# Wan 2.1 14B: High-Fidelity Image-to-Video with TeaCache & GGUF Quantization

> Canonical URL: https://decomfy.com/wan-2-1-i2v-cinematic/
> Architecture: Wan 2.1 14B I2V (Flow Matching DiT)
> Hardware Verification: RTX 4070 (Minimum 12GB VRAM, Recommended 16GB VRAM)

## Overview
Production-grade ComfyUI Image-to-Video workflow running Wan 2.1 14B on RTX 4070 (12GB VRAM). Combines Q4_K_M GGUF, UMT5-XXL FP8 text encoder, and TeaCache temporal acceleration for fluid 16fps cinematic video in under 2 minutes.

## Generation Parameters
- **Resolution**: 832x480
- **Sampler**: uni_pc
- **Scheduler**: simple
- **Steps**: 12
- **CFG Scale**: 5
- **Seed**: 12345

## Positive Prompt
```text
cinematic film lighting, subtle natural breathing movement, slight head turn, soft ambient light, high quality photorealistic 4k
```

## Negative Prompt
```text
low quality, blurry, distorted, jitter, flickering, warped face, bad anatomy
```

## LoRA Adapters
- `wan2.1_i2v_lora_rank64_lightx2v_4step.safetensors` (weight: 0.8)

## Required Model Files
- Standard base model

## 1-Click Terminal Synchronization
Run inside your ComfyUI root directory:
```bash
curl -fsSL https://decomfy.com/api/scripts/wan-2-1-i2v-cinematic.sh | bash
```

Windows PowerShell:
```powershell
irm https://decomfy.com/api/scripts/wan-2-1-i2v-cinematic.ps1 | iex
```

## Programmatic API Endpoints
- Raw Workflow JSON: https://decomfy.com/api/workflows/wan-2-1-i2v-cinematic.json
- Bash Setup Script: https://decomfy.com/api/scripts/wan-2-1-i2v-cinematic.sh
- PowerShell Script: https://decomfy.com/api/scripts/wan-2-1-i2v-cinematic.ps1
- LLM Markdown: https://decomfy.com/api/markdown/wan-2-1-i2v-cinematic.md