One continuous 40-50 second shot out of MiniMax H3 segments of 4-6 seconds, made on an RTX 4070 SUPER 12 GB. Face, outfit and colour hold to the end, and the seams don't show. The two videos here are the same cafe scene, photoreal and comic, 8 segments each.How it works: each segment continues from the latent tail of the previous one (FeiHou Easy H3, 接续 continuation, 22+22 frames), so motion carries over the seam. Segments 2 to N run in reference mode with the face reference and the establishing image, and every segment text repeats the full outfit and describes the props by their state.In the archive:<ul><li>UI workflows for segment 1 and segment N, with a note inside each on what to set;</li><li>the same graphs in API format;</li><li>the planner system prompt (paste it into any chat assistant and get the segment texts) and the plan of the cafe scene;</li><li>scripts: plan linter, chain runner over the ComfyUI API, seam and freeze checks, face similarity, review sheets.</li></ul>Needs: ComfyUI with FeiHou Easy H3 and FeiHou Toolbox, KJNodes, MiniMax H3 Remix v0.8, the H3 text encoder and VAEs from Comfy-Org/MiniMax-H3, the H3 latent upscaler. ReActor only if you swap the face on the first frame.Time on a 4070 SUPER with 96 GB RAM: about 1.5 minutes for segment 1, 2.5-3.5 minutes for every continued segment.The full method, by hand or with an agent: <a href="https://civarchive.com/articles/38141" rel="ugc">https://civarchive.com/articles/38141</a>

MiniMax H3 long take: one 40-50 s shot from chained segments (12 GB)

First release: the cafe scene plan, UI and API graphs for segment 1 and segment N, planner prompt, scripts.

Files with SHA256: d2d8001e322934694938aeb7d724225080e340dde25eb0c115b2bf0cb083d675