gpt-4o is the lead on the updated leader-board: https://
artificialanalysis.ai/text-to-image/
arena?tab=Leaderboard
…
MULTIMODAL AI
-
GPT-4o Leads Updated Text-to-Image Model Leaderboard
By
–
-
Artificial Analysis: Comparing AI Models Across Intelligence, Speed, Price
By
–
People at Artificial Analysis are doing good job on comparing models across important axes: intelligence, speed, and price. And for all modalities and tasks: language, speech, video, image, code. Benchmarks are not perfect but there is no other way to know a model is better than
-
ChatGPT Tasks Could Combine GPT-4o Image Generation Web Search
By
–
@sama , wouldn’t it be amazing if ChatGPT’s Task feature could use GPT-4o’s image generation and web search at the same time?
-
Sora AI Generates 1980s Anime Poster Art From Text Prompts
By
–
Game of Thrones vs Stranger Things as "1980s japanese anime poster art" Do your own by simply asking Sora for:
"1980s japanese anime poster art [ENTER ANYTHING]" -
Create Van Gogh-Style Videos Using Wan2.1 LoRAs
By
–
You can create Van Gogh-style videos on Replicate.
— Replicate (@replicate) 1 avril 2025
Read how in our latest post on Wan2.1 LoRAs:https://t.co/MyIEFLvKsu pic.twitter.com/XWffh9qMnZYou can create Van Gogh-style videos on Replicate. Read how in our latest post on Wan2.1 LoRAs: https://
replicate.com/blog/wan-t2v-l
oras
… -
Gen-4 Now Available for All Creative Partners and Enterprise
By
–
Gen-4 is now available for all Creative Partners, Enterprise customers and paid plans. pic.twitter.com/OJMHRREcV3
— Runway (@runwayml) 1 avril 2025Gen-4 is now available for all Creative Partners, Enterprise customers and paid plans.
-
Vision Large Language Models Guide: Teaching LLMs Image Understanding
By
–
If you’re looking for a read on how to teach LLMs to understand images and videos, the newly released Vision Large Language Models (vLLMs) by @cwolferesearch is a great choice! Link: https://
cameronrwolfe.substack.com/p/vision-llms -
SORA Image Generation Outperforms ChatGPT for Family Portraits
By
–
SORA = Less nerfing Generating images inside SORA is 10x better than inside ChatGPT. I've made a family portrait out of 4 random bad headshots of us, and yeah its coming out crazy good. Not upscaled. (1024×1536)
-
Discover how to combine ChatGPT 4o Image with ManusAI, BoltNew or Lovable
By
–
#ChatGPT 4o Image is a KILLER, we know. But if you combine it with #ManusAI, #BoltNew or #Lovable, it becomes MAGIC! In 10 minutes, you can create the website or app of your dreams. Doubt it? Judge for yourself with this tutorial → https://youtu.be/knO5RT4-DGc
-
Music video entirely generated with Gen-4 AI
By
–
Monkey see, monkey do. A music video generated entirely with Gen-4. pic.twitter.com/QVwp6HvDoX
— Runway (@runwayml) 1 avril 2025Monkey see, monkey do. A music video generated entirely with Gen-4.