Visiblemakers (@visiblemakers) header
Visiblemakers (@visiblemakers) profile picture

United AI Filmmakers Group, dedicated to rAIsing visions and transform film experiences. Founded by The @visiblemaker

in between atoms
Joined February 2023
Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)Photo by Visiblemakers (@visiblemakers)
Excited to share a Veo2 short by @visiblemaker - a parody car commercial that takes a different road: What happens when you swap gigabytes of data for a bit of grit? 🚀 Hope you enjoy the ride, and be sure to watch until the very end. ;) @GoogleDeepMind @elevenlabs #Veo2
3
2
12
857
Visiblemakers retweeted
Turn Grok Bot into your own AI lab, right from your phone. • Connect @bot to the Overmind MCP • Upload a dataset of examples to learn from • Tell it what to learn and let it fine-tune the model Over to you: overmindlab.ai
130
29
102
395
773,980
Visiblemakers retweeted
Today, we’re excited to share Enact, a research preview of scenes that respond to you. Enact represents a new way of making AI video, one that’s designed to mimic the experience of directing on set. Built on Pika H3 Flex, it allows a creator to interact with “actors,” manually re-stage a scene, and manipulate the camera—all in real time. We think this is the beginning of a new paradigm for creation. Read more and reach out for a demo below.
256
290
272
2,224
584,584
Visiblemakers retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2,367
7,254
5,755
55,908
10,093,556
Visiblemakers retweeted
If your AI characters sound fake, the fix is almost always in how you write and DIRECT the dialogue in your prompt. I recently started on the dialogue-heavy scenes for my AI feature film about Beethoven, and too many of the lines kept coming out wrong. They’d sound too theatrical, too monotone, or too much like a practice read-through between actors. (all this despite the fact that Seedance 2.5 is fantastic when it comes to realism.) So through a whole lot of trial and error, I've found that these 5 things made the biggest impact on the quality of the dialogue delivery in my generations: 1. Paying close attention to the written punctuation used. 2. Breaking long lines into shorter ones, with intentional pauses. 3. Using bodily actions as punctuation (this one gave the biggest improvement BY FAR! In the attached clip, note the sniffles in between Beethoven's lines. That alone made the delivery feel much more natural.) 4. Using "anchor gestures" (he lifts his finger as if to say "one sec") 5. Just split your generations in two (stupid simple, but it really makes a difference.) So if your characters keep sounding like they're reading from a teleprompter, give this a try!
235
253
166
4,363
756,879
Visiblemakers retweeted
Introducing Suno MCP Beta Create songs from wherever you get inspired. No tab-switching needed. Get early access: sunomusic.typeform.com/to/JM…
🤖 Made with AI
154
294
296
1,975
414,406
Meet Dessa, our AI model trained from scratch on nothing but speech. We believe speech is the natural interface for technology. So we built Dessa. And we’re inviting AI safety researchers to explore Dessa. Learn more: block.xyz/dessa
136
126
101
1,350
953,028
Visiblemakers retweeted
ByteDance Seedream 5.5 coming soon with big improvement. 100 Layer Scene Decomposition (Up from 10+ in 5.0 Pro): Splits dense posters, presentation slides, and motion templates into up to 100 individual raster layers with automatic occlusion inpainting behind extracted foreground objects. 80+ Rounds of Drift Resistant Local Editing: Locks unedited pixels (product geometry, facial identity, brand labels) across 80+ sequential single-variable editing passes (background swap -> relighting -> material change -> text addition) to minimize VAE re encoding degradation. Native 4K Output at 16:9 (Up from 2K Cap in 5.0 Pro): Generates native ⁠3840x2160⁠ widescreen frames, eliminating the 2K (⁠~2.36MP⁠) resolution bottleneck on 5.0 Pro for widescreen banners and multi panel storyboard grids. Native 4 Channel RGBA Generation (With Partial Alpha): Outputs true transparent PNG assets directly from the initial prompt, supporting semi transparent alpha values for glass refraction, soft contact shadows, sheer fabric, and fine hair strands without post generation background removal. Optical Font & Style Recognition for Text Re-Rendering: Reads existing font families, weights, colors, and layout hierarchy inside an image so you can translate or swap campaign copy (across English, Chinese, Japanese, and Thai) and re render matching typography in place. Sub Headline & Micro Copy Multilingual Fidelity: Sharpens stroke accuracy on dense, small-scale text specifically pricing, units, dates, bottle volume markings, and promotional fine print where 5.0 Pro was limited to larger poster headlines. Relighting Consistent Material & Portrait Shaders: Upgrades surface physics for ceramic micro texture, brushed metal anisotropy, glass refraction, and skin pores so that shifting lighting conditions (such as daylight to nighttime) updates reflections and contact shadows without smoothing skin texture or warping product labels. Role Assigned Multi Reference & Negative-Space Planning: Formalizes reference routing by assigning distinct jobs to each input image (Reference A = subject identity, Reference B = color palette, Reference C = pose, Reference D = layout) while automatically reserving clean negative space for headlines and CTAs.
27
19
5
283
21,079
Visiblemakers retweeted
Back in the day, I used to spend countless hours in @UnrealEngine trying to make films and games. Now with @claudeai , I have made that a reality 👀 But don't be fooled by those hype posts that it just builts amazing stuff in an hour. It's a supercharged dev partner but it still takes a lot of work. Just like how AI has made filmmaking more accessible so more stories can be told and from anywhere in the world, same I think is about to happen with games. For this game I used @unity (as it was a bit lighter for my poor macbook pro) and combine that with @MeshyAI and @Blender , I got something pretty fun as a start! - We are entering an era where IP can expand so much bigger and wider. This game can now easily be turned into a movie, a series, real toys, TCG etc. (Just watch what @garyvee did with @veefriends)
2
2
9
192
Visiblemakers retweeted
Meet Seedance 2.5 4K. 🎬 The most capable model in the Seedance 2.5 generation brings more nuanced facial expressions and movements, alongside richer visual detail. With Draft mode, creators can test storyboards and refine shots using lower-cost 480p previews, then generate the final version in 4K once they’re happy with the result. Currently available to selected enterprise customers. Stay tuned for updates on API availability. Watch its screen debut in “Otter is Nobody 2” below.
82
85
63
942
111,071
Visiblemakers retweeted
Light tells the story too, change it anytime with Video Relight → The still, in Magnific One → The motion, with Seedance 2.5 → The light, from flat daylight to colored night Full workflow below 👇
7
9
3
42
4,306
Visiblemakers retweeted
Introducing SKY-001, the first Engineering World Model. On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested: -> 51-125x faster - > 150-210x cheaper -> Higher IOU than all frontier models SKY-001 lets you dream a physical object before you build it. 18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch). The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
827
2,404
655
16,004
5,028,693
Visiblemakers retweeted
Your next AI film could win US$1 million. BytePlus has become a partner of @1billionsummit's AI Film Award 2027, the world’s largest AI film award. Whether you are a filmmaker, a creator or simply someone with a story to share, you are invited to push the boundaries of AI filmmaking. Create an original 5–7-minute film, with at least 70% generated using Dreamina Seedance. The top five films will premiere at the 1 Billion Followers Summit, where one creator will take home the US$1 million grand prize. Submission period: 30 September–20 November 2026 Submit your creation: 1billionsummit.com/ai-award-…
48
72
15
526
46,663
Visiblemakers retweeted
FLUX 3 Image Klein is here. Open Weights with the quality of a large frontier model. Customizable and fast. 5.6B parameters and runs on a single consumer GPU. Native 4K, bounding boxes, and pixel-perfect editing.
177
396
224
3,307
346,151
Visiblemakers retweeted
AI Videos finally sound real. Introducing Mirelo SFX 2.0. It watches your video, cuts the music you never prompted, keeps the dialogue, and builds a full sound design synced to the action and consistent across any length clips. You’ve made it look right. We’ll make it sound right. Live today through our API, on @runwayml and @fal. Other platforms coming soon. (Thread)
462
415
358
3,853
1,916,111
Visiblemakers retweeted
We just open-sourced an entire 3D team for Blender. Introducing the Scenario plugin. Use it inside Blender, or let Claude Code run it through MCP. 📁/scenario-plugin ┃ ┣ 📁 Concept Artist ┃ ┣ 📁 Concept Art From a Prompt ┃ ┗ 📁 References From Your Viewport ┃ ┣ 📁 3D Artist ┃ ┣ 📁 Meshes From Text or a Photo ┃ ┗ 📁 Retexture or Remesh the Selected Mesh ┃ ┣ 📁 Animator ┃ ┣ 📁 Rig the Selected Character ┃ ┗ 📁 Motion From Text ┃ ┣ 📁 Surfacing Artist ┃ ┣ 📁 PBR Materials Onto Any Slot ┃ ┗ 📁 Maps From a Photo ┃ ┣ 📁 Layout Artist ┃ ┣ 📁 Greybox From a Description ┃ ┗ 📁 360 Worlds and Skies ┃ ┣ 📁 Camera Operator ┃ ┣ 📁 Camera Path From a Sentence ┃ ┗ 📁 Orbits, Dollies, Cranes and Flyovers ┃ ┣ 📁 Render Artist ┃ ┣ 📁 Viewport to Finished Still ┃ ┗ 📁 Playblast to Finished Shot ┃ ┗ 📁 Sound Designer ┣ 📁 Music, Voice and SFX ┗ 📁 Dropped on Your Sequencer Comment "BLENDER" and I'll send you the GitHub repo.
1,166
339
28
3,776
212,720
Claude Opus 5.5への指示でBlenderで雰囲気あるコインランドリーの3DCGを作成しました。 Blenderを手動で操作することなく、すべてプロンプトだけで構築してみました。 基本的な制作の流れはリプで⬇️
81
456
85
5,245
745,589
Visiblemakers retweeted
Replying to @claudeai
@claudeai + @trymirage + @HyperFrames_ + @Blender is a lethal combo 👀 🤯 For years I've seen companies trying to build AI editors. All have been very disappointing. And then Opus 5.5 came out and bam, we do this now! Similar to AI films, you have to direct, you have to be clear, you have to have your taste and style. The first version is rarely perfect, but it gets me 80% there, then i give feedback and at times throw it into Premiere for final tweaking.
4
1
14
230
Visiblemakers retweeted
How does P-Video-2-Pro perform across quality, speed, and cost? Across its modes, it lands on the Pareto frontiers. For the scored 768p Pro variants, the P-Bench data gives: Text-to-Video • Quality: 1022 Elo · 8.34s • Speed: 1011 Elo · 4.04s • Cost: 1011 Elo · 10.17s Image-to-Video • Quality: 1013 Elo · 9.27s • Speed: 994 Elo · 3.00s • Cost: 994 Elo · 10.76s Three modes, each optimised for a different tradeoff: Quality, Speed, or Cost. Across them, P-Video-2-Pro sits on the preference × speed and preference × price Pareto frontiers. 🥇 Full benchmark: huggingface.co/spaces/PrunaA…
12
5
3
36
2,332
Visiblemakers retweeted
"Speedhunter" Can newest production tools deliver the realism, the precision and the emotional impact of a traditionally shot automotive commercial? I spent several weeks to find out 📈 Thanks to @runwayml for the CPP and support. Details of the making below👇🏼
19
8
3
78
5,957
Visiblemakers retweeted
HOY UNA INDUSTRIA ENTERA DEJÓ DE TENER SENTIDO alguien subió a GitHub un repo que coge cualquier foto y te devuelve un mundo 3d explorable: mallas con físicas, splat del fondo, audio ambiente. todo. entra una imagen. sale un mundo. cinco minutos. la gente que lleva diez años aprendiendo Blender se ha pasado el día mirando esto en silencio. se llama image-blaster. os dejo el repo abajo.
255
2,458
220
21,589
1,616,895