eqtvEverything You Wanted to Know About Google Veo3
PeerTube
YAYAFAAIで本格アニメは1人で作れるのか？OiiOii.AIで短編アニメを制作してみた https://www.yayafa.com/2806572/ ##AI動画生成 #AgenticAi #AI #AiAnimation #AiAnime #AIShortFilm #AIアニメ #AIエージェント #AI映画 #Akio #ArtificialGeneralIntelligence #ArtificialIntelligence #OiiOii #OiiOiiAI #Seedance #Seedance20 #Seedance2 #TextToVideo #YUBIWA #アキオ #アップスケール #アニメ制作 #インディースアニメ #エージェント型AI #オイオイ #シーダンス #テキストから動画 #マルチリファレンス #ワークフロー #人工知能 #個人開発 #汎用人工知能 #画像から動画 #短編アニメ
TKHUNThttps://www.tkhunt.com/2336205/ AIで本格アニメは1人で作れるのか？OiiOii.AIで短編アニメを制作してみた ##AI映画 #AgenticAi #AI #AiAnimation #AiAnime #AIShortFilm #AIアニメ #AIエージェント #AI動画生成 #akio #ArtificialIntelligence #OiiOii #OiiOiiAI #Seedance #Seedance20 #Seedance2 #TextToVideo #Yubiwa #アキオ #アップスケール #アニメ制作 #インディーズアニメ #エージェント型AI #オイオイ #シーダンス #テキストから動画 #マルチリファレンス #ワークフロー #人工知能 #個人開発 #画像から動画 #短編アニメ
Winbuzzerhttps://winbuzzer.com/2026/05/20/google-launches-the-gemini-omni-multimodal-model-s-xcxwbn/
Google has launched Gemini Omni as a mixed-input AI model family and started the first live rollout through Gemini Omni Flash on Gemini, YouTube, and creator surfaces.
#AI #GoogleGemini #Google #GeminiOmni #GoogleAI #GoogleDeepMind #MultimodalAI #AIModels #AIVideoGeneration #AIVideo #TextToVideo #GenAI
michael.brownWhat if a single text prompt could generate stunning 1080p videos with realistic sound effects, accurate lip-sync, and cinematic storytelling?
Veo 3.1 makes it possible.
Why are creators, marketers, and filmmakers paying attention?
Because Veo 3.1 transforms ideas into professional-quality videos in minutes—no cameras, no actors, no editing experience required.
https://www.jxp.com/veo/veo-3-1
#Veo31 #AIvideo #TextToVideo #AIGenerator #ContentCreation #DigitalMarketing #VideoProduction #AItools
Chinese internet company Kuaishou is reviewing a restructuring of its Kling AI video business that may include outside capital.
#AI AIVideo #KlingAI #Kuaishou #Review #Valuation #AIVideoGeneration #TextToVideo #GenerativeAI #ChinaAI
https://winbuzzer.com/2026/03/12/openai-plans-to-fold-sora-into-chatgpt-after-standalone-app-xcxwbn/
Failing Sora App: OpenAI Plans to Fold AI Video Maker Into ChatGPT
#AI #ChatGPT #OpenAI #Sora #AI #GenerativeAI #AIVideoGeneration #AIVideo #TextToVideo #AIGeneratedContent
AI Daily PostAdobe's new Firefly Quick Cut lets you type a prompt and get a first video draft in seconds—beta is live. It's a game‑changer for creators, blending generative AI with Premiere Pro workflows. Curious how text‑to‑video could reshape editing? Dive into the details. #AdobeFirefly #QuickCut #TextToVideo #GenerativeAI
🔗 https://aidailypost.com/news/adobe-launches-firefly-quick-cut-ai-tool-creates-first-video-draft
PsychoticSheepA cat jump is a much better “hello world” than a cyberpunk car. 🐈✨
Two jumps, generated locally with WAN 2.1 (1.3B, fp16) in ComfyUI.
Rendered on my AMD RX 6700 XT via ROCm.
Everything runs locally, no cloud processing, no external APIs.
Just privacy-friendly, open tools and feline physics. 💜
#cat #aicats #CatVideo #AIVideo #TextToVideo #ComfyUI #WAN21 #LocalAI #OpenSource #Privacy #ROCm #AIArt #Fediverse #Cute #linux #foss
Two jumps, generated locally with WAN 2.1 (1.3B, fp16) in ComfyUI.
Rendered on my AMD RX 6700 XT via ROCm.
Everything runs locally, no cloud processing, no external APIs.
Just privacy-friendly, open tools and feline physics. 💜
#cat #aicats #CatVideo #AIVideo #TextToVideo #ComfyUI #WAN21 #LocalAI #OpenSource #Privacy #ROCm #AIArt #Fediverse #Cute #linux #foss
🎉 Now videos are alive! After finally getting WAN 2.1 running on my RX 6700 XT via ROCm and ComfyUI, even complex prompts can be turned into animated WebPs locally!
These animated WebP were generated locally using ComfyUI and the WAN 2.1 T2V 1.3B (fp16) model.
Model Stack:
- wan2.1_t2v_1.3B_fp16
- umt5_xxl_fp8_e4m3fn_scaled (Text Encoder)
- wan_2.1_vae
- clip_vision_h
The prompt is first converted into embeddings by the UMT5 encoder.
The WAN video model then generates multiple frames using latent diffusion (noise → iterative refinement), ensuring temporal coherence between frames.
The VAE decodes the latent frames into images, exported as an animated WebP.
Prompt execution time: depends on scene complexity, from 521.62 seconds (~8.7 minutes) up to 17 minutes 26 seconds for more complex prompts.
Rendered locally via ROCm on my AMD RX 6700 XT (12GB VRAM).
No cloud. Pure local inference.
#ComfyUI #WAN21 #ROCm #AMD #LocalAI #FOSS #VideoAI #AIvideo #AIGenerated #MachineLearning #DeepLearning #DiffusionModels #TextToVideo #AIArt #CreativeAI #LocalInference #VideoGeneration
These animated WebP were generated locally using ComfyUI and the WAN 2.1 T2V 1.3B (fp16) model.
Model Stack:
- wan2.1_t2v_1.3B_fp16
- umt5_xxl_fp8_e4m3fn_scaled (Text Encoder)
- wan_2.1_vae
- clip_vision_h
The prompt is first converted into embeddings by the UMT5 encoder.
The WAN video model then generates multiple frames using latent diffusion (noise → iterative refinement), ensuring temporal coherence between frames.
The VAE decodes the latent frames into images, exported as an animated WebP.
Prompt execution time: depends on scene complexity, from 521.62 seconds (~8.7 minutes) up to 17 minutes 26 seconds for more complex prompts.
Rendered locally via ROCm on my AMD RX 6700 XT (12GB VRAM).
No cloud. Pure local inference.
#ComfyUI #WAN21 #ROCm #AMD #LocalAI #FOSS #VideoAI #AIvideo #AIGenerated #MachineLearning #DeepLearning #DiffusionModels #TextToVideo #AIArt #CreativeAI #LocalInference #VideoGeneration
