Furkan Gözükara
patreon
Extending Wan 2.1 generated video - First 14b 720p text to video, then using last frame automatically to to generate a video with 14b 720p image to video - with RIFE 32 FPS 10 second 1280x720p video - Our app has this fully automated
🕑 Added 2025-03-20 02:33:46 +0000 UTCOur Wan 2.1 app has this fully automated : https://www.patreon.com/posts/123105403
Here how it works image : https://ibb.co/b582z3R6
Then use MMAudio to add sound
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
Comments
Furkan Gözükara
yes this works perfect you can try
Steve
When wan2.1 first came out i was using vlc to take a snapshot of the last frame, using that for the same prompt and then using avidmux to join all the videos together, it did have slight issues with keeping the same brightness and colour saturation between the videos, hopefully this way it maintains them for a more clear unsegmentated video
Furkan Gözükara
it is exactly working that way. you can set extending count to 4 to get 20 sec :D
Hasan Haque
Thanks for extending it to 10s. Is it possible to make it Image to Video -> last frame -> next video -> last frame -> next video (and So on) with a continuous single prompt / prompt separately for each 5s? Or am I asking too much? :D
Furkan Gözükara
awesome
Klaus The.
Yes, the folder was created automatically while the installation and for a test i also cloned this folder into /models/LoRAs ... the "Refresh LoRAs" button can't find newly uploaded models. But when I completely restarted the pod the GUI listed the model and now the button works :-)
Furkan Gözükara
linux is case sensitive is your folder name exactly as LoRAs
Klaus The.
On Runpod, the installation of the WAN UI went very smooth, also the model downloader does it's thing. The only issue I have is that no LoRa is listed in the Lora-dropdown, even tho I downloaded some LoRA in the LoRas folder.
Furkan Gözükara
well yes you have to edit it. currently it will use last frame to extend
cool1
Thanks. I'll try that then later. So the video we want to extend can be put in "video to video" but we can't choose the frame where we want to extend from (so we'd need to edit it in a video editor first if the last frame looked bad and we didn't want to extend from that originally created last frame). I thought the video to video option was for where it altered the whole video though (where it created a whole new video based on the original video with some changes based on the prompt). Though maybe it doesn't work like that when the extension option is used.
Furkan Gözükara
ye let me update it will take last frame sorry mistaken :D
cool1
Thanks. So we put the input video to extend in "image to video" (that says "only for 1.3b"). Or do we put the input video to extend somewhere else like the "drop image here" box? You said "it will pick the first frame and extend it". I thought it would extend from the last frame of the source video. Though it might be messed up at the end and the middle frame of it might be better. Though if we can't choose the frame to extend from the video could be edited in a video editor before uploading it whatever section it needs to be uploaded and then it could be extended.
Furkan Gözükara
well give me more info. did you download models?
Furkan Gözükara
you can use existing video in video upload and extend it. now it picks first frame and extend. so select image to video model, upload video to video upload and click, it will extend it I will work on adding different prompt for each extension with || separator
Furkan Gözükara
you can use existing video in video upload and extend it. now it picks first frame and extend. so select image to video model, upload video to video upload and click, it will extend it I will work on adding different prompt for each extension with || separator
Nobodys Hero
agreed would be better to choose after initial first generation
Göran Burlin
got this error: TypeError: object of type 'NoneType' has no len()
cool1
Thanks for the update. For the "extension video factor (1=no extension)" it might be simpler if 0=no extensions, 1=1 extension). If you set it up so before you've generated the video at all that you set it to generate the video and extend it once, then you won't know if the initial video will come out well enough and whether the last frame of the video is good quality enough to continue with (by the last frame of the original video it might be too messed up and not worth extending). Also if it uses the same prompt for the extension wouldn't that make it likely to try to repeat the actions that were done in the original video even if it wasn't what was wanted (eg. prompt was "person does x and then person does y". Each extension would try to make them do x and then y again if they use the same prompt). It might be that half-way through the video things looked okay but by the end frame the video didn't look good enough. For extending the video you could wait until you've generated the first section and then the user could be allowed to pick the last good frame that they want to continue from (eg. half way through the video) and have the ability to enter a different prompt (so it wouldn't try to repeat what was done originally if that wasn't what was wanted).
