TwórczyAI
@TworczyAI
Followers
3K
Following
7K
Media
1K
Statuses
3K
🎨Grafiki i wideo AI. Odkryj przyszłość sztuki cyfrowej! 📩 DM lub [email protected]
Polska
Joined November 2023
📗Chcesz dostęp do mojej biblioteki kodów Sref?📢 📚 Udostępniam moją kolekcję prawie 2400 kodów, które pomogą Ci w Twoich projektach! Kolekcja będzie na bieżąco aktualizowana 🔥 🎯 Aby otrzymać dostęp ZA DARMO: Polub ten post ❤️ Udostępnij go 🔄 Zostaw komentarz: "sref" ✍️
146
114
183
Już się nie mogę doczekać 🔥
Kling 3.0 Model is coming! Now in exclusive early access. Stay tuned for what’s next. 🚀
1
0
4
Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎
946
4K
34K
Pinokio 6 is live. Won't explain what's new. You'll see it in 5 seconds. A new beginning. Phase 2 of Pinokio starts now. See you in the valley beyond.
14
24
233
NVIDIA just dropped a real-time conversational AI voice, free and open source PersonaPlex 7B https://t.co/RHvaItGxdx
89
355
4K
FLUX.2 [klein] 4B + 9B are the newest BFL models in the Flux family—combining image generation + image editing in one compact architecture. Built for interactive workflows and quick iteration, with extremely fast inference on distilled variants. Two models. Two modes. ⚡️
10
45
272
Introducing GLM-Image: A new milestone in open-source image generation. GLM-Image uses a hybrid auto-regressive plus diffusion architecture, combining strong global semantic understanding with high fidelity visual detail. It matches mainstream diffusion models in overall quality
114
264
2K
Model open source LTX-2 już z milionem pobrań na hugging face 🤯 zacny wynik a dopiero mija tydzień od premiery😄
1,000,000 Hugging Face downloads, and counting! LTX-2 grew the way we believe products should: in the open, with the community, through real-world use. Grateful for everyone who helped get us here and excited for what’s next. Download and try it for yourself here:
0
0
2
Not every open-source model is built equally. LTX-2 produces audio and lip-synced dialogue natively, with leading open-source quality.
58
118
1K
Niji V7 is now live. This model features improved anime coherence, prompt understanding, text rendering, and sref performance. Enjoy!
394
817
7K
LTX-2: 10 second video at 720p takes 3 minutes on RTX 4070 with 12GB VRAM
@cocktailpeanut 10-seconds at 720p rendered in 3 minutes using distilled.... not too bad. Curious to try the non-distilled to see how that compares in the result.
20
23
218
Model jest też dodany do Wan GP i można z niego skorzystać przez Pinokio😀
W końcu wleciał model LTX-2 w wersji open source🙌oczywiście w ComfyUI jest już dodanych kilka podstawowych workflow😀
0
0
2
We partnered with @NVIDIA_AI_PC and @Lightricks to push local AI video forward. NVFP4 and NVFP8 checkpoints are now available for LTX-2. With NVIDIA-optimized ComfyUI, LTX-2 delivers cloud-class 4K video locally - up to 3X faster with 60% less VRAM using NVFP4.
huggingface.co
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control -
22
50
406
W końcu wleciał model LTX-2 w wersji open source🙌oczywiście w ComfyUI jest już dodanych kilka podstawowych workflow😀
LTX-2 is now open source. The first truly open audio-video generation model with open weights and full training code, designed to run locally on @NVIDIA_AI_PC RTX consumer GPUs. Details below 🧵
0
0
2
Fajne to 😁
0
0
1
Stop guessing. Start directing. Ray3 Modify is now in Dream Machine. Edit and reimagine videos with all-new precise keyframe and character reference controls. Your vision, reimagined. Supercharge your production with rapid retouching, precise element swapping, and scene redesign.
25
79
411
FLUX.2 [max] is here Our highest quality model to date. * Grounded generation - searches the web for real-time context. * Up to 10 reference images. Products, characters, styles stay consistent. * #2 on @ArtificialAnlys in text-to-image and image editing.
42
136
999
Gothika Vol. I Song: Fimiguerrero - Tartan ft ReekzMB
6
9
109
Wan 2.6
Introducing Wan2.6 - A native multimodal model that turns your ideas into breathtaking videos and images! · Starring: Cast characters from reference videos into new scenes. Support human or human-like figures, enabling complex multi-person and human-object interactions with
0
0
2