Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Wow, killer work from the Krea team 👀 Krea 2 Large is the #2 style-transfer model, already closing in on GPT Image 2. Average Style Fidelity gap from Krea's latest model to OpenAI's GPT Image 2: 0.14 points. Gap from Krea to the rest of the field: more than...

contraben's profile picture

ben

15,092 subscribers

20,158 Aufrufe • vor 3 Monaten •via X (Twitter)

KunstWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Followed up on the same idea to create this clip. Started with a single frame from Krea 2, used GPT Image 2 to create the 3x3 contact sheet preserving the same aesthetic and dropped both into Seedance 2. Some flaws in the final clip but I think the aesthetic holds pretty well from the original image to the seedance gen. Krea 2 → GPT Image 2 → Seedance 2 was all done within Krea seedance prompt in the next post 👇
0:18

Followed up on the same idea to create this clip. Started with a single frame from Krea 2, used GPT Image 2 to create the 3x3 contact sheet preserving the same aesthetic and dropped both into Seedance 2. Some flaws in the final clip but I think the aesthetic holds pretty well from the original image to the seedance gen. Krea 2 → GPT Image 2 → Seedance 2 was all done within Krea seedance prompt in the next post 👇

V

81,267 Aufrufe • vor 2 Monaten

Krea is now built in to Hermes Agent as an image generation API provider, allowing your agent to use Krea 2: a new foundation model trained from scratch to balance aesthetic quality and fine control, with style transfer, moodboard input, and adjustable creativity settings.
0:19

Krea is now built in to Hermes Agent as an image generation API provider, allowing your agent to use Krea 2: a new foundation model trained from scratch to balance aesthetic quality and fine control, with style transfer, moodboard input, and adjustable creativity settings.

Nous Research

137,854 Aufrufe • vor 3 Monaten

take the wheel 🏁 make: ComfyUI, After Effects, Photoshop model: Wan 2.2 I2V + T2V, Krea 2, GPT Image 2.0, Grok Image, Florence2, SYSTMS HUD sound system: Suno
0:11

take the wheel 🏁 make: ComfyUI, After Effects, Photoshop model: Wan 2.2 I2V + T2V, Krea 2, GPT Image 2.0, Grok Image, Florence2, SYSTMS HUD sound system: Suno

Ingi Erlingsson 🪄

28,799 Aufrufe • vor 2 Monaten

Krea 2 is now on Artificial Analysis #1 image model from an independent research lab and #6 globally on text-to-image leaderboard. open-source cooking and coming soon.
0:13

Krea 2 is now on Artificial Analysis #1 image model from an independent research lab and #6 globally on text-to-image leaderboard. open-source cooking and coming soon.

Krea

82,494 Aufrufe • vor 3 Monaten

Well... At least mystique actually has that ability... If you haven't played with the style transfer of Krea 2 Large you are missing out... it's letting me export midjourney styles to something that has a bit more prompt adherence hence this image.
0:10

Well... At least mystique actually has that ability... If you haven't played with the style transfer of Krea 2 Large you are missing out... it's letting me export midjourney styles to something that has a bit more prompt adherence hence this image.

Skye Freeman

34,444 Aufrufe • vor 1 Monat

Arena Trends: Text-to-Image, Jan 2026 – Apr 2026 For most of the year, Google DeepMind and OpenAI traded the top spot within a tight margin - GPT-Image vs. Nano Banana - with the rest of the field clustered below 1,200. Today, GPT-Image-2 breaks away with a score of 1,512, 242 points ahead of #2 Google. The frontier continues to move.
0:19

Arena Trends: Text-to-Image, Jan 2026 – Apr 2026 For most of the year, Google DeepMind and OpenAI traded the top spot within a tight margin - GPT-Image vs. Nano Banana - with the rest of the field clustered below 1,200. Today, GPT-Image-2 breaks away with a score of 1,512, 242 points ahead of #2 Google. The frontier continues to move.

Arena.ai

515,204 Aufrufe • vor 4 Monaten

call could not be complete as dialled 📞 Before @krea 2 was open-sourced I’d pretty much abandoned all image models apart from GPT 2.0. It’s such a fun model to train and the spectrum of what it can do seems pretty expansive - like this live action / thermal imaging mix 🙏
0:12

call could not be complete as dialled 📞 Before @krea 2 was open-sourced I’d pretty much abandoned all image models apart from GPT 2.0. It’s such a fun model to train and the spectrum of what it can do seems pretty expansive - like this live action / thermal imaging mix 🙏

Ingi Erlingsson 🪄

13,845 Aufrufe • vor 1 Monat

A single image generated by GPT Image 2, combined with Seedance 2.0, can already achieve this kind of effect Below is the Image 2 prompt👇
0:15

A single image generated by GPT Image 2, combined with Seedance 2.0, can already achieve this kind of effect Below is the Image 2 prompt👇

Ai Arainz

28,476 Aufrufe • vor 3 Monaten

⚡️ Krea 2 Turbo Style Reference is now available on fal Use one or more reference images to guide the style of entirely new generations. - New subjects and scenes, same style - Adjustable style strength - No per-style LoRA training required
0:11

⚡️ Krea 2 Turbo Style Reference is now available on fal Use one or more reference images to guide the style of entirely new generations. - New subjects and scenes, same style - Adjustable style strength - No per-style LoRA training required

fal

15,784 Aufrufe • vor 1 Monat

introducing GPT Image 2 the most intelligent model to date, able to one-shot nearly any prompt see examples below 👇
0:10

introducing GPT Image 2 the most intelligent model to date, able to one-shot nearly any prompt see examples below 👇

Krea

30,085 Aufrufe • vor 4 Monaten

Asked GPT-5.5 in Codex to reconstruct this model from the image. Pretty close!
0:12

Asked GPT-5.5 in Codex to reconstruct this model from the image. Pretty close!

Ruben Kostandyan

124,735 Aufrufe • vor 4 Monaten

How to create this kind of video game interface animation with GPT Image 2 and Seedance 2 why is it possible now thanks to GPT Image 2? This model is really good in terms of details and design interface. Also, this model allows you to rework multiple times an image without damaging the quality let me share my workflow👇
0:15

How to create this kind of video game interface animation with GPT Image 2 and Seedance 2 why is it possible now thanks to GPT Image 2? This model is really good in terms of details and design interface. Also, this model allows you to rework multiple times an image without damaging the quality let me share my workflow👇

INK

246,724 Aufrufe • vor 4 Monaten

I built a GPT 2 workflow that turns one image into 20 viral ads GPT image 2 is the most powerful image model out there And you can use it to scale your ads campaign with Arcads workflow Comment Arcads to get the workflow now
0:10

I built a GPT 2 workflow that turns one image into 20 viral ads GPT image 2 is the most powerful image model out there And you can use it to scale your ads campaign with Arcads workflow Comment Arcads to get the workflow now

Romain Torres

80,262 Aufrufe • vor 4 Monaten

From the clouds to Burj Khalifa in a cinematic drone journey. Created with GPT Image 2 + Seedance 2.0 on insMind
0:15

From the clouds to Burj Khalifa in a cinematic drone journey. Created with GPT Image 2 + Seedance 2.0 on insMind

Stonic AI

11,135 Aufrufe • vor 2 Monaten

This is what football in GTA 6 could look like 🤯🔥 Made it using GPT Image 2 x Seedance 2.0 in Pollo AI from a single gameplay style storyboard image. Workflow below ↓
0:15

This is what football in GTA 6 could look like 🤯🔥 Made it using GPT Image 2 x Seedance 2.0 in Pollo AI from a single gameplay style storyboard image. Workflow below ↓

Abdul Șhakoor

30,858 Aufrufe • vor 2 Monaten

[build]⛏️[/rebuild] over the past year I've been working on a set of LoRAs for seamless transitions and now that they're starting to click I'm experimenting with ways of integrating performance Made in ComfyUI with Krea 2 / GPT Image 2.0 / Wan 2.2 / SYSTMS HUD Suno
0:11

[build]⛏️[/rebuild] over the past year I've been working on a set of LoRAs for seamless transitions and now that they're starting to click I'm experimenting with ways of integrating performance Made in ComfyUI with Krea 2 / GPT Image 2.0 / Wan 2.2 / SYSTMS HUD Suno

Ingi Erlingsson 🪄

23,853 Aufrufe • vor 1 Monat

Breath of Smoke the deadliest masters never need to draw their blades made with GPT Image 2 + Seedance 2 on OpenArt Sharing the prompt below
0:15

Breath of Smoke the deadliest masters never need to draw their blades made with GPT Image 2 + Seedance 2 on OpenArt Sharing the prompt below

Latte

16,683 Aufrufe • vor 2 Monaten

Vox-style AI motion graphics, but built as a paper-cut animation from one real portrait. Built with GPT image 2 + Seedance 2 on insMind. Four Hero scenes. One continuous 15-second story. Steal the prompt and workflow below 👇
0:15

Vox-style AI motion graphics, but built as a paper-cut animation from one real portrait. Built with GPT image 2 + Seedance 2 on insMind. Four Hero scenes. One continuous 15-second story. Steal the prompt and workflow below 👇

insMind

33,567 Aufrufe • vor 1 Monat

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.
0:15

Player stats UI animation with GPT Image 2 and MiniMax H3. This model is amazing for UI animations. Give GPT Image 2 your character image and ask it to create a stats UI. Then use that UI as a reference for MiniMax H3. You can check the prompt in the replies.

Kōda

41,330 Aufrufe • vor 23 Tagen

From a single AI-generated image to a cinematic video. ✨ Created the image in GPT-2, then brought it to life with Seedance 2.0. One idea → one image → a whole cinematic world. Prompt below ⤵️
0:15

From a single AI-generated image to a cinematic video. ✨ Created the image in GPT-2, then brought it to life with Seedance 2.0. One idea → one image → a whole cinematic world. Prompt below ⤵️

Alina Ai

30,495 Aufrufe • vor 1 Tag