@ModelCollapse38

Painter/ photographer/ build with AI

Joined February 2026
  • Tweets312
  • Following182
  • Followers274
43Media
Encodium retweeted
Perchy
@getperchy10h
perchy speaks your language 🌍 english, türkçe, deutsch, français, español, italiano, português, nederlands, 日本語, 한국어, 简体中文 getperchy.com/?ref=x
1
1
1
33
Encodium retweeted
fal
@falOct 23
Kling 4.0 is now publicly available on fal, with API access open to all customers. The latest model from @Kling_ai brings: • Up to 30 seconds of native video generation with audio • Up to 15 image, video, and element references • Precise control with up to 10 keyframes • Improved motion, character consistency, and cinematic storytelling Start building with Kling 4.0 on fal today.
28
11
11
159
15,274
Encodium retweeted
gokaygokay
@gokayfemOct 18
Video 2 GLSL I gave Claude Opus 5.5 a 20-second video clip. It rebuilt the whole thing as one GLSL fragment shader: 156 KB of code, no textures, no video frames. Just math, looping seamlessly
61
117
49
1,510
1,110,193
Encodium retweeted
fal
@falOct 15
Introducing fal Worlds. A new way to create and interact with AI-generated worlds in real time. Build characters, explore environments, direct scenes, and watch worlds respond to your actions as they unfold. Get hands-on with the latest frontier world models, including LingBot World, H3 Max Director and more.
13
68
24
496
39,383
Encodium retweeted
Lovis Odin
@OdinLovisOct 2
training a video model to teach sign language , coming soon !
11
15
5
153
10,319
MiniMax H3 Director on @fal — realtime prompt stream, no cuts. Camera dives into Harari’s Sapiens and walks the book’s timeline A few beats edited after. New fal Director model. One session, live prompts. @Hailuo_AI
1
2
4
244
Encodium retweeted
gokaygokay
@gokayfemSep 3
peak technology
fal
@falSep 3
Introducing fal's H3 Max Director, the first natively continuous real-time frontier video model for action-controlled long-form generation. Unlike H3 Max and other video models, H3 Max Director generates a single continuous video stream, maintaining context over time rather than chaining together discrete clips. It’s the technology behind fal.live, our experimental infinite AI livestream where viewers interact with and shape what gets generated in real time. Now, we’re making the underlying model available via API. For the first two weeks, all H3 Max Director generations are 75% off.
2
22
1,671
I had a lot of fun doing it, even though it's sweet, it's dangerous Workflow: Character and environment Design ⬇️ @NanoBanana : Key shots ⬇️ @Kling_ai : Animation ⬇️ Platform: @fal 🏝️
2
3
217
Encodium retweeted
Mickmumpitz@mickmumpitzSep 1
Another use case for our free & local 3D world pipeline: a car commercial, shot inside an AI world. 3D layout for the blocking, AI the environment, any camera move you want. Free workflow & tutorial below!
5
10
128
7,186
This is a live demo from the future!!! 🤯🤯🤯 An interactive sitcom? A playable episode? Games and movies are merging into one thing. I genuinely cannot stop playing this. Real-time video generation will change the entertainment industry forever. We are so close. Thanks to @fal team . @Hailuo_AI
110
205
105
2,346
549,200
Encodium retweeted
gokaygokay
@gokayfemAug 31
Realtime Interactive Education with H3 Max this model is revolutionary
37
49
18
596
56,386
Encodium retweeted
ComfyUI
@ComfyUIAug 31
SAM 3D Body is open-source, so it can be run locally or on Comfy Cloud. Extract motion from a recording → bring it into Blender → control the camera → use the result with Seedance 2.5 More control over body motion and camera movement. To try this workflows, links below 👇
36
150
16
1,558
124,420
Discovered this new series from a French director experimenting with AI video. It’s called “La Nona Gigante” - and it’s about a boy who spends the summer with his grandma, who is the last living giant on her island. Not hard to see this as a full movie…made by leo_cannone.
107
230
32
3,216
224,631
RT @ModelCollapse38: A short-film experiment made with H3 Max on fal.ai. I used first-and-last-frame control, then edited…
1
fal提供のMiniMaxH3 Maxが1日5回まで無料提供開始。5秒のビデオが3秒で生成される。日本語もそのまま通る。 fal.ai/tools/minimax-h3-max
6
23
3,125
Rendered on MiniMax H3 Max via fal.ai — each clip came back in about 10 seconds. Genuinely fast. I cut a few of those sequences @Hailuo_AI
1
2
379
Image-to-Video (I2V) MiniMax Hailuo 3 Max on @fal locked still (first frame) → clip Avg. generation: ~10s per sequence short I2V passes, then cut together @MiniMax_AI
2
1
9
1,585
Manhattan, forest → today first + last frame locked, city grows in between MiniMax H3 Max I2V on @fal 768p generated in 16s @MiniMax_AI
🤖 Made with AI
1
193
I drew the storyboard, then generated the stills with image models. Video: MiniMax H3 on fal.ai first frame, last frame, reference. Then the edit. 📽️🎞️ @MiniMax_AI @fal
2
2
5
1,578
Encodium retweeted
fal
@falAug 11
LTX 2.5 is live on fal. Now with Diffusion Fidelity Rendering, which puts more compute into complex scenes. It’s open, customizable, and built to hack on. Train LoRAs, fine-tune on your own data and adapt it to your domain.
8
18
6
122
17,248
Load more