Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights)
My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a set of creative tools that make it easier for anyone to make animation. Video models today are too slow/expensive and lack sufficient controls. Creativity is an iterative process. You make, you tweak, you get better. In our opinion, they're not usable yet for storytelling. When we set out to build Linum v3 (our next video model) earlier this year, the primary goal was to bring the
阅读原始来源
来源记录
指标快照
points · 228 votes
2026-11-06 09:45:18.776Z
cumulative since publication
研究分析
变化记录
来源描述：My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a set of creative tools that make it easier for anyone to make animation. Video models today are too slow/expensive and lack sufficient controls. Creativity is an iterative process. You make, you tweak, you get better. In our opinion, they're not usable yet for storytelling. When we set out to build Linum v3 (our next video model) earlier this year, the primary goal was to bring the
版本与成本证据
来源票数: 228 votes (2026年11月6日 UTC; cumulative since publication)；前次同口径记录为 166（2026年11月6日 UTC），两个观测值不等于需求增长。 可供比较的近期同类记录：“Show HN: RenderPixels – Generate images from any AI via MCP, 50 free renders” (Show HN, 2026年11月8日)；“[分享创造] [分享创造] 五子棋模型对外发布，故事模型小试” (V2EX, 2026年11月8日)。主题相近仅用于导航，未核验其是否属于同一需求或独立证据。
适用与受影响对象
先明确变化影响的现有工作流，再判断是否升级。发布热度不证明效果提升；接口、价格或可用性变化也可能增加迁移工作。
缺失的比较信息
待补齐：新旧行为、受影响套餐与地区、生效时间、兼容性、回退路径及同一工作量下的成本。
采用与迁移验证
保存发布或政策原文，对新旧方案运行同一个任务并比较结果与完整账单；若涉及停服，先核验截止时间再安排迁移。