Aller au contenu
WorkflowPrésentéExterne
Ouvrir la source

LTXV - Animating images that typically don't yield good results — v1.0

In this tutorial, we will learn how to animate images using LTXV, specifically those that initially do not yield good results.

Sourcecivitai.com/models/1101366
TâcheImage en imageFamilleLTX-VideoEstimé VRAMNot yet characterizedBClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Présenté
Source
Civitai
Mis à jour
30 août 2026

Description de la source

In this tutorial, we will learn how to animate images using LTXV, specifically those that initially do not yield good results.

The workflow used is a customized modification of the following workflow:

https://github.com/sandner-art/ai-research/blob/main/LTXV-Video/ltxvideo_I2V-motionfix.json

This approach was inspired by the idea of using blur effects to improve results, as proposed by VoidVisionary in:

https://civitai.com/models/1057138

The zip includes: The workflow, a .png image of the Mona Lisa without blur, a .png image of the Mona Lisa with blur and a .psd archive with the edition.

This workflow incorporates a modified version of the VAE created by SpacePXL, which you can find here:

https://huggingface.co/spacepxl/ltx-video-0.9-vae-finetune/tree/main

In this case, I am using ltx-video-v0.9-vae_finetune_all.safetensors , which you should place in the models/VAE folder of ComfyUI.

The model used for LTX is ltx-video-2b-v.0.9.1.safetensors , which should be placed in the models/checkpoints folder of ComfyUI:

https://huggingface.co/Lightricks/LTX-Video/tree/main

The text encoder used is t5-v1_1-xxl-encoder-Q6_K.gguf :

https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main , which should be placed in the models/clip folder of ComfyUI.

This workflow utilizes the following custom nodes:

https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite

https://github.com/city96/ComfyUI-GGUF

https://github.com/logtd/ComfyUI-LTXTricks

Once everything is set up, we will load the initial image of the Mona Lisa. If we use it as is (without blur) and render it, we will get a very limited animation. To enhance the animation, we will simply use a image editor, select the face, copy it, paste it onto another layer, and apply a slight horizontal motion blur. I’ve provided a Photoshop file where the face has been converted into a Smart Object with a horizontal motion blur of 12 applied. I also add the image of the Mona Lisa already blurred.

If we now copy and paste our modified image into ComfyUI, we will see a much smoother and more natural animation.

This technique can be applied to almost any image, and experimentation is encouraged.

What you need

Model files
5.3 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Exigences

Modèles

6

  • CLIPLoaderGGUF

    Possible

    Text encoder · Unknown

  • ltx-video-2b-v0.9.1.safetensors

    Trouvé

    Checkpoint · 5.32 GB · SAFETENSORS · fp16 · full · Unknown

  • ltx-video-v0.9-vae_finetune_all.safetensors

    Non résolu

    VAE · Unknown

  • t5-v1_1-xxl-encoder-Q6_K.gguf

    Non résolu

    Text encoder · Unknown

  • VAEDecode

    Possible

    VAE · Unknown

  • VAELoader

    Possible

    VAE · Unknown

Packs de nœuds

20

  • AddLatentGuide

    Trouvé

    Pack de nœud · Unknown

  • CheckpointLoaderSimple

    Possible

    Pack de nœud · Unknown

  • CLIPTextEncode

    Possible

    Pack de nœud · Unknown

  • ImageResizeKJ

    Possible

    Pack de nœud · Unknown

  • ImageScale

    Possible

    Pack de nœud · Unknown

  • ImageSharpen

    Possible

    Pack de nœud · Unknown

  • KSamplerSelect

    Possible

    Pack de nœud · Unknown

  • LoadImage

    Possible

    Pack de nœud · Unknown

  • LTXAttnOverride

    Trouvé

    Pack de nœud · Unknown

  • LTXFetaEnhance

    Trouvé

    Pack de nœud · Unknown

  • LTXPerturbedAttention

    Trouvé

    Pack de nœud · Unknown

  • LTXVConditioning

    Non résolu

    Pack de nœud · Unknown

  • LTXVImgToVideo

    Non résolu

    Pack de nœud · Unknown

  • LTXVScheduler

    Non résolu

    Pack de nœud · Unknown

  • ModifyLTXModel

    Trouvé

    Pack de nœud · Unknown

  • PreviewImage

    Possible

    Pack de nœud · Unknown

  • SamplerCustom

    Possible

    Pack de nœud · Unknown

  • VHS_LoadVideoPath

    Possible

    Pack de nœud · Unknown

  • VHS_SelectFilename

    Possible

    Pack de nœud · Unknown

  • VHS_VideoCombine

    Possible

    Pack de nœud · Unknown

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Objectif

  • Use this ComfyUI workflow to turn a still image into an LTXV animation, including images that initially produce limited results.

Flux

  • For the Mona Lisa example, the description reports limited animation from the unedited image and smoother, more natural animation after adding slight horizontal motion blur to the face on a separate layer.

Entrées et sorties

  • The download includes the workflow, Mona Lisa PNGs with and without blur, and a PSD archive containing the edit.

Installation

  • The ComfyUI instructions place ltx-video-v0.9-vae_finetune_all.safetensors in models/VAE, ltx-video-2b-v.0.9.1.safetensors in models/checkpoints, and t5-v1_1-xxl-encoder-Q6_K.gguf in models/clip.

Dépendances

  • The description names the custom node repositories ComfyUI-VideoHelperSuite, ComfyUI-GGUF, and ComfyUI-LTXTricks. ComfyUI-LTXVideo is required for AddLatentGuide, LTXAttnOverride, LTXFetaEnhance, LTXPerturbedAttention, and ModifyLTXModel.

  • Node names include LTXVScheduler, LTXFetaEnhance, CLIPTextEncode, CheckpointLoaderSimple, LTXPerturbedAttention, VAELoader, LTXAttnOverride, ImageResizeKJ, ImageSharpen, LTXVConditioning, CLIPLoaderGGUF, and LTXVImgToVideo.

  • Other node names include KSamplerSelect, VAEDecode, LoadImage, VHS_LoadVideoPath, ModifyLTXModel, ImageScale, VHS_VideoCombine, VHS_SelectFilename, AddLatentGuide, PreviewImage, and SamplerCustom.

Configuration

  • The supplied PSD applies horizontal motion blur set to 12 to a Smart Object version of the Mona Lisa's face.

  • You can experiment with slight horizontal blur on other images; the description says the technique can apply to almost any image.

    Suggestion · non vérifié

Précautions

  • Verify the checkpoint filename before setup: the instructions give ltx-video-2b-v.0.9.1.safetensors, while the listed checkpoint filename is ltx-video-2b-v0.9.1.safetensors.

    Suggestion · non vérifié

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipal
civitai.com/models/1101366

Vérifié 20 juil.

Extraits de sources

1 extrait
Note20 juil.civitai.com/models/1101366

Source context: 1185 downloads · Type Workflows · Base model LTXV