Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
This is a straightforward workflow for the LTXV 13b Distilled model, designed for quick and easy video generation. The distilled model runs much faster than the full version, but still delivers impressive...
Profil d'exécution
Description de la source
Overview
This is a straightforward workflow for the LTXV 13b Distilled model, designed for quick and easy video generation. The distilled model runs much faster than the full version, but still delivers impressive quality-making it a great choice for rapid prototyping or when you want to generate a lot of videos quickly.
How It Works
Scheduler Steps: You can set the scheduler to use anywhere from 4 to 12 steps .
For image-to-video (i2v) tasks, using 12 steps usually helps retain more detail from your input image.
8 steps is a good general-purpose setting-fast and still pretty accurate.
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.
This workflow is for image-to-video generation with the LTXV 13b Distilled model: it uses an input image to produce a generated video.
The workflow includes scheduling, conditioning, sampling, decoding, and video-combining stages.
Use an input image for image-to-video generation.
The output is a generated video; the described example is 5 seconds long.
The workflow is published by BingiBongi on Civitai.
Its listed base model is LTXV.
The named model files are ltxv-13b-0.9.7-distilled.safetensors, melting_v3_13b.safetensors, and t5xxl_fp16.safetensors.
Named workflow nodes include Add VAE Decoder Noise, BasicScheduler, CheckpointLoaderSimple, CLIPLoader, CLIPTextEncode, KSamplerSelect, and LoadImage.
Other named nodes are LoraLoader, LTXVBaseSampler, LTXVConditioning, RandomNoise, STGGuiderAdvanced, VAEDecode, and VHS_VideoCombine.
Set the scheduler between 4 and 12 steps.
For image-to-video, 12 steps is suggested when retaining input detail matters; 8 steps is described as a general-purpose setting.
Suggestion · non vérifié
Enable Load LoRA for extra effects or style, or leave it off for standard generation.
Suggestion · non vérifié
At 4–6 steps, generation is described as faster, but complex images may drift visually or change style.
Suggestion · non vérifié
No checksum is listed for the named model files; verify the exact files before use.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 433 downloads · Type Workflows · Base model LTXV
If you go lower (e.g., 4-6 steps), the workflow is even faster, but with complex images, the output might drift visually or change style.
LoRA Support: There’s a Load LoRA node included. Enable it if you want to add a LoRA for extra effects or style-otherwise, just leave it off for standard generation.
Speed: On an H100 GPU , this workflow generates a 5-second video (8 steps) in about 11 seconds .
Combining Models: For the best results, you can combine the distilled model with the full LTXV 13b model-use the distilled version for speed, and the full model for final, high-quality renders if needed. But honestly, the distilled model alone is already pretty solid for most use cases.
Estimation des besoins VRAM
Estimation indisponible
9,12 GB sur 1 de 6 fichiers de modèle. Total des fichiers du modèle + 25 % de surcharge de chargement + 2 Go de tampon d'exécution, arrondi à l'unité supérieure.
Exigences
Exigences 17Add VAE Decoder Noise
Non résoluVAE · Unknown
CLIPLoader
Non résoluText encoder · Unknown
ltxv-13b-0.9.7-distilled.safetensors
Non résoluCheckpoint · Unknown
melting_v3_13b.safetensors
Non résoluLoRA · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
VAEDecode
Non résoluVAE · Unknown
BasicScheduler
Non résoluPack de nœud · Unknown
CheckpointLoaderSimple
Non résoluPack de nœud · Unknown
CLIPTextEncode
Non résoluPack de nœud · Unknown
Pack de nœud · Unknown
LoadImage
Non résoluPack de nœud · Unknown
LoraLoader
Non résoluPack de nœud · Unknown
LTXVBaseSampler
Non résoluPack de nœud · Unknown
LTXVConditioning
Non résoluPack de nœud · Unknown
RandomNoise
Non résoluPack de nœud · Unknown
STGGuiderAdvanced
Non résoluPack de nœud · Unknown
VHS_VideoCombine
Non résoluPack de nœud · Unknown
