SEFurkan GözükaraSECourses · Generative AI Join onPatreon

Wan 2.1 Video Extension: Text-to-Video Then Last-Frame Image-to-Video

Extending a Wan 2.1 generated video: a 14B 720p text-to-video clip, then its last frame feeds 14B 720p image-to-video, giving a 10 second 1280x720p video.

Our app uses the last frame automatically and has the whole process fully automated; RIFE brings the result to 32 FPS. The prompts and settings of both generations are shared (81 frames, 20 steps, CFG 6, TeaCache, BF16), and MMAudio added the sound.

Updated By Dr. Furkan Gözükara
Tutorial
Wan 2.1 Video Extension: Text-to-Video Then Last-Frame Image-to-Video
Older post. this is an older post kept for reference. The current, maintained version is MiniMax H3 Infinite Video: Make 2-Hour Movies in ComfyUI (0-Shot).

Our Wan 2.1 app has this fully automated : Wan 2.1 Gradio App: 1-Click Install, 4 GB VRAM, T2V, I2V & V2V

Here how it works image : https://ibb.co/b582z3R6

Wan 2.1 Video Extension: Text-to-Video Then Last-Frame Image-to-Video

Then use MMAudio to add sound

Wan 2.1 Video Extension: Text-to-Video Then Last-Frame Image-to-Video (2)

Here initial video

Prompt: Close-up shot of a Roman gladiator, wearing a leather loincloth and armored gloves, standing confidently with a determined expression, holding a sword and shield. The lighting highlights his muscular build and the textures of his worn armor.

Negative Prompt: Overexposure, static, blurred details, subtitles, paintings, pictures, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, cluttered background, three legs, a lot of people in the background, upside down

Used Model: WAN 2.1 14B Text-to-Video

Number of Inference Steps: 20

CFG Scale: 6

Sigma Shift: 10

Seed: 224866642

Number of Frames: 81

Denoising Strength: N/A

LoRA Model: None

TeaCache Enabled: True

TeaCache L1 Threshold: 0.15

TeaCache Model ID: Wan2.1-T2V-14B

Precision: BF16

Auto Crop: Enabled

Final Resolution: 1280x720

Generation Duration: 770.66 seconds

And here video extension

Prompt: Close-up shot of a Roman gladiator, wearing a leather loincloth and armored gloves, standing confidently with a determined expression, holding a sword and shield. The lighting highlights his muscular build and the textures of his worn armor.

Negative Prompt: Overexposure, static, blurred details, subtitles, paintings, pictures, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, cluttered background, three legs, a lot of people in the background, upside down

Used Model: WAN 2.1 14B Image-to-Video 720P

Number of Inference Steps: 20

CFG Scale: 6

Sigma Shift: 10

Seed: 1311387356

Number of Frames: 81

Denoising Strength: N/A

LoRA Model: None

TeaCache Enabled: True

TeaCache L1 Threshold: 0.15

TeaCache Model ID: Wan2.1-I2V-14B-720P

Precision: BF16

Auto Crop: Enabled

Final Resolution: 1280x720

Generation Duration: 1054.83 seconds

↑ ↓ to move · Enter to open · Esc to close · Ctrl K or / to search from any page