ComfyUI Node
LTX 2.3 Image Guides (All-in-One)
All-in-one native LTXV guide node: select images, apply guide metadata, and output guided conditioning plus latent.
LTX 2.3 Image Guides (All-in-One)
- positive
- negative
- vae
- latent
- start_images
- positive
- negative
- latent
◄width768►
◄height512►
◄half_size_first_passfalse►
◄fps24.00►
◄num_frames97►
◄timing_modeframe►
◄resize_modecontain►
◄duplicate_policyerror►
◄pad_color0,0,0►
◄img_compression35►
◄global_strength1.00►
◄lock_start_framesfalse►
◄lock_end_framefalse►
◄start_images_strength0.85►
◄guides_json{"version":1,"guides":[]}►
CategoryLTX 2.3
Inputs (20)
| Name | Type | Default | Description |
|---|---|---|---|
| positive | CONDITIONING | Positive conditioning to augment with native LTXV guide metadata. | |
| negative | CONDITIONING | Negative conditioning to augment with matching native LTXV guide metadata. | |
| vae | VAE | LTXV VAE used to encode selected guide images and optional start image sequences. | |
| width | INT | 76864–16384 | Target output size for this stage. With half_size_first_pass enabled and no latent connected, the internal latent uses half this value. |
| height | INT | 51264–16384 | Target output size for this stage. With half_size_first_pass enabled and no latent connected, the internal latent uses half this value. |
| half_size_first_pass | BOOLEAN | false | For 2x LTX upscale workflows: when no latent is connected, create and guide a half-size first-pass latent. Width/height should be the final target size. |
| fps | FLOAT | 24.001–240 | Frames per second used when timing_mode is seconds. |
| num_frames | INT | 971–16384 | Pixel frame count used for timing, negative frame positions, and internally-created empty latents. Native LTXV lengths must be 8*n + 1, for example 97, 105, 113. |
| timing_mode | COMBO | frame | Interpret manual guide positions as frame indexes or seconds. |
| resize_mode | COMBO | contain | How guide images are resized before VAE encoding. contain/pad preserves aspect ratio with padding. |
| duplicate_policy | COMBO | error | How to handle manual guide images that resolve to the same frame. |
| pad_color | STRING | 0,0,0 | RGB padding color for contain/pad resize mode. Accepts r,g,b or #rrggbb. |
| img_compression | INT | 350–100 | Native LTXV image compression applied before guide encoding. Set 0 to disable. |
| global_strength | FLOAT | 1.000–1 | Multiplier applied to every manual guide strength and start sequence strength. |
| lock_start_frames | BOOLEAN | false | When enabled, frame 0 guides and start_images are written into the beginning video latent instead of only appended as guide references. VAE-level lock, not pixel-perfect copy. |
| lock_end_frame | BOOLEAN | false | When enabled, a manual guide resolving to the final frame is written into the final video latent instead of only appended as a guide reference. VAE-level lock, not pixel-perfect copy. |
| start_images_strength | FLOAT | 0.850–1 | Strength for the optional start image sequence before global_strength is applied. |
| guides_json | STRING | {"version":1,"guides":[]} | Hidden serialized guide data used by the custom UI and saved in workflows. |
| latentopt | LATENT | Optional existing video latent. When connected, its shape is used and half_size_first_pass does not resize it. | |
| start_imagesopt | IMAGE | Optional IMAGE batch from a video source. Applied as a native multi-frame guide starting at frame 0. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |