Lightricks LTX-2.5
This demo is a trimmed LTX-2.5 module within the VideoGen module of the Comfy web UI. Supports High-Level MCP 🤖
LTX-2.5 Text-to-Video
💡 Tip: Under the default ZeroGPU Duration (s) of 60s, tasks with native 768p resolution and 5s duration pass successfully. Under ZeroGPU Duration (s) of 180s, tasks with native 1080p resolution and 5s duration pass successfully.
💡 Tip: When downloading from Civitai, please use the Version ID, not the Model ID. You can find the Version ID in the URL (e.g., civitai.com/models/123?modelVersionId=456) or under the model's download button. When downloading from Hugging Face, please use the format: repo_id/filename.extension or repo_id/folder_path/filename.extension (e.g., Lightricks/LTX-Video/loras/ltx_lora.safetensors).
| Prompt | Negative Prompt | Resolution | Aspect Ratio | Width | Height | Duration (seconds) | FPS | Seed (-1 for random) | ZeroGPU Duration (s) | Use 2x Spatial Upscaler | Use 2x Temporal Upscaler |
|---|
LTX-2.5 Image-to-Video
💡 Tip: Under the default ZeroGPU Duration (s) of 60s, tasks with native 768p resolution and 5s duration pass successfully. Under ZeroGPU Duration (s) of 180s, tasks with native 1080p resolution and 5s duration pass successfully.
💡 Tip: When downloading from Civitai, please use the Version ID, not the Model ID. You can find the Version ID in the URL (e.g., civitai.com/models/123?modelVersionId=456) or under the model's download button. When downloading from Hugging Face, please use the format: repo_id/filename.extension or repo_id/folder_path/filename.extension (e.g., Lightricks/LTX-Video/loras/ltx_lora.safetensors).
LTX-2.5 First & Last Frame-to-Video
💡 Tip: Under the default ZeroGPU Duration (s) of 60s, tasks with native 768p resolution and 5s duration pass successfully. Under ZeroGPU Duration (s) of 180s, tasks with native 1080p resolution and 5s duration pass successfully.
💡 Tip: When downloading from Civitai, please use the Version ID, not the Model ID. You can find the Version ID in the URL (e.g., civitai.com/models/123?modelVersionId=456) or under the model's download button. When downloading from Hugging Face, please use the format: repo_id/filename.extension or repo_id/folder_path/filename.extension (e.g., Lightricks/LTX-Video/loras/ltx_lora.safetensors).
LTX-2.5 Text & Audio-to-Video
💡 Tip: Video duration is determined by the input audio duration. Under the default ZeroGPU Duration (s) of 60s, tasks with native 768p resolution and 5s duration pass successfully. Under ZeroGPU Duration (s) of 180s, tasks with native 1080p resolution and 5s duration pass successfully.
💡 Tip: When downloading from Civitai, please use the Version ID, not the Model ID. You can find the Version ID in the URL (e.g., civitai.com/models/123?modelVersionId=456) or under the model's download button. When downloading from Hugging Face, please use the format: repo_id/filename.extension or repo_id/folder_path/filename.extension (e.g., Lightricks/LTX-Video/loras/ltx_lora.safetensors).
LTX-2.5 Image & Audio-to-Video
💡 Tip: Video duration is determined by the input audio duration. Under the default ZeroGPU Duration (s) of 60s, tasks with native 768p resolution and 5s duration pass successfully. Under ZeroGPU Duration (s) of 180s, tasks with native 1080p resolution and 5s duration pass successfully.
💡 Tip: When downloading from Civitai, please use the Version ID, not the Model ID. You can find the Version ID in the URL (e.g., civitai.com/models/123?modelVersionId=456) or under the model's download button. When downloading from Hugging Face, please use the format: repo_id/filename.extension or repo_id/folder_path/filename.extension (e.g., Lightricks/LTX-Video/loras/ltx_lora.safetensors).