Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training

fal

69,571 subscribers

48,244 просмотров • 4 месяцев назад •via X (Twitter)

Искусство Образование Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 7

Фото профиля fal

fal4 месяцев назад

The code and weights are open with the full writeup to match. The technical report covers the architecture, training approach and the RAW-to-Turbo design. GitHub: Technical report:

Фото профиля fal

fal4 месяцев назад

Try them on fal today! Turbo LoRA Trainer LoRA Inference

Фото профиля Nicholas Dunzelman

Nicholas Dunzelman4 месяцев назад

@krea_ai lfg!!!!!

Фото профиля Meris Dabhi

Meris Dabhi4 месяцев назад

I never use this. It's good?

Фото профиля @dingchilling 🫪

@dingchilling 🫪4 месяцев назад

is it even a new model launch on fal if the announcement doesn't come with coupon codes?

Фото профиля blankbrain

blankbrain4 месяцев назад

have they not seen the license ?

Фото профиля Jakub Palka

Jakub Palka4 месяцев назад

If you’re into new AI tools, this is worth a look — IDA generates personalized interior designs from a photo of your room. First 1,000 users can try it for free:

Похожие видео

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

LMSYS Org

11,216 просмотров • 4 месяцев назад

MiniMax H3 Image is now available on fal. The latest open-weights image model from MiniMax (official) delivers exceptional visual quality at lightning-fast speeds, with powerful generation and editing capabilities. Generate and edit images in native 4K, combine multiple references, and render complex text with precision.

MiniMax H3 Image is now available on fal. The latest open-weights image model from MiniMax (official) delivers exceptional visual quality at lightning-fast speeds, with powerful generation and editing capabilities. Generate and edit images in native 4K, combine multiple references, and render complex text with precision.

fal

48,878 просмотров • 5 дней назад

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities! ✨4x faster inference (2s vs 7s) 💰 Ultra-affordable at $0.025/megapixel 🔧 Full LoRA training support 🖌️Game-changing image editing capabilities

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities! ✨4x faster inference (2s vs 7s) 💰 Ultra-affordable at $0.025/megapixel 🔧 Full LoRA training support 🖌️Game-changing image editing capabilities

fal

161,022 просмотров • 1 год назад

I trained an open-source LoRA for MiniMax H3: Realism People. weights are open. and the exact trainer I used is now available to everyone on fal Lora Link : Trainer :

I trained an open-source LoRA for MiniMax H3: Realism People. weights are open. and the exact trainer I used is now available to everyone on fal Lora Link : Trainer :

Lovis Odin

67,360 просмотров • 3 месяцев назад

LoRA trainer for MiniMax H3 is now available on fal. to show what it can do, we trained Realism People, an open-source LoRA that pushes H3 toward raw, photorealistic humans. skin, eyes, motion. More LoRA coming soon !

LoRA trainer for MiniMax H3 is now available on fal. to show what it can do, we trained Realism People, an open-source LoRA that pushes H3 toward raw, photorealistic humans. skin, eyes, motion. More LoRA coming soon !

fal

167,184 просмотров • 3 месяцев назад

today, we release the open weights of Krea 2. welcome Krea 2 Raw and Krea 2 Turbo, an undistilled model from mid-training meant to be fine-tuned, and a fast distilled version with a wide aesthetic diversity. read the details below 👇

today, we release the open weights of Krea 2. welcome Krea 2 Raw and Krea 2 Turbo, an undistilled model from mid-training meant to be fine-tuned, and a fast distilled version with a wide aesthetic diversity. read the details below 👇

Krea

769,058 просмотров • 4 месяцев назад

Hyper-Precise Virtual Try-On LoRA for FLUX.2 [klein] 9B Edit Hosted on fal and Open source Upload 1 person photo + 2 clothing references → realistic try-on result 3 images in → 1 styled output Open weights on HuggingFace

Hyper-Precise Virtual Try-On LoRA for FLUX.2 [klein] 9B Edit Hosted on fal and Open source Upload 1 person photo + 2 clothing references → realistic try-on result 3 images in → 1 styled output Open weights on HuggingFace

fal

52,836 просмотров • 8 месяцев назад

Bria Fibo 2.0 from BRIA AI is live on fal. The #1 open-weight image editing model on Artificial Analysis, with text-to-image generation and targeted editing. Trained only on licensed data, with clear commercial rights. - Image editing with up to four input images - Background swaps, product restaging and lighting changes - Text-to-image generation for reasoning-heavy prompts

Bria Fibo 2.0 from BRIA AI is live on fal. The #1 open-weight image editing model on Artificial Analysis, with text-to-image generation and targeted editing. Trained only on licensed data, with clear commercial rights. - Image editing with up to four input images - Background swaps, product restaging and lighting changes - Text-to-image generation for reasoning-heavy prompts

fal

15,730 просмотров • 26 дней назад

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.

AI Search

14,705 просмотров • 3 месяцев назад

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source

Apple just released and open-sourced FastVLM! FastVLM is a lightning-fast vision-language model that combines rapid image and text understanding with efficient on-device performance. 100% Open Source

Sumanth

43,734 просмотров • 1 год назад

GPT Image 2.6 is now available on fal Markup editing: draw circles, arrows and notes on an image to guide the edit Animated GIF output on both text-to-image and edit Five reasoning effort levels, from low to max

GPT Image 2.6 is now available on fal Markup editing: draw circles, arrows and notes on an image to guide the edit Animated GIF output on both text-to-image and edit Five reasoning effort levels, from low to max

fal

33,456 просмотров • 10 дней назад

KREA 2 is live on fal. KREA's first foundation image model, trained from scratch. Built around a real tradeoff in image generation: - most models force a choice between aesthetic quality and creative control - KREA 2 holds style, mood, and direction across a full workflow, not just one shot - stronger primitive for moodboard-driven, brand-consistent, art-directed pipelines

fal

16,067 просмотров • 5 месяцев назад

New open-source LoRA built in-house: LTX2.3 Audio Reactive LoRA. Built for music-driven video generation: stronger beat sync, graphic texture, color separation, light pulses, particles, and shapes that move with the track. Model:

New open-source LoRA built in-house: LTX2.3 Audio Reactive LoRA. Built for music-driven video generation: stronger beat sync, graphic texture, color separation, light pulses, particles, and shapes that move with the track. Model:

fal

17,789 просмотров • 5 месяцев назад

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: GitHub： Hugging Face： Project Page：

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model 🏆 Text/Image-to-Video Performance Hits Open-Source SOTA 🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout) ⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model ⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes 🤗 Open-Source Links: GitHub： Hugging Face： Project Page：

Meituan LongCat

43,895 просмотров • 1 год назад

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

66,268 просмотров • 10 месяцев назад

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.

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.

fal

26,983 просмотров • 23 дней назад

world models are here! fal is the best platform for real-time audio and video inference. RT for access 😇 incredible work by Eloi Alonso to open source this model

world models are here! fal is the best platform for real-time audio and video inference. RT for access 😇 incredible work by Eloi Alonso to open source this model

fal

123,318 просмотров • 2 лет назад

🎨 I trained 999 Style LoRAs with the fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, Krea 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.

🎨 I trained 999 Style LoRAs with the fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, Krea 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.

ilker

13,060 просмотров • 4 месяцев назад

Krea 2 Turbo drops on fal! Deep aesthetic understanding for concept art, fashion and editorial Compatible with style refs for locked-in visual direction Turbo speed for rapid iteration without losing quality

Krea 2 Turbo drops on fal! Deep aesthetic understanding for concept art, fashion and editorial Compatible with style refs for locked-in visual direction Turbo speed for rapid iteration without losing quality

fal

10,424 просмотров • 5 месяцев назад

I can't believe this is open source. Wan 2.1 has great prompt coherence and the realism is really impressive for an open source model. This is image to video by the way.

I can't believe this is open source. Wan 2.1 has great prompt coherence and the realism is really impressive for an open source model. This is image to video by the way.

Halim Alrasihi

65,185 просмотров • 1 год назад