Seedance 2.5 keeps Midjourney reference style remarkably well in video gen test
CurieuxExplorer · x · 2026-10-17
A user tested ByteDance's Seedance 2.5 video generation model and found it remarkably good at preserving the visual style of a reference image during image-to-video generation. The reference was a Midjourney style image (sref 1181489133), and the result was praised as "incredible" for style consistency.
More from Multimodal
- DeepSeek 4.1 Flash generates a realistic animated grassy hill with sound in one turn — zizhpan · 2026-10-17
- Real-Time Hair Rendering: 100 Characters, 100K Strands Each, Just 1.7 MB — TinfoilTricorn · 2026-10-17
- Strand-Aligned 3D Gaussians Enable Strand-Level Hair Reconstruction — TinfoilTricorn · 2026-10-17
- MOSS-Image gets INT8 quants and a community LoRA fixing SFT banding — tomByrer · 2026-10-17
- Creative AI videos made with Gemini Omni & Flow, prompts shared — michaelrabone · 2026-10-17
- Midjourney style code --sref 1602964516 yields cinematic giant-monster imagery — tisch_eins · 2026-10-17