[Return]

Report a post

Preview
for the curious, this is all local generation.
-Minimax H3 for the video
-Moss Image to generate reference photos
-Qwen 2.1 Image Edit as a helper to tweak reference photos/screenshots for new shots
main workflow: https://civitai.com/models/2881362/minimax-h3-seed-hunter-latent-upscaler-seamless-video-continuation-speedups-ref-mods?modelVersionId=3337930
secondary workflow: https://civitai.com/models/2947601/simply-advanced-minimax-h3?modelVersionId=3355427 i only use the local LLM prompt generation from this one, the other workflow is better for the actual video generation.
Post number No.31768
Board Artificial Intelligence
Optional. Describe what's wrong with it.