<h3 id="minimax-h3:">MiniMax H3:</h3>This is part of the <a rel="ugc" href="https://civarchive.com/models/789313/80s-fantasy-movie">80s Fantasy Movie </a>and will be merged there after MiniMax H3 contest. This version is trained on images only (for now) - it's a style LoRA, so its video strength comes from locking every frame to the "80s Fantasy Movie Still" look rather than from motion training.<ul><li>Best results: FL2V or hybrid workflows (T2I → I2V/FL2V).</li><li>Gallery: several T2Videos generated with various workflows, with and without Turbo settings. Note: Turbo LoRAs tend to diminish fidelity - when combining them, raise this LoRA's strength above 1.2 (e.g., 1.2–1.7)</li><li>Showcase: includes 5 pairs of images generated as T2I and then extended with REF2V. You don't need our stills for the first frame - generate it in any image model (Krea 2 here is what I would recommend), then apply this LoRA during REF2V to pull the video into consistent 80s Fantasy style.</li></ul>

80s Fantasy Movie

80sFantasyMovie_minimaxh3_3333584_epoch_10.safetensors

MiniMax H3

This LoRA is designed to capture the distinct look and feel of early 80s fantasy movies.The trigger words are ArsMovieStill, 80s Fantasy Movie Still Recommended usage settings:<ol><li>Your favourite spot.</li><li>Listen to Castle Rat as background.</li><li>Enjoy!</li></ol><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/iWKmiTwjjHA?rel=1" start="0"></iframe></div> MJ7 UPDATE: Building each dataset is a joy, so with the release of MidJourney 7, I naturally started this one again from scratch.This version stays true to the original aesthetic but with improved fidelity and an even stronger 80s vibe.It’s trained on a fresh, carefully curated set of ~250 images, created by referencing the best results from the previous versions. V3 UPDATE: The training dataset has been further expanded to 1,000 curated images, pushing it to the limits of Civit’s on-site training capabilities.This update include broader selection of fantasy environments, mythical creatures, and epic scenes, enhancing the fidelity to the iconic 80s fantasy aesthetic. V2 UPDATE: Added to the dataset a huge amount of Fantasy Characters, beasts and scenes. Use v1 for stronger effects and v2/v3 for better versatility.

Files with SHA256: 396cc7c3aca633b3d42ee954ca70d03d27da3584d30c3e675e4261f041a83fc1