[B! å‹•ç”»ç”Ÿæˆ] petite_blueã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

petite_blue id:petite_blue

å‹•ç”»ç”Ÿæˆã«é–¢ã™ã‚‹petite_blueã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ (12)

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

${{author_name}}$
{{author_name}}{{created}}
{{ #comment }}{{ comment }}{{ /comment }}
- {{ label }}

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

ç„¡æ–™ã®å‹•ç”»ç”ŸæˆAIã€ŒWan2.2ã€ãŒå‡„ã™ãŽã‚‹ã€€PCãƒãƒ¼ã‚«ãƒ«ã§ã“ã®å“è³ªãŒå‡ºã›ã‚‹ã¨ã¯ (1/5)
ã‚¢ãƒªãƒãƒã®å‹•ç”»ç”Ÿæˆãƒ¢ãƒ‡ãƒ«ã€ŒWan2.2 14Bã€i2vã‚’ä½¿ã„ã€æ˜Žæ—¥æ¥åã•ã‚“ï¼ˆã“ã®é€£è¼‰ã«ã‚ˆãç™»å ´ã™ã‚‹ä½œä¾‹ã‚ãƒ£ãƒ©ã‚¯ã‚¿ãƒ¼ï¼‰ã«éŠƒã‚’æ§‹ãˆã•ã›ãŸå‹•ç”»ã®ä¸€éƒ¨ï¼ˆç†è€…ä½œæˆï¼‰ 7æœˆ28æ—¥ã«å…¬é–‹ã•ã‚ŒãŸä¸å›½ãƒ»ã‚¢ãƒªãƒãƒã®å‹•ç”»ç”ŸæˆAIãƒ¢ãƒ‡ãƒ«ã€ŒWan2.2ã€ãŒã™ã•ã¾ã˜ã„æ€§èƒ½ã‚’ç™ºæ®ã—ã¦ã„ã¾ã™ã€‚ãƒãƒ¼ã‚«ãƒ«PCç’°å¢ƒã§åˆ©ç”¨ã§ãã‚‹ã‚ªãƒ¼ãƒ—ãƒ³ãƒ¢ãƒ‡ãƒ«ã¨ã—ã¦å…¬é–‹ã•ã‚Œã¾ã—ãŸãŒã€ãƒ˜ã‚¿ãªå•†ç”¨AIã‚¯ãƒ©ã‚¦ãƒ‰ã‚µãƒ¼ãƒ“ã‚¹ã‚’è¶…ãˆã¦ã„ã‚‹ã¨æ„Ÿã˜ã•ã›ã‚‹ã»ã©ã€é«˜å“è³ªãªAIå‹•ç”»ãŒç”Ÿæˆå¯èƒ½ã§ã™ã€‚2æœˆãƒªãƒªãƒ¼ã‚¹ã®ã€ŒWan2.1ã€ã§ã‚‚é«˜ã„è©•ä¾¡ã‚’å¾—ã¦ã„ã¾ã—ãŸãŒã€ãã‚Œã‚’é¥ã‹ã«è¶…ãˆã¦ãŠã‚Šã€æ¥ç•Œã‚’å¸å·»ã—ãã†ãªé›°å›²æ°—ã‚’æ„Ÿã˜ã¾ã—ãŸã€‚ â€»è¨˜äº‹é…ä¿¡å…ˆã®è¨å®šã«ã‚ˆã£ã¦ã¯å›³ç‰ˆã‚„å‹•ç”»ç‰ãŒæ£ã—ãè¡¨ç¤ºã•ã‚Œãªã„ã“ã¨ãŒã‚ã‚Šã¾ã™ã€‚ãã®å ´åˆã¯ASCII.jpã‚’ã”è¦§ãã ã•ã„ å®Ÿå†™ã‚‚ã‚¢ãƒ‹ãƒ¡ã‚‚é«˜æ€§èƒ½ Wan2.2ã®æ€§èƒ½ã®é«˜ã•ã¯è§¦ã‚Œã°è§¦ã‚‹ã»ã©ã‚ã‹ã£ã¦ãã¾ã™ã€‚ã‚«ãƒƒãƒ—éººã€ç®¸ã€éººãªã©ã€è¤‡æ•°ã®ã‚ªãƒ–ã‚¸ã‚§ã‚¯ãƒˆãŒé–¢ã‚ã‚‹ãŸã‚ã€ç”»åƒã‚„
petite_blue 2025/08/12
å‹•ç”»ç”Ÿæˆ

ai
ãƒªãƒ³ã‚¯
SELF-FORCING - NUEVO MODELO DE DE VIDEO EN LOCAL ULTRA RÃPIDO Y SIN CENSURA
petite_blue 2025/06/23
ai

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
Self-ForcingãŒå¼·åŠ›ã™ãŽã‚‹ã€€å‹•ç”»ã®ãƒªã‚¢ãƒ«ã‚¿ã‚¤ãƒ ç”Ÿæˆã ã‘ã§ãªãè¨€èªžãƒ¢ãƒ‡ãƒ«ã‚„éŸ³å£°ã€å¼·åŒ–å¦ç¿’ãŒåŠ‡çš„ã«é«˜æ€§èƒ½åŒ–ã™ã‚‹å¯èƒ½æ€§ï½œshi3z
Self-ForcingãŒå¼·åŠ›ã™ãŽã‚‹ã€€å‹•ç”»ã®ãƒªã‚¢ãƒ«ã‚¿ã‚¤ãƒ ç”Ÿæˆã ã‘ã§ãªãè¨€èªžãƒ¢ãƒ‡ãƒ«ã‚„éŸ³å£°ã€å¼·åŒ–å¦ç¿’ãŒåŠ‡çš„ã«é«˜æ€§èƒ½åŒ–ã™ã‚‹å¯èƒ½æ€§ æ˜¨æ—¥è¦‹ã¤ã‘ãŸã€ŒSelf-Forcingã€ã¨ã„ã†æ‰‹æ³•ãŒå¼·åŠ›ã™ãŽã¦ä½“ã®éœ‡ãˆãŒæ¢ã¾ã‚‰ãªã„ã€‚è»½ãé¬±ã«ãªã‚Šãã†ã ã€‚ https://arxiv.org/html/2506.08009v1 Adobeã¨ãƒ†ã‚ã‚µã‚¹å¤§å¦ã‚ªãƒ¼ã‚¹ãƒãƒ³æ ¡ã®å…±åŒç ”ç©¶ã«ã‚ˆã£ã¦å°Žã‹ã‚ŒãŸã“ã®æ‰‹æ³•ã‚’ä½¿ã†ã¨ã€å‹•ç”»ã‚’ãƒªã‚¢ãƒ«ã‚¿ã‚¤ãƒ ã§ç”Ÿæˆã™ã‚‹ã“ã¨ãŒã§ãã‚‹ã€‚ãƒªã‚¢ãƒ«ã‚¿ã‚¤ãƒ ã ã€‚ ã“ã‚Œã¾ã§ã¯ã€5ç§’ã®å‹•ç”»ç”Ÿæˆã«æ•°åˆ†ã‹ã‹ã£ã¦ã„ãŸãŒã€5ç§’ã®å‹•ç”»ã‚’5ç§’ã§ä½œã‚Œã‚‹ã¨è¨€ã†ã“ã¨ã§ã‚ã‚‹ã€‚ã¨ã„ã†ã‹ã€è¦‹ã¦ã„ã‚‹å‹•ç”»ã‚’ãƒªã‚¢ãƒ«ã‚¿ã‚¤ãƒ ã«å¤‰åŒ–ã•ã›ã‚‹ã“ã¨ãŒã§ãã‚‹ã€‚æœ¬è³ªçš„ãªæ„å‘³ã§ã‚¤ãƒ³ã‚¿ãƒ©ã‚¯ãƒ†ã‚£ãƒ–ãªæ˜ ç”»ã‚’ä½œã‚‹ã“ã¨ãŒã§ãã‚‹ã¨è¨€ã†ã“ã¨ã ã€‚ã“ã‚Œã¾ã§ã®ã€Œãƒªã‚¢ãƒ«ãª3DCGã€ã¨ã¯æ¬¡å…ƒã®é•ã†ã€ã¾ã•ã«AIã«ã‚ˆã‚‹ã‚²ãƒ¼ãƒ ãƒ¬ãƒ³ãƒ€ãƒªãƒ³ã‚°ã®é©å‘½ãŒèµ·ãã¦ã„ã‚‹ã€‚ ä»Šã€ã™ã§ã«éŸ³æ¥½ç”Ÿæˆåˆ†é‡Žã§ã¯ã€30ç§’ã§
petite_blue 2025/06/23
ai

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
å¤©æ‰ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ãƒ»ã‚¤ãƒªãƒ¤ã‚¹ãƒ•ã‚£ãƒ¼ãƒ«æ°ã€çªå¦‚ãƒãƒ¼ã‚«ãƒ«ç’°å¢ƒã§å‹•ã‹ã™ã¨ã‚“ã§ã‚‚ãªã„å‹•ç”»ç”ŸæˆAIã€ŒFramePackã€ã‚’æŠ•ä¸‹ã—ç•ŒéšˆãŒæ²¸é¨°ä¸
sponsored ãƒ•ã‚¡ãƒ¼ã‚¦ã‚§ã‚¤ã®æœ€æ–°ãƒ¢ãƒ‡ãƒ«ã‹ã‚‰è¦‹ãˆã¦ãã‚‹ãã‚Œãžã‚Œã®é…åŠ›ã¨ã¯ï¼Ÿ ã‚¹ãƒžãƒ¼ãƒˆãƒãƒ³ãƒ‰ã¨ã‚¹ãƒžãƒ¼ãƒˆã‚¦ã‚©ãƒƒãƒã€ã©ã£ã¡ãŒã„ã„ï¼Ÿ ã©ã£ã¡ã‚’é¸ã¶ï¼Ÿ æœ€æ–°ãƒ¢ãƒ‡ãƒ«ã§è€ƒãˆã‚‹ sponsored MSIã®23.6ã‚¤ãƒ³ãƒãƒ¢ãƒ‹ã‚¿ãƒ¼ã€ŒMAG 242Cã€ã‚’ãƒ¬ãƒ“ãƒ¥ãƒ¼ ç‰©ä¾¡é«˜ãªã®ã«æ€§èƒ½ã‚¢ãƒƒãƒ—ã§ä¾¡æ ¼ã‚’ä¸‹ã’ã‚‹ã¨ã„ã†ã€ã‚ã‚ŠãŒãŸã„ã‚²ãƒ¼ãƒŸãƒ³ã‚°ãƒ‡ã‚£ã‚¹ãƒ—ãƒ¬ãƒ¼ã‚’è¤‡æ•°è²·ã„ã—ãŸã„ sponsored CData Arcã§åŸºå¹¹ã‚·ã‚¹ãƒ†ãƒ ã®ãƒ‡ãƒ¼ã‚¿ã‚’kintoneã«å–ã‚Šå‡ºã—ãŸã‚‰ã€æ¥å‹™ãŒå¤‰ã‚ã£ãŸ æ®‹æ¥åœ°ç„çµ‚äº†ã€€ERPã¨kintoneã‚’é€£æºã•ã›ãŸã‚‰ã€è¦‹ç©ã‚‚ã‚Šã‚‚åœ¨åº«ç®¡ç†ã‚‚çˆ†é€Ÿã« sponsored åŸºå¹¹ã‚·ã‚¹ãƒ†ãƒ ã¨kintoneã¨ã®é€£æºã€ãƒãƒ£ãƒ¬ãƒ³ã‚¸ã—ãŸã‚‰DXãŒè¦‹ãˆã‚‹ è§¦ã‚ŒãŸã‚‰æ€–ã„ERPã€€ãªãœé‡åŽšé•·å¤§ã«ãªã£ã¦ã—ã¾ã£ãŸã®ã‹ï¼Ÿã€€ã‚µã‚¤ãƒœã‚¦ã‚ºã¨CDataãŒèªžã‚‹ sponsored MSIã€ŒMAG B860M MORTAR WIFIã€ãƒ¬ãƒ“ãƒ¥ãƒ¼ ãƒžã‚¤ã‚¯ãƒã‚¿ãƒ¯ãƒ¼
petite_blue 2025/04/19
ai

å‹•ç”»ç”Ÿæˆ

ç”»åƒç”Ÿæˆ
ãƒªãƒ³ã‚¯
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation Yupeng Zhou1* Daquan Zhou2â€¡â€ Mingming Cheng1 Jiashi Feng2 Qibin Hou1â€¡â€
petite_blue 2024/05/06
ai

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
EMO
We proposed EMO, an expressive audio-driven portrait-video generation framework. Input a single reference image and the vocal audio, e.g. talking and singing, our method can generate vocal avatar videos with expressive facial expressions, and various head poses, meanwhile, we can generate videos with any duration depending on the length of input video. Overview of the proposed method. Our framewor
petite_blue 2024/02/29
ai

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
æŽ§ãˆç›®ã«è¨€ã£ã¦é©å‘½ã€‚OpenAIã€å‹•ç”»ç”ŸæˆAIãƒ¢ãƒ‡ãƒ«ã€ŒSoraã€ç™ºè¡¨
OpenAIã¯2æœˆ15æ—¥ï¼ˆç¾åœ°æ™‚é–“ï¼‰ã€ãƒ†ã‚ã‚¹ãƒˆã‹ã‚‰æœ€å¤§1åˆ†é–“ã®å‹•ç”»ã‚’ç”Ÿæˆã§ãã‚‹å‹•ç”»ç”ŸæˆAIãƒ¢ãƒ‡ãƒ«ã€ŒSoraã€ã‚’å¤§é‡ã®ãƒ‡ãƒ¢å‹•ç”»ã¨å…±ã«ç™ºè¡¨ã—ãŸã€‚è¤‡æ•°ã®ã‚ãƒ£ãƒ©ã‚¯ã‚¿ãƒ¼ã€ç‰¹å®šã®ç¨®é¡žã®å‹•ãã€è¢«å†™ä½“ã¨èƒŒæ™¯ã®æ£ç¢ºãªè©³ç´°ã‚’å«ã‚€è¤‡é›‘ãªã‚·ãƒ¼ãƒ³ã‚’ç”Ÿæˆã™ã‚‹ã“ã¨ãŒã§ãã‚‹ã¨ã„ã†ã€‚ ãƒ—ãƒãƒ³ãƒ—ãƒˆã‹ã‚‰ç ´ç¶»ã®ãªã„å‹•ç”»ã‚’ç”Ÿæˆ Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W Prompt: â€œBeautiful, snowyâ€¦ pic.twitter.com
petite_blue 2024/02/17
openai

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
Sora: Creating video from text
Sora Creating video from text Sora is an AI model that can create realistic and imaginative scenes from text instructions. Read technical report Weâ€™re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve probl ems that require real-world interaction. Introducing Sora, our text-to-video model. Sora can generate videos up to a mi
petite_blue 2024/02/17
openai

video

å‹•ç”»ç”Ÿæˆ

llm
ãƒªãƒ³ã‚¯
D-ID Creative Realityâ„¢ï¸
Redefining digital connections. Craft a lifelike conversational AI Agent that knows everything about you, your products, and services, all while reflecting your brandâ€™s look, voice, and tone.
petite_blue 2023/03/23
ai

å‹•ç”»ç”Ÿæˆ

video
ãƒªãƒ³ã‚¯
Make-A-Video by Meta AI
Make-A-Video is a state-of-the-art AI system that generates videos from text. Make-A-Video research builds on the recent progress made in text-to-image generation techno logy built to enable text-to-video generation. The system uses images with descriptions to learn what the world looks like and how it is often described. It also uses unlabeled videos to learn how the world moves. With this data, M
petite_blue 2022/10/03
ç”»åƒç”Ÿæˆ

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
ãƒ†ã‚ã‚¹ãƒˆã‚’åŸºã«ã™ã‚‹å‹•ç”»ç”ŸæˆAIã€ŒPhenakiã€ã‚’åŒ¿åã®ç ”ç©¶è€…ãŒå…¬é–‹ã€å®‡å®™é£›è¡Œå£«ãŒè¸Šã£ãŸã‚Šãƒ†ãƒ‡ã‚£ãƒ™ã‚¢ãŒæ³³ã„ã ã‚Šã™ã‚‹ã‚µãƒ³ãƒ—ãƒ«å‹•ç”»ã‚‚
è¿‘å¹´ã¯ç”»åƒç”ŸæˆAIã®ã€ŒStable Diffusionã€ãŒã‚¯ã‚ªãƒªãƒ†ã‚£ã®é«˜ã•ã‚’è¦‹ã›ã¤ã‘ã¦è©±é¡Œã¨ãªã£ã¦ã„ã¾ã™ãŒã€æ–°ãŸã«åŒ¿åã®ç ”ç©¶è€…ãŒãƒ†ã‚ã‚¹ãƒˆã‚’åŸºã«å‹•ç”»ã‚’ç”Ÿæˆã™ã‚‹AIã€ŒPhenakiã€ã‚’ç™ºè¡¨ã—ã¾ã—ãŸã€‚ Phenaki https://phenaki.video/ Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions | OpenReview https://openreview.net/forum?id=vOEXS39nOF ã€ŒPhenakiã€ã®è§£èª¬ãƒšãƒ¼ã‚¸ã‚’é–‹ãã¨ã€ä¸Šéƒ¨ã«ã€ŒPhenakiã€ã§ç”Ÿæˆã—ãŸã¨ã•ã‚Œã‚‹3æœ¬ã®ã‚·ãƒ§ãƒ¼ãƒˆå‹•ç”»ãŒè¡¨ç¤ºã•ã‚Œã¦ã„ã¾ã—ãŸã€‚ ä¸€ç•ªå·¦ã®å‹•ç”»ã¯ã€ã€ŒA photorealistic teddy bear is swimming in the ocean at San Fran
petite_blue 2022/10/03
ç”»åƒç”Ÿæˆ

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
Phenaki
A model for generating videos from text, with prompts that can change over time, and videos that can be as long as multiple minutes. Read Paper The water is magical Prompts used: A photorealistic teddy bear is swimming in the ocean at San Francisco The teddy bear goes under water The teddy bear keeps swimming under the water with colorful fishes A panda bear is swimming under water Chilling on the
petite_blue 2022/10/03
ç”»åƒç”Ÿæˆ

å‹•ç”»ç”Ÿæˆ
ãƒªãƒ³ã‚¯
1