Last Imageisteğe bağlı
Optional last image to condition the video generation. If provided, creates smoother transitions between frames.
Num Framesisteğe bağlı
Number of video frames. 81 frames give the best results
Resolutionisteğe bağlı
Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
Frames Per Secondisteğe bağlı
Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
Interpolate Outputisteğe bağlı
Interpolate the generated video to 30 FPS using ffmpeg
Go Fastisteğe bağlı
Go fast
Sample Shiftisteğe bağlı
Sample shift factor
Seedisteğe bağlı
Random seed. Leave blank for random
Disable Safety Checkeristeğe bağlı
Disable safety checker for generated video.
Lora Weights Transformeristeğe bağlı
Load LoRA weights for the HIGH transformer. Supports arbitrary .safetensors URLs from the Internet (for example, 'https://huggingface.co/TheRaf7/instagirl-v2/resolve/main/Instagirlv2.0_hinoise.safetensors')
Lora Scale Transformeristeğe bağlı
Determines how strongly the transformer LoRA should be applied.
Lora Weights Transformer 2isteğe bağlı
Load LoRA weights for the LOW transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA. (for example, 'https://huggingface.co/TheRaf7/instagirl-v2/resolve/main/Instagirlv2.0_lownoise.safetensors')
Lora Scale Transformer 2isteğe bağlı
Determines how strongly the transformer_2 LoRA should be applied.
