"Image 5 can now work at native resolutions of up to 4 megapixels, a massive increase from the previous-gen model, which could natively generate images at 1 megapixel but then would upscale them to 4 megapixels. The new model is also better at rendering humans, the company said. Image 5 also enables layered and prompt-based editing - the model treats different objects as layers and allows you to edit them using prompts,"
"Adobe's Firefly site has supported third-party models from AI labs like OpenAI, Google, Runway, Topaz, and Flux to augment its appeal to its creative customer base, and now the company is taking that a step further by letting users create custom models based on their art style. Currently in a closed beta, this feature lets users drag and drop assets, such as images, illustrations and sketches, to create a custom image model based on their style."
Firefly Image 5 generates images natively up to 4 megapixels, a fourfold native-resolution increase over the prior model and improved human rendering. The model supports layered and prompt-based editing, treating objects as editable layers with tools like resize and rotate while preserving image detail. The Firefly site now supports switching between image and video generation, selecting AI models, changing aspect ratios, and shows files and recent history. Users can create custom models from their own images, illustrations, and sketches via a closed beta drag-and-drop workflow. Video generation/editing was redesigned to support layers and timeline-based editing.
#ai-image-generation #custom-artist-trained-models #layered-prompt-based-editing #audio-and-video-features
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]