {},
"widgets_values": [
"## Preprocess (stage 1)\n\nMasks the frames (`LTXVInpaintPreprocess`), builds the empty AV latent **at the reference video's size/length** (GetImageSize is here), conditions on the optional start image, injects the IC-LoRA guide, and adds **frozen audio** (VAEEncodeAudio → SetAudioRefTokens).\n\n*Frozen audio keeps the result consistent with the original sound; remove the audio stream if you don't want that guidance.*"
"## Preprocess (stage 1)\n\nMasks the frames (`LTXVInpaintPreprocess`), builds the empty AV latent **at the reference video's size/length** (GetImageSize is here), conditions on the optional start image, injects the IC-LoRA guide, and adds **frozen audio** (VAEEncodeAudio \u2192 SetAudioRefTokens).\n\n*Frozen audio keeps the result consistent with the original sound; remove the audio stream if you don't want that guidance.*"
],
"color": "#432",
"bgcolor": "#653"
@@ -1019,7 +1019,7 @@
"widgets_values": [
"",
"",
"ltx-2.4-22b-distilled-rc2.safetensors",
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
15,
false,
true,
@@ -1352,13 +1352,50 @@
}
],
"properties": {
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/resolve/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
"ltx-2.5-video-vae-bf16.safetensors",
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors",
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"gemma4_e2b_it_bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors"
@@ -2044,7 +2081,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -2087,7 +2131,14 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-video-vae-bf16.safetensors"
@@ -2129,7 +2180,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -2211,10 +2269,17 @@
"properties": {
"Node name for S&R": "LatentUpscaleModelLoader",
"cnr_id": "comfy-core",
"ver": "0.14.1"
"ver": "0.14.1",
"models": [
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
}
]
},
"widgets_values": [
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors"
]
},
{
@@ -2254,10 +2319,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -2299,10 +2371,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -2357,7 +2436,14 @@
}
],
"properties": {
"Node name for S&R": "LTXICLoRALoaderModelOnly"
"Node name for S&R": "LTXICLoRALoaderModelOnly",
"models": [
{
"name": "ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/resolve/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
@@ -2930,7 +3016,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -3833,7 +3919,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
example_workflows/2.5/LTX-2.5_ICLoRA_Motion_Track_Distilled.json
+87 -13
View File
@@ -61,7 +61,7 @@
"title": "Save video",
"properties": {},
"widgets_values": [
"## Save video\n\nThis is your output preview 🎉🥳"
"## Save video\n\nThis is your output preview \ud83c\udf89\ud83e\udd73"
],
"color": "#432",
"bgcolor": "#653"
@@ -149,7 +149,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Motion Track Control - ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 loras/\n│ │ └── ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Motion Track Control - ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 loras/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -1081,7 +1081,39 @@
"properties": {
"cnr_id": "comfy-core",
"ver": "0.25.0",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control/resolve/main/ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
@@ -1694,7 +1726,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -1737,7 +1776,14 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-video-vae-bf16.safetensors"
@@ -1779,7 +1825,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -1858,10 +1911,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -1903,10 +1963,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -1970,7 +2037,14 @@
}
],
"properties": {
"Node name for S&R": "LTXICLoRALoaderModelOnly"
"Node name for S&R": "LTXICLoRALoaderModelOnly",
"models": [
{
"name": "ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control/resolve/main/ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.3-22b-ic-lora-motion-track-control-ref0.5.safetensors",
@@ -3100,7 +3174,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -3164,7 +3238,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
example_workflows/2.5/LTX-2.5_ICLoRA_Outpaint_Two_Stage_Distilled.json
+105 -19
View File
@@ -421,10 +421,10 @@
"mode": 0,
"inputs": [],
"outputs": [],
"title": "How to use — Outpainting",
"title": "How to use \u2014 Outpainting",
"properties": {},
"widgets_values": [
"# How to Use Outpainting\n\nThis workflow supports **outpainting** (extending the canvas beyond the original frame). You provide a mask telling the model where to generate, and an optional prompt describing what should be there.\n\n## 1. No prompt = the simple case\n\n- without a prompt → just extends the existing canvas. The model fills the new area to match the surrounding scene.\n\n\n## 2. Prompts describe the scene, not the edit\n\nIt's not an edit tool. Write a regular T2V-style prompt describing the out-painting region.\n\n\n\n## 3. Green leftovers\n\nThe pipeline composites green under the mask before diffusion — sometimes traces leak through at mask edges. Try a bigger dilation, a different seed, or re-encode the mask losslessly or the blending parameter is very important."
"# How to Use Outpainting\n\nThis workflow supports **outpainting** (extending the canvas beyond the original frame). You provide a mask telling the model where to generate, and an optional prompt describing what should be there.\n\n## 1. No prompt = the simple case\n\n- without a prompt \u2192 just extends the existing canvas. The model fills the new area to match the surrounding scene.\n\n\n## 2. Prompts describe the scene, not the edit\n\nIt's not an edit tool. Write a regular T2V-style prompt describing the out-painting region.\n\n\n\n## 3. Green leftovers\n\nThe pipeline composites green under the mask before diffusion \u2014 sometimes traces leak through at mask edges. Try a bigger dilation, a different seed, or re-encode the mask losslessly or the blending parameter is very important."
],
"color": "#432",
"bgcolor": "#653"
@@ -448,7 +448,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA In/Outpainting - ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/blob/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.3-spatial-upscaler-x2-1.1.safetensors ](https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 loras/\n│ │ └── ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n│ ├── 📂 latent_upscale_models/\n│ └── ltx-2.3-spatial-upscaler-x2-1.1.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA In/Outpainting - ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/blob/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 loras/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 latent_upscale_models/\n\u2502 \u2514\u2500\u2500 ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -496,7 +496,7 @@
"title": "Preprocess",
"properties": {},
"widgets_values": [
"## Preprocess (stage 1)\n\nMasks the frames (`LTXVInpaintPreprocess`), builds the empty AV latent **at the reference video's size/length** (GetImageSize is here), conditions on the optional start image, injects the IC-LoRA guide, and adds **frozen audio** (VAEEncodeAudio → SetAudioRefTokens).\n\n*Frozen audio keeps the result consistent with the original sound; remove the audio stream if you don't want that guidance.*"
"## Preprocess (stage 1)\n\nMasks the frames (`LTXVInpaintPreprocess`), builds the empty AV latent **at the reference video's size/length** (GetImageSize is here), conditions on the optional start image, injects the IC-LoRA guide, and adds **frozen audio** (VAEEncodeAudio \u2192 SetAudioRefTokens).\n\n*Frozen audio keeps the result consistent with the original sound; remove the audio stream if you don't want that guidance.*"
],
"color": "#432",
"bgcolor": "#653"
@@ -1166,12 +1166,49 @@
}
],
"properties": {
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/resolve/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"directory": "loras"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
"ltx-2.5-video-vae-bf16.safetensors",
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors",
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"gemma4_e2b_it_bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
@@ -1402,7 +1439,7 @@
0,
457289196,
1088,
"ltx-2.4-22b-distilled-rc2.safetensors"
"ltx-2.5-22b-distilled-transformer-bf16.safetensors"
]
}
],
@@ -2092,7 +2129,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -2135,7 +2179,14 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-video-vae-bf16.safetensors"
@@ -2181,10 +2232,17 @@
"properties": {
"Node name for S&R": "LatentUpscaleModelLoader",
"cnr_id": "comfy-core",
"ver": "0.14.1"
"ver": "0.14.1",
"models": [
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
}
]
},
"widgets_values": [
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors"
]
},
{
@@ -2224,10 +2282,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -2282,7 +2347,14 @@
}
],
"properties": {
"Node name for S&R": "LTXICLoRALoaderModelOnly"
"Node name for S&R": "LTXICLoRALoaderModelOnly",
"models": [
{
"name": "ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting/resolve/main/ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.3-22b-ic-lora-in-outpainting-0.9.safetensors",
@@ -2326,10 +2398,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -2370,7 +2449,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -4205,7 +4291,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -4269,7 +4355,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
example_workflows/2.5/LTX-2.5_ICLoRA_Union_Control_Distilled.json
+103 -17
View File
@@ -113,7 +113,7 @@
"title": "Save video",
"properties": {},
"widgets_values": [
"## Save video\n\nThis is your output preview 🎉🥳"
"## Save video\n\nThis is your output preview \ud83c\udf89\ud83e\udd73"
],
"color": "#432",
"bgcolor": "#653"
@@ -201,7 +201,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Union Control - ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/blob/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.3-spatial-upscaler-x2-1.1.safetensors ](https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 loras/\n│ │ └── ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n│ ├── 📂 latent_upscale_models/\n│ └── ltx-2.3-spatial-upscaler-x2-1.1.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Union Control - ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/blob/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 loras/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 latent_upscale_models/\n\u2502 \u2514\u2500\u2500 ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -1129,13 +1129,50 @@
"properties": {
"cnr_id": "comfy-core",
"ver": "0.25.0",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/resolve/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
"ltx-2.5-video-vae-bf16.safetensors",
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors",
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"gemma4_e2b_it_bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors"
@@ -1907,7 +1944,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -1950,7 +1994,14 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-video-vae-bf16.safetensors"
@@ -1992,7 +2043,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -2074,10 +2132,17 @@
"properties": {
"Node name for S&R": "LatentUpscaleModelLoader",
"cnr_id": "comfy-core",
"ver": "0.14.1"
"ver": "0.14.1",
"models": [
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
}
]
},
"widgets_values": [
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors"
]
},
{
@@ -2117,10 +2182,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -2162,10 +2234,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -2220,7 +2299,14 @@
}
],
"properties": {
"Node name for S&R": "LTXICLoRALoaderModelOnly"
"Node name for S&R": "LTXICLoRALoaderModelOnly",
"models": [
{
"name": "ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/resolve/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors",
@@ -3463,7 +3549,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -3527,7 +3613,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -7088,7 +7174,7 @@
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Reference video → control signal",
"title": "Reference video \u2192 control signal",
"properties": {},
"widgets_values": [
"## Reference control signal\n\nThe reference video is turned into a guide by an **annotator**. **Depth** (VideoDepthAnything) is wired by default.\n\n## To switch:\n\nconnect **Canny** (`CannyEdgePreprocessor`) or **Pose** (`DWPreprocessor`) output into the `input` of the *scale-to-multiple* Resize node instead of the Depth output. All three read the resized reference frames; only the one wired into that Resize is used."
example_workflows/2.5/LTX-2.5_T2A_Single_Stage_Distilled.json
+60 -10
View File
@@ -143,7 +143,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\nText-to-audio uses the **audio VAE** and the **audio-only** wrapper around the diffusion model. There is no video VAE and no spatial upscaler in this flow.\n\n## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\nText-to-audio uses the **audio VAE** and the **audio-only** wrapper around the diffusion model. There is no video VAE and no spatial upscaler in this flow.\n\n## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -448,7 +448,29 @@
],
"properties": {
"Node name for S&R": "ff7e0338-cf55-4a2c-a455-34bec1cf3d1e",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
@@ -693,7 +715,7 @@
5,
0,
"",
"ltx-2.4-22b-distilled-rc2.safetensors"
"ltx-2.5-22b-distilled-transformer-bf16.safetensors"
]
},
{
@@ -1247,7 +1269,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -1289,7 +1318,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -1371,10 +1407,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"gemma4_e2b_it_bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -1416,7 +1459,14 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
@@ -2138,7 +2188,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -2202,7 +2252,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
example_workflows/2.5/LTX-2.5_T2V_I2V_Single_Stage_Distilled.json
+77 -15
View File
@@ -134,7 +134,7 @@
"title": "Save video",
"properties": {},
"widgets_values": [
"## Save video\n\nThis is you output preview 🎉🥳"
"## Save video\n\nThis is you output preview \ud83c\udf89\ud83e\udd73"
],
"color": "#432",
"bgcolor": "#653"
@@ -319,7 +319,7 @@
"title": "Decode",
"properties": {},
"widgets_values": [
"## Decode\n\nMake sure to adjust the number of tiles and overlap to fit your hardware.\n(fewer tiles will result in faster execution, but will require more memory).\n\n### Recommended settings\n\n| node settings (pixels) | resolved latent geometry |\n| ------------------------------------------ | ------------------------------- |\n| `512 / 64 / 128 / 32` | 16×16, ov 2 | 16f, ov 4 |\n| `768 / 192 / 128 / 32` | 24×24, ov 6 | 16f, ov 4 |\n| `1024 / 256 / 128 / 48` | 32×32, ov 8 | 16f, ov 6 |\n| `1536 / 384 / 192 / 48` | 48×48, ov 12 | 24f, ov 6 |\n| `768 / 192 / spatial-only` | 24×24, ov 6 | no temporal split |"
"## Decode\n\nMake sure to adjust the number of tiles and overlap to fit your hardware.\n(fewer tiles will result in faster execution, but will require more memory).\n\n### Recommended settings\n\n| node settings (pixels) | resolved latent geometry |\n| ------------------------------------------ | ------------------------------- |\n| `512 / 64 / 128 / 32` | 16\u00d716, ov 2 | 16f, ov 4 |\n| `768 / 192 / 128 / 32` | 24\u00d724, ov 6 | 16f, ov 4 |\n| `1024 / 256 / 128 / 48` | 32\u00d732, ov 8 | 16f, ov 6 |\n| `1536 / 384 / 192 / 48` | 48\u00d748, ov 12 | 24f, ov 6 |\n| `768 / 192 / spatial-only` | 24\u00d724, ov 6 | no temporal split |"
],
"color": "#432",
"bgcolor": "#653"
@@ -864,7 +864,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -986,7 +986,34 @@
"properties": {
"cnr_id": "comfy-core",
"ver": "0.25.0",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
@@ -1448,7 +1475,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -1491,10 +1525,17 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
"ltx-2.5-video-vae-bf16.safetensors"
]
},
{
@@ -1533,10 +1574,17 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-dev-transformer-bf16.safetensors",
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"default"
]
},
@@ -1577,10 +1625,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -1657,10 +1712,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -3115,7 +3177,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -3179,7 +3241,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
example_workflows/2.5/LTX-2.5_T2V_I2V_Two_Stage_Distilled.json
+92 -18
View File
@@ -134,7 +134,7 @@
"title": "Save video",
"properties": {},
"widgets_values": [
"## Save video\n\nThis is you output preview 🎉🥳"
"## Save video\n\nThis is you output preview \ud83c\udf89\ud83e\udd73"
],
"color": "#432",
"bgcolor": "#653"
@@ -319,7 +319,7 @@
"title": "Decode",
"properties": {},
"widgets_values": [
"## Decode\n\nMake sure to adjust the number of tiles and overlap to fit your hardware.\n(fewer tiles will result in faster execution, but will require more memory).\n\n### Recommended settings\n\n| node settings (pixels) | resolved latent geometry |\n| ------------------------------------------ | ------------------------------- |\n| `512 / 64 / 128 / 32` | 16×16, ov 2 | 16f, ov 4 |\n| `768 / 192 / 128 / 32` | 24×24, ov 6 | 16f, ov 4 |\n| `1024 / 256 / 128 / 48` | 32×32, ov 8 | 16f, ov 6 |\n| `1536 / 384 / 192 / 48` | 48×48, ov 12 | 24f, ov 6 |\n| `768 / 192 / spatial-only` | 24×24, ov 6 | no temporal split |"
"## Decode\n\nMake sure to adjust the number of tiles and overlap to fit your hardware.\n(fewer tiles will result in faster execution, but will require more memory).\n\n### Recommended settings\n\n| node settings (pixels) | resolved latent geometry |\n| ------------------------------------------ | ------------------------------- |\n| `512 / 64 / 128 / 32` | 16\u00d716, ov 2 | 16f, ov 4 |\n| `768 / 192 / 128 / 32` | 24\u00d724, ov 6 | 16f, ov 4 |\n| `1024 / 256 / 128 / 48` | 32\u00d732, ov 8 | 16f, ov 6 |\n| `1536 / 384 / 192 / 48` | 48\u00d748, ov 12 | 24f, ov 6 |\n| `768 / 192 / spatial-only` | 24\u00d724, ov 6 | no temporal split |"
],
"color": "#432",
"bgcolor": "#653"
@@ -858,7 +858,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.3-spatial-upscaler-x2-1.1.safetensors ](https://huggingface.co/Lightricks/LTX-2.3/blob/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n│ ├── 📂 latent_upscale_models/\n│ └── ltx-2.3-spatial-upscaler-x2-1.1.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n- [ Upscaler - ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors)\n\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 latent_upscale_models/\n\u2502 \u2514\u2500\u2500 ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -999,13 +999,45 @@
"properties": {
"cnr_id": "comfy-core",
"ver": "0.25.0",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
"ltx-2.5-video-vae-bf16.safetensors",
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors",
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"gemma4_e2b_it_bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors"
]
@@ -2797,7 +2829,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -2861,7 +2893,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -6850,7 +6882,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -6893,10 +6932,17 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
"ltx-2.5-video-vae-bf16.safetensors"
]
},
{
@@ -6935,10 +6981,17 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-dev-transformer-bf16.safetensors",
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"default"
]
},
@@ -7017,10 +7070,17 @@
"properties": {
"Node name for S&R": "LatentUpscaleModelLoader",
"cnr_id": "comfy-core",
"ver": "0.14.1"
"ver": "0.14.1",
"models": [
{
"name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"directory": "latent_upscale_models"
}
]
},
"widgets_values": [
"ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
"ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors"
]
},
{
@@ -7060,10 +7120,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -7105,10 +7172,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
example_workflows/2.5/LTX-2.5_V2V_ICLoRA_Single_Stage_Distilled.json
+92 -18
View File
@@ -87,7 +87,7 @@
"title": "Save video",
"properties": {},
"widgets_values": [
"## Save video\n\nThis is your output preview 🎉🥳"
"## Save video\n\nThis is your output preview \ud83c\udf89\ud83e\udd73"
],
"color": "#432",
"bgcolor": "#653"
@@ -113,7 +113,7 @@
"title": "Inputs",
"properties": {},
"widgets_values": [
"## Inputs\n\nEverything here is optional.\n\n### Prompt\n\nEnter a positive prompt. To rewrite it into a fuller description first, enable\n**enhance positive prompt** on the Input Parameters node below. The negative\nprompt is used as written and is never enhanced.\n\nSupplying an **LTX API key** encodes and enhances the prompt through the API\ninstead of locally, which saves memory. The workflow switches over on its own\nwhenever a key is present - there is nothing to un-bypass.\n\nSee the [prompting guide](https://docs.ltx.io/open-source-model/usage-guides/prompting-guide).\n\n### Image input\n\nCondition the video to open on a still by loading an image and enabling\n**use image input** on the Input Parameters node.\n\n### Source video\n\nThe source video is the subject of the edit. Its frames are resized and handed\nstraight to the IC-LoRA as guide frames.\n\nIts width, height, length and frame rate drive the whole generation, and its audio\ntrack is carried through so the result keeps the original sound. The instant-shave\n**IC-LoRA** is loaded in **Load Models**, the guide frames are injected in\n**Preprocess**, then cropped out during sampling.\n"
"## Inputs\n\nEverything here is optional.\n\n### Prompt\n\nEnter a positive prompt. To rewrite it into a fuller description first, enable\n**enhance positive prompt** on the Input Parameters node below. The negative\nprompt is used as written and is never enhanced.\n\nSupplying an **LTX API key** encodes and enhances the prompt through the API\ninstead of locally, which saves memory. The workflow switches over on its own\nwhenever a key is present - there is nothing to un-bypass.\n\nSee the [prompting guide](https://docs.ltx.io/open-source-model/usage-guides/prompting-guide).\n\n### Image input\n\nCondition the video to open on a still by loading an image and enabling\n**use image input** on the Input Parameters node.\n\n### Source video\n\nThe source video is the subject of the edit. Its frames are resized and handed\nstraight to the IC-LoRA as guide frames.\n\nIts width, height, length and frame rate drive the whole generation, and its audio\ntrack is carried through so the result keeps the original sound. The deblur\n**IC-LoRA** is loaded in **Load Models**, the guide frames are injected in\n**Preprocess**, then cropped out during sampling.\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -175,7 +175,7 @@
"title": "Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Instant Shave - ltx-2.3-22b-ic-lora-instant-shave-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Instant-Shave)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ ├── gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n│ │ └── gemma4_e2b_it_bf16.safetensors\n│ ├── 📂 loras/\n│ │ └── ltx-2.3-22b-ic-lora-instant-shave-0.9.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── ltx-2.5-22b-distilled-transformer-bf16.safetensors\n│ ├── 📂 vae/\n│ │ └── ltx-2.5-audio-vae-bf16.safetensors\n│ │ └── ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
"## Model Links\n\n**LTX-2.5 Model Weights**\n\nMake sure to click the \"Agree and Access\" button the first time you download.\n\n- [ Distilled model - ltx-2.5-22b-distilled-transformer-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors)\n\n- [ IC-LoRA Deblur - ltx-2.3-22b-ic-lora-deblur-0.9.safetensors ](https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Deblur/blob/main/ltx-2.3-22b-ic-lora-deblur-0.9.safetensors)\n\n- [ Audio VAE - ltx-2.5-audio-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-audio-vae-bf16.safetensors)\n\n- Video VAE - one of these:\n - [ Diffusion decoder ltx-2.5-video-vae-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-bf16.safetensors) - Best quality\n - [ Convolutional decoder - ltx-2.5-video-vae-conv-bf16.safetensors ](https://huggingface.co/Lightricks/LTX-2.5/blob/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors) - Lower memory & faster\n\n\n**Text Encoder - finetuned for LTX-2.5**\n- [gemma4-12b-with-proj-ltx-2.5-bf16.safetensors](https://huggingface.co/Lightricks/LTX-2.5/blob/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors)\n\n**Text Enhancer**\n- [Google Gemma 4 E2B IT](https://huggingface.co/Comfy-Org/gemma-4/blob/main/text_encoders/gemma4_e2b_it_bf16.safetensors)\n\n\n**Model Storage Location**\n\n```\n\ud83d\udcc2 ComfyUI/\n\u251c\u2500\u2500 \ud83d\udcc2 models/\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 text_encoders/\n\u2502 \u2502 \u251c\u2500\u2500 gemma4-12b-with-proj-ltx-2.5-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 gemma4_e2b_it_bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 loras/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.3-22b-ic-lora-deblur-0.9.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 diffusion_models/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-22b-distilled-transformer-bf16.safetensors\n\u2502 \u251c\u2500\u2500 \ud83d\udcc2 vae/\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-audio-vae-bf16.safetensors\n\u2502 \u2502 \u2514\u2500\u2500 ltx-2.5-video-vae-conv-bf16.safetensors / ltx-2.5-video-vae-bf16.safetensors\n```\n\n## Report Issues\nTo report any issues when running this workflow, [go to GitHub](https://github.com/Lightricks/ComfyUI-LTXVideo/issues)\n"
],
"color": "#432",
"bgcolor": "#653"
@@ -201,7 +201,7 @@
"title": "Generate",
"properties": {},
"widgets_values": [
"## Generate\n\n**Sampler - Distilled (8 steps)**\n\nRuns the distilled ltx-2.5 model with the instant-shave IC-LoRA applied, in 8\nsteps. You can change the noise seed, the guider cfg (used for both video and\naudio) and the sampler. The guide frames are cropped out afterwards\n(`LTXVCropGuides`) so only the generated video is decoded."
"## Generate\n\n**Sampler - Distilled (8 steps)**\n\nRuns the distilled ltx-2.5 model with the deblur IC-LoRA applied, in 8\nsteps. You can change the noise seed, the guider cfg (used for both video and\naudio) and the sampler. The guide frames are cropped out afterwards\n(`LTXVCropGuides`) so only the generated video is decoded."
],
"color": "#432",
"bgcolor": "#653"
@@ -1036,7 +1036,39 @@
"properties": {
"cnr_id": "comfy-core",
"ver": "0.25.0",
"previewExposures": []
"previewExposures": [],
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
},
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
},
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-22b-ic-lora-deblur-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Deblur/resolve/main/ltx-2.3-22b-ic-lora-deblur-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors",
@@ -1044,7 +1076,7 @@
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"gemma4_e2b_it_bf16.safetensors",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltx-2.3-22b-ic-lora-instant-shave-0.9.safetensors",
"ltx-2.3-22b-ic-lora-deblur-0.9.safetensors",
1
]
}
@@ -1592,7 +1624,14 @@
],
"title": "Load VAE - Audio",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-audio-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-audio-vae-bf16.safetensors"
@@ -1635,7 +1674,14 @@
],
"title": "Load VAE - Video",
"properties": {
"Node name for S&R": "VAELoader"
"Node name for S&R": "VAELoader",
"models": [
{
"name": "ltx-2.5-video-vae-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"ltx-2.5-video-vae-bf16.safetensors"
@@ -1677,7 +1723,14 @@
}
],
"properties": {
"Node name for S&R": "UNETLoader"
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"ltx-2.5-22b-distilled-transformer-bf16.safetensors",
@@ -1756,10 +1809,17 @@
],
"title": "Load CLIP - Text Enhancer",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4_e2b_it_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4_e2b_it_bf16.safetensors",
"ltxv",
"default"
]
@@ -1801,10 +1861,17 @@
],
"title": "Load CLIP - Text Encoder",
"properties": {
"Node name for S&R": "CLIPLoader"
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"ViT-B-32.pt",
"gemma4-12b-with-proj-ltx-2.5-bf16.safetensors",
"ltxv",
"default"
]
@@ -1868,10 +1935,17 @@
}
],
"properties": {
"Node name for S&R": "LTXICLoRALoaderModelOnly"
"Node name for S&R": "LTXICLoRALoaderModelOnly",
"models": [
{
"name": "ltx-2.3-22b-ic-lora-deblur-0.9.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Deblur/resolve/main/ltx-2.3-22b-ic-lora-deblur-0.9.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"ltx-2.3-22b-ic-lora-instant-shave-0.9.safetensors",
"ltx-2.3-22b-ic-lora-deblur-0.9.safetensors",
1
]
}
@@ -3103,7 +3177,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - POSITIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - POSITIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -3167,7 +3241,7 @@
]
}
],
"title": "🅛🅣🅧 Gemma API Text Encode - NEGATIVE",
"title": "\ud83c\udd5b\ud83c\udd63\ud83c\udd67 Gemma API Text Encode - NEGATIVE",
"properties": {
"Node name for S&R": "GemmaAPITextEncode"
},
@@ -5428,7 +5502,7 @@
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Source video → guide frames",
"title": "Source video \u2192 guide frames",
"properties": {},
"widgets_values": [
"## Source video\n\nEverything the generation is sized and timed by comes from here. The frames are\nresized to the generation resolution and handed to the IC-LoRA as guide frames,\nand the width, height, length and frame rate are all read off this video.\n\nThe audio track is passed through too, so the result keeps the original sound."
example_workflows/2.5/README.md
+103
View File
@@ -0,0 +1,103 @@
# LTX-2.5 example workflows
These graphs generate video (and usually audio) with the **LTX-2.5 distilled** model. They share the same subgraph layout — load models, set inputs, preprocess, sample, decode — so you can switch files without relearning the graph.
All of them use the distilled transformer (`ltx-2.5-22b-distilled-transformer-bf16.safetensors`): a few sampling steps, meant for fast iteration. Two-stage graphs add a 2× spatial upscale and a short refine pass; single-stage graphs skip that.
Default values are tuned for lower-VRAM machines. If you have more memory, you can speed things up by increasing the **decode tile size** — see the Decode notes inside each graph (fewer, larger tiles run faster but need more VRAM).
## Getting started
This assumes ComfyUI is already installed. If not, see the [ComfyUI download page](https://www.comfy.org/download), the [ComfyUI setup guide](https://docs.ltx.io/open-source-model/integration-tools/comfy-ui), and the [system requirements](https://docs.ltx.io/open-source-model/getting-started/system-requirements).
1. Open ComfyUI.
2. Load a workflow from this folder (**Workflow** → **Open**, or drag the `.json` onto the canvas). The built-in ComfyUI **Templates** search for **LTX-2.5** is the same family of graphs if you prefer that entry point.
3. Open the **Workflow Overview** panel. On first use it lists **Missing Models**.
4. Click **Download all** to fetch the files into the right `ComfyUI/models/` folders. You only do this once — later runs reuse them.
5. Fill in the left-hand **Inputs** (prompt, optional image, duration, and anything the graph asks for such as audio or a reference video).
6. Click **Run**.
Weights also live on the [LTX-2.5 Hugging Face repo](https://huggingface.co/Lightricks/LTX-2.5) if you want to download them by hand. Each graph’s **Model Links** note lists the exact files it needs, including any IC-LoRA.
Prompting tips: [prompting guide](https://docs.ltx.io/open-source-model/usage-guides/prompting-guide). A beginner walkthrough of text-to-video: [Text-to-Video workflow](https://docs.ltx.io/open-source-model/usage-guides/text-to-video).
Frame count must be `1 + a multiple of 8`. Duration in the graphs is converted from fps × seconds and may land slightly off the number you typed.
## Workflows
### Generation
| Workflow | What it does |
| -------- | ------------ |
| [LTX-2.5_T2V_I2V_Two_Stage_Distilled.json](./LTX-2.5_T2V_I2V_Two_Stage_Distilled.json) | **Start here.** Text-to-video, optional first-frame image. Stage 1 at base resolution, 2× spatial upscale, then a 3-step refine. Generates video and audio together. |
| [LTX-2.5_T2V_I2V_Single_Stage_Distilled.json](./LTX-2.5_T2V_I2V_Single_Stage_Distilled.json) | Same text / image inputs, one distilled pass, no upscaler. Faster and lighter; lower spatial detail than two-stage. |
| [LTX-2.5_A2V_Two_Stage_Distilled.json](./LTX-2.5_A2V_Two_Stage_Distilled.json) | Audio-to-video. Encodes an input clip (with start + duration trim), **freezes** those tokens in both stages, and muxes the original waveform into the output (no audio decode). Optional first-frame image. |
| [LTX-2.5_T2A_Single_Stage_Distilled.json](./LTX-2.5_T2A_Single_Stage_Distilled.json) | Text-to-audio only. No video VAE or upscaler. |
### IC-LoRA (control and edit)
These keep the distilled 2.5 backbone and add an IC-LoRA so a guide (video, image sheet, tracks, or mask) steers generation.
| Workflow | What it does |
| -------- | ------------ |
| [LTX-2.5_ICLoRA_Union_Control_Distilled.json](./LTX-2.5_ICLoRA_Union_Control_Distilled.json) | Video-to-video from a **depth / canny / pose** annotator on a reference clip. Depth is wired by default; switch the annotator inside the graph. |
| [LTX-2.5_V2V_ICLoRA_Single_Stage_Distilled.json](./LTX-2.5_V2V_ICLoRA_Single_Stage_Distilled.json) | Video-to-video using the source frames as IC-LoRA guides. Ships with the Instant Shave LoRA as the example; swap the LoRA for other identity/edit LoRAs. Original audio is frozen through. |
| [LTX-2.5_ICLoRA_Ingredients_Single_Stage_Distilled.json](./LTX-2.5_ICLoRA_Ingredients_Single_Stage_Distilled.json) | Generate from a **reference sheet** (characters, props, wardrobe, location laid out in one image). Describe each element in the prompt by its place on the sheet. |
| [LTX-2.5_ICLoRA_Motion_Track_Distilled.json](./LTX-2.5_ICLoRA_Motion_Track_Distilled.json) | Image-to-video with **sparse motion tracks** you draw on the first frame. Optional still as the opening frame. |
| [LTX-2.5_ICLoRA_Inpaint_Two_Stage_Distilled.json](./LTX-2.5_ICLoRA_Inpaint_Two_Stage_Distilled.json) | Fill masked regions of a reference video (two-stage). Source audio can stay frozen. |
| [LTX-2.5_ICLoRA_Outpaint_Two_Stage_Distilled.json](./LTX-2.5_ICLoRA_Outpaint_Two_Stage_Distilled.json) | Extend the canvas of a reference video (two-stage). Same in/outpaint LoRA as inpaint. |
## Which workflow should I use?
```text
Do you only need audio (no picture)?
├─ YES → LTX-2.5_T2A_Single_Stage_Distilled.json
│
Do you have an audio file the video should follow?
├─ YES → LTX-2.5_A2V_Two_Stage_Distilled.json
│ (optional still as the first frame)
│
Do you have an existing video to edit or follow?
├─ YES → What kind of control?
│ ├─ Depth / edges / pose from the clip
│ │ → LTX-2.5_ICLoRA_Union_Control_Distilled.json
│ ├─ Keep the footage, change appearance (identity / style LoRA)
│ │ → LTX-2.5_V2V_ICLoRA_Single_Stage_Distilled.json
│ ├─ Fill a masked region
│ │ → LTX-2.5_ICLoRA_Inpaint_Two_Stage_Distilled.json
│ └─ Grow the frame / canvas
│ → LTX-2.5_ICLoRA_Outpaint_Two_Stage_Distilled.json
│
Do you have stills rather than a video?
├─ YES → A sheet of characters / props / locations?
│ ├─ YES → LTX-2.5_ICLoRA_Ingredients_Single_Stage_Distilled.json
│ └─ NO → Draw motion paths on a first frame?
│ ├─ YES → LTX-2.5_ICLoRA_Motion_Track_Distilled.json
│ └─ NO → Text-to-video with an optional opening still
│ (see below)
│
Text-to-video (optional image)?
├─ Want 2× spatial upscale and a refine pass?
│ └─ YES → LTX-2.5_T2V_I2V_Two_Stage_Distilled.json (recommended)
└─ Want the fastest / lightest run?
└─ YES → LTX-2.5_T2V_I2V_Single_Stage_Distilled.json
```
Two-stage is the better default when you care about spatial detail. Single-stage is for previews and tighter VRAM.
## Comparison
| Workflow | Stages | Upsample | Main conditioning | Best for |
| -------- | ------ | -------- | ----------------- | -------- |
| T2V / I2V two-stage | 2 | 2× spatial | Text + optional image | Default generation |
| T2V / I2V single-stage | 1 | — | Text + optional image | Fast previews |
| A2V two-stage | 2 | 2× spatial | Audio (frozen) + optional image | Video that must match a soundtrack |
| T2A single-stage | 1 | — | Text | Audio-only clips |
| Union Control | 1 | — | Reference video (depth / canny / pose) | Structure-following v2v |
| V2V IC-LoRA | 1 | — | Source video (+ frozen audio) | Appearance edits on existing footage |
| Ingredients | 1 | — | Reference sheet | Cast / props / location from one image |
| Motion Track | 1 | — | Image + drawn tracks | Directed motion from a still |
| Inpaint two-stage | 2 | 2× spatial | Video + mask (+ frozen audio) | Replacing a region |
| Outpaint two-stage | 2 | 2× spatial | Video + mask (+ frozen audio) | Extending the frame |
Python / pipeline equivalents of these ideas live in [pipeline-selection.md](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-pipelines/docs/pipeline-selection.md) in the LTX-2 repo.