Perfil de ejecución
Descripción de la fuente
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
LTX 2 VIDEO DETAILER is for detailing 5- or 10-second 1280 × 720 videos and supporting temporal consistency. It takes a video as input and outputs a detailed video without changing the resolution.
Use the 5-second workflow for a 5-second video or the 10-second workflow for a 10-second video. The description covers 1280 × 720 input and says the output resolution stays the same.
The setup description names the Vantage GGUF Unet Loader node from VantageWithAI, Vantage-Nodes, its requirements, and a ComfyUI restart.
Using the 5-second workflow for a 10-second video may require 32+ GB RAM; before running, verify that ltx-2-19b-distilled-lora-384.safetensors and ltx-2-19b-ic-lora-detailer.safetensors match the intended model types.
Sugerencia · sin verificar
The listed node packs are comfyui-videohelpersuite, RES4LYF, comfyui-easy-use, ComfyLiterals, ComfyUI-LTXVideo, comfyui-florence2, and ComfyUI-GGUF.
The listed model and file names are gemma_3_12B_it_fp8_e4m3fn.safetensors, ltx-2-19b-distilled-lora-384.safetensors, ltx-2-19b-ic-lora-detailer.safetensors, ltx-2-19b-embeddings_connector_dev_bf16.safetensors, ltx-2-19b-dev_Q4_K_M.gguf, LTX2_video_vae_bf16.safetensors, LTX2_video
The setup description suggests a dedicated LTX-2 launch file with --lowvram, --disable-xformers, --use-pytorch-cross-attention, --reserve-vram 2, and --disable-smart-memory.
Sugerencia · sin verificar
If the machine struggles with this resource-intensive workflow, the description suggests lowering the working resolution to 480p.
Sugerencia · sin verificar
The description calls this a test workflow, says artifacts may still appear, and reports testing on 16 GB VRAM; results for other hardware are not stated.
After repeated runs, black or red-grid output is attributed in the description to VRAM throttling and may call for a PC restart; switching between the 5- and 10-second workflows may also require closing and reopening ComfyUI because the VAE encoding method and cache differ.
Sugerencia · sin verificar
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
2 extractosSource context: 894 downloads · Type Workflows · Base model LTXV
Models :
This workflow simply works as a detailer, worked for temporal consistency.Video resolution will not change. Works for 1280 x 720 5second and 10 second videos. There is a comparison video on civitai.
-Tested on 16GB VRAM.
Two workflows attached in zip folder, First one is for 5 second videos. The other is for 10 second. If your ram is good enough (32+), you can make 10 second video on 5 second workflow too. In that case sampling time will decrease.
But it is a test workflow, not claiming it to be the best, artifacts still appear. If you get it done and your output video is like black or red grids,(Usually happens after you make like 10 20 videos). That means you need to restart your PC, because of VRAM throttling.
If you make video from like 5 sec workflow and shift it to 10 sec workflow and press run, you will get black screen or something like that. It is because different vae encoding method and cache, you need to close and open comfy.
Test results (16GB VRAM):
Workflow needs different LTX installation process - Follow the process below :
Download the custom nodes from the workflow below, There is also video explanation for the nodes and models Quantized models used. Reference video to watch (Not mine) :
Models :
Red Nodes under :
-a custom node from VantageWithAI named "Vantage GGUF Unet Loader" node
this node is experimental but more efficient than the regular unet GGUF nodes. (there is a PR pull missing from the GGUF nodes at the moment and until it is merged fully the node wont work without updating it in your command prompt yourself. i dont suggest as it is highly unusable. trust me, use the Vantage node.)
TO GET THE VANTAGE NODES, open a command prompt in your custom nodes folder and copy in this command and hit enter:
(i removed the "cd comfyui/custom_nodes" portion from the youtube video tutorial as its not needed)
use this command once its finished:
cd Vantage-Nodes
pip install -r requirements.txt
this installs the nodes fully. restart comfyui and you drag in my workflow and you have a fully functioning LTX-2 workflow!
I HIGHLY RECOMMEND UPDATING YOUR BAT FILE WITH THESE FLAGS:
--lowvram --disable-xformers --use-pytorch-cross-attention --reserve-vram 2 --disable-smart-memory
this workflow is very resource intense. even for the lowest quant my pc struggled until i lowered resolution to 480p. i suggest editing your bat file in notepad and just adding the flags to the code line that contains the "--windows-standalone" code and just save the file as a copy and use that one for LTX-2 ONLY. (rename it that if it helps you remember) instructions on how to do it are in the youtube video if you dont know how!
Workflow made by AITold.
Requisito de VRAM estimado
Estimación no disponible
26,5 GB en 3 de 7 archivos de modelos. Total de archivos de modelos + 25 % de sobrecarga de carga + 2 GB de margen de ejecución, redondeado hacia arriba.
Requisitos
14 requisitosgemma_3_12B_it_fp8_e4m3fn.safetensors
EncontradoText encoder · 12.3 GB · SAFETENSORS · fp16 · full · Hugging Face · GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn
Checkpoint · 11.8 GB · GGUF · Hugging Face · Kijai/LTXV2_comfy
LoRA · Civitai · 2291679
Fuentes posibles
ltx-2-19b-embeddings_connector_dev_bf16.safetensors
No resueltoText encoder · Unknown
ltx-2-19b-ic-lora-detailer.safetensors
EncontradoLoRA · 2.44 GB · Hugging Face · Lightricks/LTX-2-19b-IC-LoRA-Detailer
LTX2_video_vaeold_bf16.safetensors
No resueltoVAE · Unknown
Vision model · Hugging Face · microsoft/Florence-2-large · Florence 2 Large
Paquete de nodos · Registry
Paquete de nodos · Registry
comfyui-florence2
Source context: 865 downloads · Type Workflows · Base model LTXV
Paquete de nodos · Registry
ComfyUI-GGUF
PosiblePaquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry