My attempt to create a Wan 2.2 concept lora. Its scope is pretty limited, but I think it works well enough.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4a200c45-1963-4831-8084-146ef84d25af/original=true/4a200c45-1963-4831-8084-146ef84d25af.jpeg" /> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bc46b278-8553-441d-acd3-0d759853f042/original=true/bc46b278-8553-441d-acd3-0d759853f042.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7717a663-f3b6-4040-96a4-b9921ef39e8e/original=true/7717a663-f3b6-4040-96a4-b9921ef39e8e.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/974a33c9-4c93-42d8-a9e1-8a53c077ac26/original=true/974a33c9-4c93-42d8-a9e1-8a53c077ac26.jpeg" /> I'll be honest. Video generation is still pretty arcane to me, so I don't really have advice for. It's a lot more difficult to experiment, and prompting seems to be ancillary to a good starting image, and the right Loras.

Files with SHA256: 3351bc664b052102adfb207f13a52fc2008a76d89446782ffd5e7ef43396c915