home.social

#text2image — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #text2image, aggregated by home.social.

  1. Introducing ChatGPT Images, powered by our flagship new image generation model.

    - Stronger instruction following
    - Precise editing
    - Detail preservation
    - 4x faster than before

    Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

    x.com/openai/status/2000990989

    @_OpenAI #AI #Text2Image #OpenAI

  2. Introducing ChatGPT Images, powered by our flagship new image generation model.

    - Stronger instruction following
    - Precise editing
    - Detail preservation
    - 4x faster than before

    Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

    x.com/openai/status/2000990989

    @_OpenAI

  3. Introducing ChatGPT Images, powered by our flagship new image generation model.

    - Stronger instruction following
    - Precise editing
    - Detail preservation
    - 4x faster than before

    Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

    x.com/openai/status/2000990989

    @_OpenAI #AI #Text2Image #OpenAI

  4. Introducing ChatGPT Images, powered by our flagship new image generation model.

    - Stronger instruction following
    - Precise editing
    - Detail preservation
    - 4x faster than before

    Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

    x.com/openai/status/2000990989

    @_OpenAI #AI #Text2Image #OpenAI

  5. Introducing ChatGPT Images, powered by our flagship new image generation model.

    - Stronger instruction following
    - Precise editing
    - Detail preservation
    - 4x faster than before

    Rolling out today in ChatGPT for all users, and in the API as GPT Image 1.5.

    x.com/openai/status/2000990989

    @_OpenAI #AI #Text2Image #OpenAI

  6. #OldAi

    Zero Tolerance, also Null Toleranz hat ein Gesicht. Text to Image | DeepaI; 0 Toleranz! #text2image

  7. #OldAi

    Zero Tolerance, also Null Toleranz hat ein Gesicht. Text to Image | DeepaI; 0 Toleranz! #text2image

  8. PixelsArt is now available at my Clean #Text2Image #AI #aiimage #genAI! This should accelerate the artwork post-processing work by working on top of an #image rather than drawing everything from scratch.

    Check it out at: perchance.org/clean-text2image

    Disclaimer: I'm the generator maintainer.

  9. PixelsArt is now available at my Clean #Text2Image #AI #aiimage #genAI! This should accelerate the artwork post-processing work by working on top of an #image rather than drawing everything from scratch.

    Check it out at: perchance.org/clean-text2image

    Disclaimer: I'm the generator maintainer.

  10. @AISearch on YouTube!

    Google's AI just CRUSHED image editing!

    youtu.be/2qYjhHtKxB8?feature=s

    Poor adobe inc 😉

  11. Midjourney V7 10 Dinge, die Du wissen musst

    Neues Upscaling verblüffend stark
    Prompting jetzt viel flexibler
    Realismus auf krassem Level

    #KI #Midjourney #midjourneyv7 #Text2Image #ai #artificialintelligence #kuenstlicheintelligenz

    Jetzt LIKEN, teilen LESEN und FOLGEN!

    kinews24.de/midjourney-v7-komp

  12. Midjourney V7 10 Dinge, die Du wissen musst

    Neues Upscaling verblüffend stark
    Prompting jetzt viel flexibler
    Realismus auf krassem Level

    #KI #Midjourney #midjourneyv7 #Text2Image #ai #artificialintelligence #kuenstlicheintelligenz

    Jetzt LIKEN, teilen LESEN und FOLGEN!

    kinews24.de/midjourney-v7-komp

  13. There's an ongoing drive for #FOSS #distributedAI computing, e.g. #aiHorde. It's not perfect & needs a 3rd-party security audit, but is somewhere on the path to more-secure non-local #edgecomputing for devices like phones that can't load large #AImodels or run popular #text2text / #text2image #genAI applications locally.

    *NB: Apologies to Horde volunteers if I just bumped your traffic past reasonable limits.*

    aihorde.net

  14. There's an ongoing drive for #FOSS #distributedAI computing, e.g. #aiHorde. It's not perfect & needs a 3rd-party security audit, but is somewhere on the path to more-secure non-local #edgecomputing for devices like phones that can't load large #AImodels or run popular #text2text / #text2image #genAI applications locally.

    *NB: Apologies to Horde volunteers if I just bumped your traffic past reasonable limits.*

    aihorde.net

  15. There's an ongoing drive for #FOSS #distributedAI computing, e.g. #aiHorde. It's not perfect & needs a 3rd-party security audit, but is somewhere on the path to more-secure non-local #edgecomputing for devices like phones that can't load large #AImodels or run popular #text2text / #text2image #genAI applications locally.

    *NB: Apologies to Horde volunteers if I just bumped your traffic past reasonable limits.*

    aihorde.net

  16. There's an ongoing drive for #FOSS #distributedAI computing, e.g. #aiHorde. It's not perfect & needs a 3rd-party security audit, but is somewhere on the path to more-secure non-local #edgecomputing for devices like phones that can't load large #AImodels or run popular #text2text / #text2image #genAI applications locally.

    *NB: Apologies to Horde volunteers if I just bumped your traffic past reasonable limits.*

    aihorde.net

  17. There's an ongoing drive for #FOSS #distributedAI computing, e.g. #aiHorde. It's not perfect & needs a 3rd-party security audit, but is somewhere on the path to more-secure non-local #edgecomputing for devices like phones that can't load large #AImodels or run popular #text2text / #text2image #genAI applications locally.

    *NB: Apologies to Horde volunteers if I just bumped your traffic past reasonable limits.*

    aihorde.net

  18. There's an ongoing drive to create #FOSS open source, #distibutedAI computing. #AI_Horde is one such project, and possibly the most well-known right now. It's not perfect, and no one I know has done an in-depth security analysis, but I suspect this is somewhere on the path to safer non-local AI computing for edge devices like phones that simply can't run larger #AImodels or popular #text2text or #text2image #genAI applications locally.

    NB: My apologies to the Horde volunteers if I just bumped your traffic past reasonable limits.

    aihorde.net

  19. There's an ongoing drive to create #FOSS open source, #distibutedAI computing. #AI_Horde is one such project, and possibly the most well-known right now. It's not perfect, and no one I know has done an in-depth security analysis, but I suspect this is somewhere on the path to safer non-local AI computing for edge devices like phones that simply can't run larger #AImodels or popular #text2text or #text2image #genAI applications locally.

    NB: My apologies to the Horde volunteers if I just bumped your traffic past reasonable limits.

    aihorde.net

  20. There's an ongoing drive to create #FOSS open source, #distibutedAI computing. #AI_Horde is one such project, and possibly the most well-known right now. It's not perfect, and no one I know has done an in-depth security analysis, but I suspect this is somewhere on the path to safer non-local AI computing for edge devices like phones that simply can't run larger #AImodels or popular #text2text or #text2image #genAI applications locally.

    NB: My apologies to the Horde volunteers if I just bumped your traffic past reasonable limits.

    aihorde.net

  21. There's an ongoing drive to create #FOSS open source, #distibutedAI computing. #AI_Horde is one such project, and possibly the most well-known right now. It's not perfect, and no one I know has done an in-depth security analysis, but I suspect this is somewhere on the path to safer non-local AI computing for edge devices like phones that simply can't run larger #AImodels or popular #text2text or #text2image #genAI applications locally.

    NB: My apologies to the Horde volunteers if I just bumped your traffic past reasonable limits.

    aihorde.net

  22. There's an ongoing drive to create #FOSS open source, #distibutedAI computing. #AI_Horde is one such project, and possibly the most well-known right now. It's not perfect, and no one I know has done an in-depth security analysis, but I suspect this is somewhere on the path to safer non-local AI computing for edge devices like phones that simply can't run larger #AImodels or popular #text2text or #text2image #genAI applications locally.

    NB: My apologies to the Horde volunteers if I just bumped your traffic past reasonable limits.

    aihorde.net

  23. - Nova Premier (Q1 2025):
    • Ultimate #MachineLearning capabilities
    • Advanced #ModelDistillation
    • Complex #ReasoningAI tasks
    #TeacherModel functionality

    🎨 Creative Suite #AIGC #GenerativeAI:
    - #NovaCanvas:
    #Text2Image generation

  24. - Nova Premier (Q1 2025):
    • Ultimate #MachineLearning capabilities
    • Advanced #ModelDistillation
    • Complex #ReasoningAI tasks
    #TeacherModel functionality

    🎨 Creative Suite #AIGC #GenerativeAI:
    - #NovaCanvas:
    #Text2Image generation

  25. - Nova Premier (Q1 2025):
    • Ultimate #MachineLearning capabilities
    • Advanced #ModelDistillation
    • Complex #ReasoningAI tasks
    #TeacherModel functionality

    🎨 Creative Suite #AIGC #GenerativeAI:
    - #NovaCanvas:
    #Text2Image generation

  26. - Nova Premier (Q1 2025):
    • Ultimate #MachineLearning capabilities
    • Advanced #ModelDistillation
    • Complex #ReasoningAI tasks
    #TeacherModel functionality

    🎨 Creative Suite #AIGC #GenerativeAI:
    - #NovaCanvas:
    #Text2Image generation

  27. - Nova Premier (Q1 2025):
    • Ultimate #MachineLearning capabilities
    • Advanced #ModelDistillation
    • Complex #ReasoningAI tasks
    #TeacherModel functionality

    🎨 Creative Suite #AIGC #GenerativeAI:
    - #NovaCanvas:
    #Text2Image generation

  28. #Text2Image with large models is both kinda boring and getting better by the minute. What is *not* boring is fine tuning larger models with smaller datasets for more nuanced output. Way more practical. Today I tuned weights on the #Flux1 model. Did not disappoint...

    1/7

  29. with large models is both kinda boring and getting better by the minute. What is *not* boring is fine tuning larger models with smaller datasets for more nuanced output. Way more practical. Today I tuned weights on the model. Did not disappoint...

    1/7

  30. #Text2Image with large models is both kinda boring and getting better by the minute. What is *not* boring is fine tuning larger models with smaller datasets for more nuanced output. Way more practical. Today I tuned weights on the #Flux1 model. Did not disappoint...

    1/7

  31. #Text2Image with large models is both kinda boring and getting better by the minute. What is *not* boring is fine tuning larger models with smaller datasets for more nuanced output. Way more practical. Today I tuned weights on the #Flux1 model. Did not disappoint...

    1/7

  32. Today’s Ai Art and Animation ...

    Optimizing Hollywood workflows, Filmmakers have nothing to fear (yet), Grok 1.5, making comics, and being photographed by the paparazzi.

    aiartandanimation.substack.com

    #GenerativeAI #AIArt #AIAnimation #AiVideo #Text2Image #Text2Video #CreativeAI #GenAI #AICreativity

  33. Interesting and encouraging for ai animators ... YouTube short-form video platform now averages over 70 billion daily views and over 25% of channels in YouTube’s Partner Program monetize their videos through revenue-sharing on Shorts.

    techcrunch.com/2024/03/28/yout

    #GenerativeAI #AIArt #AIAnimation #AiVideo #Text2Image #Text2Video #CreativeAI #GenAI #AICreativity

  34. #514 Ai Art and Animation out now.

    Danny DeVito is Wolverine, a movie trailer created using a free Ai tool, GenAi news and tools, and more.

    AiArtandAnimation.com

    #GenerativeAI,#AIArt,#AIAnimation,#AIVideo,#Text2Image,#Text2Video,#CreativeAI,#DigitalArt

  35. Discussion about #generativeAI is also about it's requirements in terms of compute. But big progress is made in running models on smaller platforms, like this #text2image model, #mobilediffusion that runs on high-end android and iOS devices.
    blog.research.google/2024/01/m

  36. Discussion about #generativeAI is also about it's requirements in terms of compute. But big progress is made in running models on smaller platforms, like this #text2image model, #mobilediffusion that runs on high-end android and iOS devices.
    blog.research.google/2024/01/m