Josh

That AI Guy🎗Content Creator🎗Animator.
✨ Grab my free ebooks on my linktree

[Josh @JoshDev_Anime]

🤯🤯🤯Made this animated micro episode with @Alibaba_Wan @Kling_ai @dreamina_ai. It was a really good creative stretch with different styles used to express the main subject's emotions at every point of the video. Also used some post processing with AI vid green screens

[Josh @JoshDev_Anime]

@pst_iren We're the unstoppable move of God 🔥

[Josh @JoshDev_Anime]

@web3prosper Dope. Love the concept

[Josh @JoshDev_Anime]

@jerrod_lew @dreamina_ai Cool

[Josh @JoshDev_Anime]

Cool 👌

[LTX.io @ltx_io]

Today we’re launching LTX-2 in LTX (we're more than a studio).

LTX-2 represents a major breakthrough in speed and quality.

It offers fast generation, native 4K, lipsync, high frame rate, and up to 10s of continuous video.

Here’s what you need to know 🧵

[Josh @JoshDev_Anime]

Keyframes on Veo 😭🙏

[Logan Kilpatrick @OfficialLoganK]

Introducing Veo 3.1 and Veo 3.1 Fast, our latest state of the art video models with:

- richer native audio
- better cinematic styles
- reference to video
- transitions between frames
- video extensions

[Josh @JoshDev_Anime]

@dirmeller This is really cool

[Josh @JoshDev_Anime]

@munoz_benj86450 @DavizCF7777 @PJaccetturo @JesusPlazaX @Diesol So cool, very realistic and believable 🤯

[Josh @JoshDev_Anime]

Cool guys, loving the progress

[Boba AI Labs @BobaVideo]

Boba Anime 1.4 Video Model is here!

1.4 comes with significant upgrades 🎬 in Motion, Dialogue, and Consistent Characters.

It has taken a huge effort to make the leap from 1.0 to 1.4, and we couldn’t be more proud of the results.

Try it now: https://t.co/QaaPzEj4aN

[Josh @JoshDev_Anime]

@ABillaut Interested

[Josh @JoshDev_Anime]

💀

[Tencent Hy @TencentHunyuan]

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀

HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities:

✅Reason with world knowledge
✅Understand complex, thousand-word prompts
✅Generate precise text within images

Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks.

Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content.

The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more.

👉🏻Try it now: https://t.co/hHhQpNxJ4e
🔗GitHub: https://t.co/B2bkhlbXxk
🤗Hugging Face: https://t.co/s0G2Lix3ZD

[Josh @JoshDev_Anime]

Opensource Veo 3 finally here 🙌

[Wan @Alibaba_Wan]

Today, we're officially launching Wan2.5-Preview! It's set to reshape the future of visual generation with a new architecture and powerful features.
• Architectural Features: Native Multimodality, Deep Alignment
∘ Native Multimodal Architecture: Adopts a new, unified framework for both understanding and generation, flexibly supporting the input and output of text, images, video, and audio.
∘ Joint Multimodal Training: Achieves stronger modal alignment by jointly training on text, audio, and visual data—key to enabling audio-visual sync and greatly improved instruction following.
∘ Human Preference Alignment: Implements Reinforcement Learning from Human Feedback (RLHF) to continuously align with human preferences, enhancing image quality and video dynamics.

• Video Capabilities: A/V Synchronization, Cinematic Quality
∘ Synchronized A/V Generation: Natively supports high-fidelity, high-consistency video generation with synchronized audio, including multi-person vocals, sound effects, and BGM.
∘ Controllable Multimodal Input: Supports text, images, and audio as input sources for limitless creativity.
∘ Cinematic Aesthetics: Features powerful dynamics and structural stability with an upgraded cinematic control system, generating 1080p HD 10s videos of cinematic quality.

• Image Capabilities: Creative & Precise Control
∘ Advanced Image Generation: Greatly improved instruction following to support photorealistic quality, diverse artistic styles, creative typography, and professional-grade charts.
∘ Image Editing: Supports conversational, instruction-based image editing and pixel-level precision for tasks like multi-concept fusion, material transformation, and product color swapping, and more.

[Josh @JoshDev_Anime]

Woah 😱

[Qwen @Alibaba_Qwen]

🔥 Qwen-Image-Edit-2509 IS LIVE — and it’s a GAME CHANGER. 🔥

We didn’t just upgrade it. We rebuilt it for creators, designers, and AI tinkerers who demand pixel-perfect control.

✅ Multi-Image Editing? YES.
Drag in “person + product” or “person + scene” — it blends them like magic. No more Franken-images.

✅ Single-Image? Rock-Solid Consistency.
• 👤 Faces stay you — through poses, filters, and wild styles.
• 🛍️ Products keep their identity — ideal for ads & posters.
• ✍️ Text? Edit everything: content, font, color, even material texture.

✅ ControlNet Built-In.
Depth. Edges. Keypoints. Plug & play precision.

✨ Blog: https://t.co/BDJ8Zj3UBT
💬 QwenChat: https://t.co/r2Zcg4OjGc
🐙 GitHub: https://t.co/A9yvJZ6TJc
🤗 HuggingFace: https://t.co/avoqKZU80C
🧩 ModelScope: https://t.co/aGByF9H7QX

[Josh @JoshDev_Anime]

Now we're talking 💪

[WaveSpeedAI @wavespeed_ai]

🚀 WAN 2.5 · Global Debut on WaveSpeedAI! Multilingual, cinematic, and fully audio-synced — the next-level AI video model is finally here.
🔥 See it in action and experience AI video like never before!
Try Wan 2.5 now!
🔗 https://t.co/mdzzyT7TeG
🔗 blog: https://t.co/A54YJCD2hT
#WAN2_5 #AI #VideoRevolution #WaveSpeedAI #AIVideo #MultilingualAI #CinematicAI #LipSyncAI #DigitalCreativity #NextGenAI #ContentCreation #VideoAI #AIInnovation

[Josh @JoshDev_Anime]

We're at 2.5 already? 😳

[Josh @JoshDev_Anime]

This is cool, Just got access to the world lab model.

[TechHalla @techhalla]

Get spatial and character consistency by combining AI with 3D.

Learn to create your avatar and generate quality clips with built-in prompts and tools, in this thread 🧵👇

[Luma @LumaLabsAI]

This is Ray3. The world’s first reasoning video model, and the first to generate studio-grade HDR. Now with an all-new Draft Mode for rapid iteration in creative workflows, and state of the art physics and consistency. Available now for free in Dream Machine.

[Josh @JoshDev_Anime]

@pst_iren 😭😭😭😭

[Josh @JoshDev_Anime]

@sumit_rana_AI 🔥Alright, would be expecting that

[Josh @JoshDev_Anime]

🦸‍♂️