LTX2.3 GGUF Simple i2v + Last Frame 16GB/low vram — v3 — v4

Use this LTXV 2.3 workflow to create an image-to-video clip from an image and text prompt, with a last-frame option and an upscaling path; its graph includes video-combine and image-save nodes.

The 105-node layout includes image loading and text encoding, LTXV video-processing nodes, video combining, and image saving.

The graph includes LoadImage, CLIPTextEncode, VHS_VideoCombine, and SaveImage nodes.

The workflow file is named ltxv23GGUFSimpleI2v_v4.json, and its listed version is v4.

Model files listed with the workflow: 10Eros_v1.4-Q4_K_S.gguf, gemma_3_12B_it_fp8_scaled.safetensors, ltx-2-spatial-upscaler-x2-1.0.safetensors, ltx-2.3-22b-dev_embeddings_connectors.safetensors, ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safetensors, LTX23_audio_

Also listed: LTX23_video_vae_bf16.safetensors and rife49.pth.

Named node items include Bookmark (rgthree), comfyui-kjnodes, comfyui-videohelpersuite, easy showAnything, ImageBatchMulti, ImageResizeKJv2, kijai/ComfyUI-KJNodes, LTXVChunkFeedForward, rgthree-comfy, RIFE VFI, Ryuu_TokenCountTextBox, StringConstantMultiline, UnetLoaderGGUF, VHS_

The author lists two diffuser choices—10Eros_v1.4-Q4_K_S.gguf or ltx-2.3-22b-dev-Q4_K_S.gguf—and says to use both text encoders and keep the distilled LoRA enabled.

The author warns that comfyui_smznodes breaks LTXV workflows and says to disable it if installed.

Before setup, compare the workflow’s listed ltx-2-spatial-upscaler-x2-1.0.safetensors with the author’s ltx-2.3-spatial-upscaler-x2-1.1.safetensors note; the filenames differ.

Suggestion