dopamines

@mark_k when 14 July, tomorrow?

Seedance 2.5 release is imminent from ByteDance

@johnAGI168 还是有些AI感 皮肤的质感 估计还是要糙一些

Seedance 2.0 满血版效果👇 完美无瑕，这质感，这匹配剪辑效果，不告诉你是 AI 生成的，真的能够看得出来是 AI 吗 ❓

@aisearchio when api to public?

What are some prompts you'd like me to test for Seedance 2.5?

@johnAGI168 是的啊 真怀念原来勃勃生机 万物竞发的时间 自断臂膀的sora 严重掉链子的deepmind 没一个能打的

消失的视频大模型 一个很诡异的想象，自从 Seedance 2.0 发布以来，其他视频模型好像几乎销声匿迹了一样，几个月过去了没有哪家视频模型更新迭代的。 现在 Seedance 2.0 马上更新到 Seedance 2.5 去了，像之前什么可灵，海螺Minimax，runway，luma，veo 都是你方唱罢我登场，今天这个更新，明天那个又更新，都不会说是给哪家一家独大的。 几个月过去了，都没有说哪一家能够赶得上Seedance 2.0的，更别说之后的 Seedance 2.5 了。好像这些模型一夜之间就突然消失了一样，就再也没有更新了，也没有说是新功能啊，新模型这些。 现在还有人使用其他那些模型吗？

@IamEmily2050 deepmind sucks too

What is happening at Meta? Open source models are better than Muse Spark, and now ByteDance is moving ahead with Seedance V2.5 and Seedream 5 Pro. What exactly are all the talented people doing with all the GPUs and data?

@JSFILMZ0412 @yvesai0 what and when?

@yvesai0 not even close

Comparing Seedance 2.0 vs. Kling 3.0 Turbo Which one wins your workflow? Dropping my full initial review in the comments soon!

@johnAGI168 和sd2.0差多少？

Seedance 2.0 Mini 首发了！ 感觉就是和 fast 版本一样，但是便宜快一点！ 一把折扇横扫千军。prompt 👇 【风格】东方玄幻真人特效大片（Oriental Fantasy Live-Action Blockbuster），IMAX电影画质，8K超清，真实摄影（Photorealistic），虚幻引擎5写实渲染，达芬奇高级调色，暗黑战场氛围，无动漫感、无塑料感 【时长】15秒 【场景】末世焦土战场，龟裂的暗红色焦土，阴霾的暗灰色天空，背景千军万马的杂兵剪影（无需逐个描述） 【角色】白衣女侠（一袭白衣，手持折扇，绑带高跟鞋，长发，气质清冷孤傲，脸部毛孔与发丝清晰可见） [00:00-00:01] 镜头1：天降神兵（Crash Landing / Speed-Ramp） 大远景：一道金色发光粒子光柱从阴霾天空极速下坠。 落地瞬间切入极致慢动作（Super Slow-mo），特写穿绑带高跟鞋的足部重重踏在龟裂焦土上，扬尘炸开、地面碎裂向四周辐射。 [00:01-00:02] 镜头2：折扇起手式（Power Burst / Wide） 全景固定机位：白衣女子在千军万马前单腿旋转，折扇横扫扫出一道巨大的金色环形冲击波，四周沙尘被掀起。暗黑战场被金光照亮。 [00:02-00:05] 镜头3：横扫千军（Tracking + Motion Blur） 中景转全景，镜头紧跟人物流畅移动，强烈动态模糊。 白衣女子如舞蹈般在敌阵中穿梭挥扇，身姿轻盈，扇影带出金色气刃轨迹。杂兵接连被气浪掀飞腾空，击飞瞬间局部切入慢动作。灰暗战场中白衣与金光是绝对视觉中心。 [00:05-00:07] 镜头4：分身压制（Bullet-time / Low-angle Push-in） 全景低角度仰拍，镜头极慢向前推进（子弹时间）。 女子单腿傲立、折扇张开，身后幻化出多个同步动作的白衣残影分身。背景大量杂兵被定格悬浮在半空，空间出现轻微扭曲感。神明降临般的压迫感。 [00:07-00:09] 镜头5：神女法相（Epic Scale / Slow Tilt-up） 大远景轻微上摇：女子立于画面正中，背后拔地而起一尊巨大的半透明发光神女法相，双手合十后凝化出一柄巨剑。杂兵如蝼蚁冲向法相。 特效：全息半透明粒子法相，神圣的蓝白与幽蓝能量光辉。色调由金灰转为冷白幽蓝。 [00:09-00:11] 镜头6：火龙吞噬（Hollywood VFX / Handheld Shake） 远景转大远景，镜头随爆炸剧烈震动（手持碎震）。 地面炸开红色裂纹，多头烈焰火龙从地裂中喷涌而出，瞬间引发核爆级爆炸，掀起震天动地的巨大蘑菇云。女子立于爆炸中心前，身姿渺小却岿然不动。火红与黑灰浓烟交织。 [00:11-00:14] 镜头7：废墟漫步（Slow Push-in） 大远景转中全景，平稳缓慢推镜，与前段激战形成反差。 女子手持折扇，在燃烧的废墟与漫天红黑浓烟中向镜头从容走来，空气中漂浮的火星与灰烬缓缓飘落。胜利者的孤傲。 [00:14-00:15] 镜头8：清冷回眸（Near Shot / Subtle Breathing） 中景转近景，固定机位近乎静止，仅微风拂动。 女子直视镜头，表情平静清冷，毫无战后波澜。逼真的衣物与发丝物理风动模拟，背景烟雾柔化。冷灰冷蓝主导，空灵收尾。

@IamEmily2050 @BrentLynch With ByteDance releasing Seedance 2.0 in a bid to seize the crown of video generation, OpenAI seems to be self-sabotaging, while Gemini is hesitating and making little progress—truly strange.

@BrentLynch 20% improvement with one click extend is a good update, but this means SD2.5 end of October or November.

Wait? Is this Seedance 2 Mini? The mystery Seedance 2 model IS HERE! No wait this time. About 55% of the cost of the 2.0 Fast is about 75% Quality wise they say to expect Fast level output and that seems fair? Thoughts? Left is Seedance 2 Mini Right is Seedance 2.0 Full Prompt Image To Video Use the uploaded images as identity, costume, and lighting reference. Same naturally confident charismatic age 25 woman throughout performing a sold-out arena concert. Real concert documentary feel, handheld camera energy, practical stage lighting only. gritty, real, fun, clean editing, english language high energy modern concert performance 0: 00–0:01 — Open tight on her face mid-performance, eyes bright, genuine laugh breaking through a lyric, hair catching stage light. Crowd noise swells under faint mic hum. 0: 01–0:06 — She steps forward to the edge of the stage, singing into the mic with playful energy, she frowns, sad "Wait! Is this Seedance 2 Mini?" and then smiles and laughs free hand reaching out toward the crowd, fingers brushing toward raised phones and hands. The crowd repeats the lyric back to her as she laughs. Warm stage lights and lens flares in the background, slight handheld camera sway following her movement. 0: 06–0:09 — Wide shot from a low angle near the crowd barrier — she's framed against haze and colored stage lights, band visible in soft focus behind her (guitarist stage left, keyboard player stage right). She throws her free arm out wide, laughing between lines, hair whipping slightly as she turns. 0: 10–0:12 — Cut to a closer three-quarter shot — she playfully points the mic toward the crowd for a sing-along moment, grinning, eyes scanning the audience with real warmth and connection. Visible sweat sheen, natural skin texture, slight camera shake as if shot from the pit. — Final beat: close-up, she looks directly into the lens with a bright, genuine smile Camera: handheld documentary-style movement throughout, natural focus pulls, no perfectly smooth gimbal shots, slight shake and imperfection consistent with a real concert film crew. Practical stage lighting only — no CGI glow, no artificial bloom, no glossy skin, visible natural texture and sweat under hot lights. Audio: live arena ambience — crowd roar, cheering, phone-camera flash pops, her voice carrying clearly over a full live band mix (electric guitar, keys, drums, bass). No studio polish — natural live-mix dynamics, slight room reverb. No on-screen text, no logos, no subtitles, no watermarks, no identity drift, no extra performers beyond the band already in frame, no slideshow stillness, no overly smooth or glossy rendering, no jarring cuts, no akward moments, no jerky moves, no duplicates, no clones

@liyue_ai 降级到0.120

Codex的 /压缩 功能是不是坏掉了？ 就没压缩成功过。。。

@JSFILMZ0412 不要再继续羞辱google了

Google promised that Gemini Omni Flash would change the game, but when you put it side-by-side with Seedance 2.0... it’s not even a fair fight. Fingers crossed for Veo4

@bindureddy 太搞笑了 一个都没对

Google I/O Predictions - new video model, Veo 3.5 - Nano Banana 3 - Flash 3.2 - Gemini Pro 3.5 Gemini beats GPT 5.5 at coding

@dotey 全线拉垮 本来靠着veo和nb还有亮点

Gemini 2.5 Pro 之前，Google 模型没有超过 GPT-4 的好么 现在 Gemini 又开始掉队了……

@hq4ai 不是一般的拉

毫不意外，相当一般。

@alisaqqt any info of veo4

Seedance 2.1 and Seedance 2.0 Mini are coming soon. Two things worth watching: - Seedance 2.1 reportedly brings a ~20% improvement in generation quality over Seedance 2.0. - Seedance 2.0 Mini is said to be a lighter version that performs better than Seedance 2.0 Fast, with an expected price of around $0.073/sec.

@samaidirector @Gdthainakub @VraserX If this is really the case, DeepMind might as well disband on the spot.

@Gdthainakub @VraserX Both options are bad. If we don’t have veo4, did Google make us wait a year for nothing? And if it is, did you make us wait for nothing?

Looks like Gemini / Veo 4 is getting its own version of Sora 2’s Cameo feature. Honestly, that is genuinely cool. I dearly miss Cameo. Dropping yourself into AI video was one of the most fun and human features Sora had.

@berryxia 就这，超越sd2，看流出的视频，差太远了

Gemini 视频Veo4.𝕏 ？ 要来了,期待超越SD2啊！兄弟们~~

@Waguri_Kaoruko8 @nicdunz yes，the model sucks

@nicdunz That's bad 👎 and internally it's called VEO4. It's just that not everyone wants to admit it. I've seen leaks with its internal name, and they say "VEO4."

gemini omni model video generation

@xiaohu 有veo4么 不要是那个omni的模型 另外有NB新版本么

今天出发去硅谷参加Google I/O大会 根据目前我看到的一些资料 本次大会会有很多猛料，各种新模型和新的产品要发布，还有Google面向编程方面也要发力了… 有木有硅谷面基的𝕏友🫡

@gorkem Please put more effort into maintaining the CDN's download speed and the model's stability.

your gpus deserve the prettiest dashboards #aggregate-analytics-components" target="_blank" rel="nofollow noopener">fal.ai/docs/changelog…

@Mho_23 You're kidding, right? The quality is this bad? It's still nowhere near SD2.

Veo 4 vs Seedance 2.0 social media is cooked Veo 4 looks like it will be much better than Seedance 2.0 and it's an omni model which means consistent voice references and image inputs just like Seedance what a time to be alive.. Prompt: A professor writes out a mathematical proof for trigonometric identities on a traditional chalkboard, explaining the step he is currently on in the equation.