LTX-2 19B GGUF 12GB ComfyUI Workflows 5 TOTAL! t2v/i2v/v2v/ia2v/ta2v — Text-Audio-2-Video-V2

This ComfyUI workflow generates LTX-2 video from text, images, short video clips, and audio, with modes for text-to-video, image-to-video, video extension, text-and-audio-to-video, and image-and-audio-to-video.

The workflow lists five paths: text-to-video, image-to-video, video-to-video extension, text-and-audio-to-video, and image-and-audio-to-video.

It includes two audio-enhancement nodes near the end of the workflow.

For text-to-video, provide a text prompt; for video extension, provide a few seconds of video and a prompt to continue it.

For audio-driven paths, provide a text prompt and audio, or an image and audio; the image-and-audio path is described as lip-syncing the result.

For the V2 version, update ComfyUI and comfyui-kjnodes because ComfyUI reorganized where the embedding model loads.

Sugerencia

Before running, check that every listed model file and node pack is installed.

Sugerencia

Listed model files include gemma_3_12B_it_fp4_mixed.safetensors, ltx-2-19b-dev-Q4_K_M.gguf, ltx-2-19b-distilled-lora_resized_dynamic_fro09_avg_rank_175_fp8.safetensors, ltx-2-19b-embeddings_connector_dev_bf16.safetensors, and ltx-2-19b-ic-lora-detailer.safetensors.

Additional listed files are ltx-2-spatial-upscaler-x2-1.0.safetensors, LTX2_audio_vae_bf16.safetensors, LTX2_video_vae_bf16.safetensors, and taeltx_2.safetensors.

Listed ComfyUI node packs are audio-separation-nodes-comfyui, comfyui-kjnodes, and comfyui-logic.

The description specifies at least 12 GB of VRAM and 48 GB of system RAM for the LTX-2 19B GGUF workflows.

The description names an FP4 Gemma text encoder, Tiny VAE previews, and LoRAs.

Before downloading, verify that the version label is Text-Audio-2-Video-V2.

Sugerencia

No license is specified for the source page, so check its terms before reusing the workflow.

Sugerencia