正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

same idea but way better results now, text → concept image → meshy v7 on fal→ auto-rig → playable in ue5 here's an example with a muscular alien wearing khakis

Blendi

4,829 subscribers

11,765 次观看 • 13 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

13 条评论

Ron Millar 的头像

Ron Millar13 天前

Shameless plug! You can also use to generate all sorts of characters at various quality levels and even add ai generated animations. Then export. The Idea Forge is very powerful. Here's a few aliens in pants hangin' out.

Blendi 的头像

Blendi13 天前

Try out the upgrades!

Sogni.ai 的头像

Sogni.ai13 天前

love this 🤩 our Sogni Creative Agent slots right into the front of that chain, unlimited concept iterations before anything touches a mesh →

Tushar 的头像

Tushar13 天前

Finally! This is sick

Blendi 的头像

Blendi13 天前

🙏

Directive Creator 🪥 的头像

Directive Creator 🪥13 天前

@sideloadgg Powered by Fal for images!

Thunderfall 的头像

Thunderfall12 天前

Wow that makes it look so easy!

Daniel Johnsen 的头像

Daniel Johnsen13 天前

This is what I've been hunting for. Still stuck on text to usable @threejs though. You tried that path?

Griz 的头像

Griz13 天前

my version of this lived in three tabs

TurnOn 的头像

TurnOn13 天前

how long does it take from prompt to play?

Sloyd 的头像

Sloyd12 天前

the alien in khakis is sending me 😂 text straight to auto rigged in ue5 is genuinely wild

Lee Penkman 的头像

Lee Penkman13 天前

epic you beat me to it. something not right about my rigging lol

Ovarlak Gaming 的头像

Ovarlak Gaming13 天前

Omg

相关视频

Meshy V7 is now available on fal - Turns an image into a textured, export-ready 3D model in seconds - From image to animated character in one pass - Auto-rigging and ready-to-use animation - Full PBR textures included production-grade materials and clean topology

Meshy V7 is now available on fal - Turns an image into a textured, export-ready 3D model in seconds - From image to animated character in one pass - Auto-rigging and ready-to-use animation - Full PBR textures included production-grade materials and clean topology

fal

34,300 次观看 • 1 个月前

Wan 3.0 is now live on fal. - Produces native 30-second clips in a single pass without stitching - Omni-reference input: text, image, audio, video, web pages and documents - Reality-grade rendering with improved real-world motion

Wan 3.0 is now live on fal. - Produces native 30-second clips in a single pass without stitching - Omni-reference input: text, image, audio, video, web pages and documents - Reality-grade rendering with improved real-world motion

fal

53,155 次观看 • 22 天前

Working my way through the Assault Rifle rig! I still absolutely love my auto magazine mechanism, and i've got an extra firing MCH idea that i want to try out on this rig. It's a little different to the Pistol rig, but should be fun and useful!😄 #blender #rigging #rig

Working my way through the Assault Rifle rig! I still absolutely love my auto magazine mechanism, and i've got an extra firing MCH idea that i want to try out on this rig. It's a little different to the Pistol rig, but should be fun and useful!😄 #blender #rigging #rig

RyanLykos

102,349 次观看 • 1 年前

Create high-quality, production-ready visuals in seconds with improved realism, better text rendering, and more precise control. GPT Image 2.0 allows you to: • Generate more detailed and accurate images • Create visuals with cleaner, more reliable text • Edit and refine outputs with greater control Whether you're building marketing creatives, social content, or concept visuals, it helps you go from idea to image faster than ever. 🚀 Now live on Akool, try it today!

Create high-quality, production-ready visuals in seconds with improved realism, better text rendering, and more precise control. GPT Image 2.0 allows you to: • Generate more detailed and accurate images • Create visuals with cleaner, more reliable text • Edit and refine outputs with greater control Whether you're building marketing creatives, social content, or concept visuals, it helps you go from idea to image faster than ever. 🚀 Now live on Akool, try it today!

Akool Inc

379,274 次观看 • 4 个月前

I'm a bit confused... Google's Veo 2 is the best video model in text-to-video. But on the other hand... The newly released image-to-video for Veo 2 (on Freepik (now Magnific) and @FAL) feels underwhelming. Input images generated with Runway Frames. Here it is compared to Luma

I'm a bit confused... Google's Veo 2 is the best video model in text-to-video. But on the other hand... The newly released image-to-video for Veo 2 (on Freepik (now Magnific) and @FAL) feels underwhelming. Input images generated with Runway Frames. Here it is compared to Luma

Alex Patrascu

85,445 次观看 • 1 年前

, webgl experience fully made using fal the pipeline: GPT-Image-2 (or FLUX.2 Klein 9B for the live "create your own") 🦴 meshy v6 image-to-3d takes that → rigged GLB with a baked animation 🐾 GPT-Image-2/edit on the same character → companion creature image, color-locked to the character's palette → meshy v6 again (no rig) → static creature GLB 🪨 PATINA (fal-ai/patina/material/extract) takes the character image and outputs basecolor + normal + roughness + metalness for a per-character floor that matches their environment 🎬 Seedance 2.0 fast → 8s looping background video per character 📦 everything runs through gltf-transform (resize 1024 → webp q80 → draco) for ~95% size reduction → 400-800 KB GLBs 🖥️ the front-end is a single static index.html: Three.js scene, alpha-mapped marble disc with PlaneGeometry tessellation for real displacementMap depth, mirrored reflection plane, breathing animations on companions, palette-swap via CSS custom properties on character click 🧩 the whole recipe is published as a Claude Code skill fal-regenerate-3d so you can rebuild this yourself → ⚠ metrics shown are decorative

, webgl experience fully made using fal the pipeline: GPT-Image-2 (or FLUX.2 Klein 9B for the live "create your own") 🦴 meshy v6 image-to-3d takes that → rigged GLB with a baked animation 🐾 GPT-Image-2/edit on the same character → companion creature image, color-locked to the character's palette → meshy v6 again (no rig) → static creature GLB 🪨 PATINA (fal-ai/patina/material/extract) takes the character image and outputs basecolor + normal + roughness + metalness for a per-character floor that matches their environment 🎬 Seedance 2.0 fast → 8s looping background video per character 📦 everything runs through gltf-transform (resize 1024 → webp q80 → draco) for ~95% size reduction → 400-800 KB GLBs 🖥️ the front-end is a single static index.html: Three.js scene, alpha-mapped marble disc with PlaneGeometry tessellation for real displacementMap depth, mirrored reflection plane, breathing animations on companions, palette-swap via CSS custom properties on character click 🧩 the whole recipe is published as a Claude Code skill fal-regenerate-3d so you can rebuild this yourself → ⚠ metrics shown are decorative

Lovis Odin

99,185 次观看 • 4 个月前

Wolverine delivers an authentic, highly playable Wolverine experience. But at the same time, it's a barebones third-person action game executed in a no-frills way, with no real surprises. Full review:

Wolverine delivers an authentic, highly playable Wolverine experience. But at the same time, it's a barebones third-person action game executed in a no-frills way, with no real surprises. Full review:

GameSpot

83,181 次观看 • 5 天前

✦ AUTO RIG ANY PNG INTO A PET ✦ This is an incredibly smart idea and an easy way for you to get yourself a Live2D pet to hang out with you on stream. It's extremely easy to use and comes with a tutorial and everything. It's worth every penny so check it out!

✦ AUTO RIG ANY PNG INTO A PET ✦ This is an incredibly smart idea and an easy way for you to get yourself a Live2D pet to hang out with you on stream. It's extremely easy to use and comes with a tutorial and everything. It's worth every penny so check it out!

Phlox Nesspalier 🪫📺

52,043 次观看 • 8 个月前

Google Reverse Image Search doesn’t work the way you might think. When you search a viral image, the results may show an old date under the image. That doesn’t necessarily mean it’s the actual date of the photo. This happens because the image might have been used in another article. To find the real source, you need to click on the link in the results and check the page itself. For example, when I reverse-searched this photo, one result showed the date March 4, 2026 under the image. But when I clicked the article, Benjamin Netanyahu’s photo wasn’t there. Similarly, another result showed October 11, 2022, but clicking the link revealed that the photo wasn’t in that article either. Here’s another example, one result showed February 28, 2026, but clicking the article opened a March 17, 2026 post, and there the same image appeared.

Google Reverse Image Search doesn’t work the way you might think. When you search a viral image, the results may show an old date under the image. That doesn’t necessarily mean it’s the actual date of the photo. This happens because the image might have been used in another article. To find the real source, you need to click on the link in the results and check the page itself. For example, when I reverse-searched this photo, one result showed the date March 4, 2026 under the image. But when I clicked the article, Benjamin Netanyahu’s photo wasn’t there. Similarly, another result showed October 11, 2022, but clicking the link revealed that the photo wasn’t in that article either. Here’s another example, one result showed February 28, 2026, but clicking the article opened a March 17, 2026 post, and there the same image appeared.

Vishal Maheshwari

24,282 次观看 • 6 个月前

Working on implementing a LiDAR concept for Falling Frontier. Still very much in-progress, but the goal is to integrate it into the existing Fog of War system/Uber shader. An immense undertaking from all sides, but worth it. Here's the idea at work in an isolated Unity scene.

Working on implementing a LiDAR concept for Falling Frontier. Still very much in-progress, but the goal is to integrate it into the existing Fog of War system/Uber shader. An immense undertaking from all sides, but worth it. Here's the idea at work in an isolated Unity scene.

Stutter Fox Studios

11,948 次观看 • 10 个月前

Announcing #TheSingularity *An epic rock concept album, coming May 10 *An original graphic novel, coming May 8 from Image Comics *A concert in Los Angeles May 12, tix on sale now! Our first single, “Type III” with @rufuswainwright is STREAMING NOW.

Announcing #TheSingularity An epic rock concept album, coming May 10 An original graphic novel, coming May 8 from Image Comics *A concert in Los Angeles May 12, tix on sale now! Our first single, “Type III” with @rufuswainwright is STREAMING NOW.

Bear McCreary 🐻🎶

272,138 次观看 • 2 年前

Qwen3.8-27b produces beautiful results very presentable 😍 Way better than 3.6-27b by a long shot. My three.js and glsl tests are going on, but here is few examples, same prompt with same default settings all run on my 3090. qwen3.6-27b-Q5 vs qwen3.8-27b-Q5

Qwen3.8-27b produces beautiful results very presentable 😍 Way better than 3.6-27b by a long shot. My three.js and glsl tests are going on, but here is few examples, same prompt with same default settings all run on my 3090. qwen3.6-27b-Q5 vs qwen3.8-27b-Q5

AJ

93,007 次观看 • 1 个月前

Governor Gavin Newsom doesn't want you to know a California inmate is on trial right now for grooming a 12-year-old on his taxpayer-funded tablet. Why are we buying prisoners iPads? Here's an idea: let's use our tax dollars to provide children in school with better technology.

Governor Gavin Newsom doesn't want you to know a California inmate is on trial right now for grooming a 12-year-old on his taxpayer-funded tablet. Why are we buying prisoners iPads? Here's an idea: let's use our tax dollars to provide children in school with better technology.

Rep. James Comer

161,604 次观看 • 3 个月前

You're in a meeting with an investor. They are skeptical of your business idea. You flick your wrist to reveal you're wearing a Rolex. Then slowly put your feet up on the conference table. Wide eyed, the investor says, "Sir." He says, "Sir, I had no idea. Here's $500M."

You're in a meeting with an investor. They are skeptical of your business idea. You flick your wrist to reveal you're wearing a Rolex. Then slowly put your feet up on the conference table. Wide eyed, the investor says, "Sir." He says, "Sir, I had no idea. Here's $500M."

derek guy

299,786 次观看 • 8 天前

Introducing the Multi-Shot App. An easy way to go from a simple prompt to a thoughtfully crafted scene. All with dialogue, sound effects, intentional cuts, pacing and cinematic framing. Start from an image or go purely Text to Video for total creative exploration. Available now on the web app. See examples in the thread below.

Introducing the Multi-Shot App. An easy way to go from a simple prompt to a thoughtfully crafted scene. All with dialogue, sound effects, intentional cuts, pacing and cinematic framing. Start from an image or go purely Text to Video for total creative exploration. Available now on the web app. See examples in the thread below.

Runway

191,976 次观看 • 5 个月前

Agentomorphizing is treating AI agents like smart humans. And it might be the simplest way to get better results from your agents right now. When an agent underperforms, ask what a smart person would have needed to succeed with the same instructions. Our CTO Ben Kus explains why in the latest AI Explainer episode.

Agentomorphizing is treating AI agents like smart humans. And it might be the simplest way to get better results from your agents right now. When an agent underperforms, ask what a smart person would have needed to succeed with the same instructions. Our CTO Ben Kus explains why in the latest AI Explainer episode.

Box

86,031 次观看 • 3 个月前

Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation. Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)

Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation. Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)

Poe

21,988 次观看 • 10 个月前

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 次观看 • 2 年前