Flex

AI Photographer Artist Designer Explorer.

[Flex @FlexAIGC]

@Mixwell @OBSBOT_Official @BayL0nGo

[Flex @FlexAIGC]

Paradise

[Flex @FlexAIGC]

@Geostorm77 @hi_lucid_dream which model?

[Flex @FlexAIGC]

Defiant

[Flex @FlexAIGC]

GN

[Flex @FlexAIGC]

Seedream 3.0

[Flex @FlexAIGC]

Daughter of the Ancient Light

[Flex @FlexAIGC]

Prompt Share: This is a highly detailed photograph featuring a woman with short black hair and a slender physique. She is dressed in an ethereal, flowing dress with a deep V-neckline, blending into the surrounding translucent, bubble-like orbs in pastel hues of blue, white, and beige. The background is a gradient of soft, cloudy whites and blues, creating an otherworldly, dreamlike atmosphere. The woman's expression is serene, and the overall composition evokes a sense of floating in a surreal, aquatic environment.

[Flex @FlexAIGC]

Prompt Share: A photograph depicting a surreal scene where a majestic stag's body is composed entirely of swirling, ethereal clouds. The stag stands on a misty, dark ground, its antlers reaching high into a cloudy sky. The clouds blend seamlessly with the stag's form, creating an otherworldly, almost dreamlike atmosphere. The background is shrouded in a dense, gray fog, enhancing the mystical ambiance. The image evokes a sense of fantasy and tranquility, with the soft, diffuse lighting adding to the dreamlike quality

[Flex @FlexAIGC]

In the corners where the mist whispers ancient secrets, dwells the stag of the wind

[Flex @FlexAIGC]

In the corners where the mist whispers ancient secrets, dwells the stag of the wind

[Flex @FlexAIGC]

@moji_ft22801

[Flex @FlexAIGC]

#TianQiong #天穹

[Flex @FlexAIGC]

Born of the moon, forged by the gods (TianQiong 天穹)

[Flex @FlexAIGC]

Born of the moon, forged by the gods (TianQiong 天穹)

[Flex @FlexAIGC]

@moji_ft22801 pony吗？

[Flex @FlexAIGC]

Guardian of the Enchanted Forest

May her light guide you through the mist and remind you that even in the darkness... there is always beauty

[Flex @FlexAIGC]

@kimmonismus and its open source

[Yaofang Liu @stephenajason]

Never seen a R1 moment in video diffusion models??😰Can't things just emerge using very low cost??🧐Certainly can!!!!

🚀 Introducing Pusa now!
Pusa: Thousands Timesteps Video Diffusion Model — A ​​single model​​ that unlocks:
Text-to-Video​​ → ​​
• Image-to-Video​​
​​• Start/End Frames to Video
• Video Transitions
• Video Extensions​​
• Next-frame prediction​​
​​• Novel sampling algorithms(frame-independent noise)​
• ...
Also note that the model still can do text-to-video generation!!
All for just ~$0.1k training cost (about 100 H800 GPU hours)!​

🔍 ​​Key Innovations:​​
​​- Frame-level noise control​​ (FVDM-inspired) → Unmatched flexibility
​​- Non-destructive adaptation​​ → Preserves base T2V capabilities
​​- Universal methodology​​ → Applicable to other SOTA models (e.g., Wan2.1, Hunyuan Video)

💡 ​​100% Open-source​​—code, data, and training scripts ​​release today!​​

📽 ​​Demos and details below ↓​

#AI #VideoGen #OpenSource

[Flex @FlexAIGC]

Gm