固定されたツイート
Runflow
265 posts
Runflow
@runflow_io
The missing layer between ComfyUI and production. Visual workflows + developer API + automated quality scoring. Deploy your pipeline, not your weekends.
United States 参加日 Mart 2023
143 フォロー中3.5K フォロワー
Adobe just added Kling 3 and Kling 3 Omni to Firefly - consistent characters across shots is getting surprisingly easy. We support this and 740+ more models through a single API - runflow.io
x.com/icreatelife/st…
Kris Kashtanova@icreatelife
I loved creating this cartoon. Adobe added Kling 3 and Kling 3 Omni to Firefly. For the first time in a while, I had that feeling of “okay… this is getting very real.” Consistent characters across shots used to be the hardest part. This made it feel… easy. Workflow below:
English
Face consistency breaking across scenes is not a Seedance-specific problem. It's a pipeline architecture problem. The base image anchor approach works until your pipeline has multiple models in sequence.
x.com/D_studioprojec…
DStudioproject@D_studioproject
most people struggle to generate human faces consistently on seedance 2.0, especially when relying on character sheets a lot of the time, the system rejects it or the face breaks across scenes so I built a workflow that uses a base image as the anchor instead this keeps the face clean, natural, and consistent while still giving you full control for cinematic shots it’s a small change, but it makes a huge difference when working with human characters another thing I’ve learned, instead of generating scene by scene (which burns a lot of credits), it’s much more efficient to build multiple moments inside one 15s generation you can guide each second with slightly different prompt directions, then refine the final result with manual cut-to-cut editing this way you get more usable footage in one go and still keep control in post try it here: app.flora.ai/techniques/see… @floraai #FLORATechnique
English
Seedance 2.0 just went live in the US - Dreamina's latest video model brings stronger generation and a tighter end-to-end workflow, from text to video in one place.
x.com/nrqa__/status/…
Nelly;@nrqa__
The AI video upgrade we’ve been waiting for just dropped Dreamina Seedance 2.0 is now LIVE in the US 🇺🇸 Stronger model + unified platform = real workflow improvement. From idea → video, all in one place. AI video is getting practical.
English
Seedance 2.0 just launched - adds realistic physics simulation, built-in audio-video generation, and tighter image control. Worth testing if AI video is in your stack.
x.com/I_amShiti/stat…
Kuria | AI@I_amShiti
💥BREAKING: Seedance 2.0 has officially launched on GlobalGPT — now available at 50% OFF! Experience advanced AI video with realistic physics, built-in audio-video generation, and top-tier image control. Accessible worldwide — no limits, no restrictions, no invite codes. 👇
English
Seedance 2.0 from BytePlus just went API-live - production-grade AI video with realistic physics and native audio-video generation in one model. Controllable video generation is moving fast.
x.com/HalimA60962/st…
Jessica AI@HalimA60962
The era of "experimental" AI video is over. Production-grade AI video is HERE. 🚀 Introducing Seedance 2.0 by BytePlus — a massive leap forward in controllable, high-fidelity video generation. And the API is now officially live. You can now direct AI video. Not just generate it. 🎬
English
Seedance 2.0 just topped all three video generation leaderboards on Video Arena - including Image-to-Video and Multi-Image-to-Video. BytePlus shipped something real here.
x.com/Designarena/st…
Design Arena@Designarena
BREAKING: Seedance 2.0 and Seedance 2.0 Fast by @BytePlusGlobal are #1 and #2 on Video Arena, Image-to-Video Arena, and Multi-Image-to-Video Arena! These are defining a new frontier of video generation models Huge congrats to the @BytePlusGlobal team on the launch!
English
Recraft Studio just added five new video models: Seedance 2.0, Seedance 2.0 Fast, PixVerse V6.0, PixVerse V5.6, and Wan V2.7. Good expansion of the video gen toolkit.
x.com/recraftai/stat…
Recraft@recraftai
New video models just dropped in Recraft Studio! We’ve added support for: • Seedance 2.0 • Seedance 2.0 Fast • PixVerse V6.0 • PixVerse V5.6 • Wan V2.7 Explore more ways to create, experiment, and bring your ideas to life with the latest video generation tools.
English
Seedance 2.0 is enabling fully automated AI video UGC pipelines. One prompt, zero editing, production-ready output at scale.
x.com/FynCas/status/…
Cas.Fyn@FynCas
Seedance 2.0 + my AI UGC prompting system = insane results Generated 200+ videos in 24 hours to refine the framework This video = 1 prompt, 1 tool, zero editing Easily the best model I’ve used so far Fully automatable workflow First time high-quality AI UGC can be automated like this If you want me to share the full setup, just comment “UGC”
English
Testing 50 product videos in one afternoon is now a realistic workflow with AI video generation. We support this and 740+ more models through a single API - runflow.io
x.com/maxxmalist/sta…
MAX@maxxmalist
you can really test 50 product videos on TikTok Shop in one afternoon all generated from Marketing Studio on Higgsfield the workflow: - find a product - paste the link - get UGC and product review formats back all TikTok-native the videos look like a real creator filmed them what used to cost $6-11 per video on other platforms, or $500 per video hiring a real UGC creator costs $0.347 per generation now
English
Seedance 2.0 is making full music video production pipelines practical - from prompt to final delivery without the usual fragmented toolchain.
x.com/SheBuildsAI_/s…
Compound Learning - AI | Tech | Science@SheBuildsAI_
Covering the whole workflow from prompt to delivery... Seedance 2.0 is a lifesaver for music video concepts. 🔄
English
Seedance 2.0 as a full ad production pipeline - paste a link, pick an avatar, choose a format (UGC, unboxing, review, TV spot), hit generate. That's the entire workflow. This is where video generation gets actually useful.
x.com/zodchiii/statu…
darkzodchi@zodchiii
The AI video space is full of "look what this model can do" demos. This is different - it's a complete ad production pipeline. > paste a link > pick an avatar > choose a format (UGC, unboxing, review, TV spot) > hit generate > done That's the whole workflow. Seedance 2.0 is the engine, but the studio is the product!
English
Seedance 2.0 API is now live - stronger consistency, more usable workflows, and production-ready video generation for teams that need real control.
x.com/heyDhavall/sta…
Dhaval Makwana@heyDhavall
🚨 AI video is moving beyond experiments. BytePlus just launched the Seedance 2.0 API for creators and teams that need real control. Generate videos with stronger consistency and workflows that feel far more usable. This is what production-ready video AI looks like 👇
English