Skip to main content

Filter by idea status

10000+ Ideas

Photoshop bug: Generative Fill unavailable with Quick Mask intensity-mask workflowOpen for Voting

Hello Adobe Photoshop Team,I would like to report a regression affecting the Quick Mask and Generative Fill workflow used to create watercolour, oil-painting and other generative art effects.Adobe previously demonstrated this workflow using Quick Mask to create an intensity-based selection, followed by Generative Fill through the Contextual Task Bar:https://www.youtube.com/watch?v=4THG0IPx9hchttps://www.adobe.com/learn/photoshop/web/create-art-styles-generative-fillWorkflow that previously workedOpen an image in Photoshop. Enter Quick Mask Mode. Fill the mask with a controlled percentage of grey to determine the strength of the generative transformation. Exit Quick Mask Mode to convert the mask into a selection. Use Generative Fill from the Contextual Task Bar. Enter a prompt such as “watercolour painting” or “oil painting.”This produced highly useful painterly interpretations while retaining the composition and visual structure of the original image.Current problemIn newer Photoshop updates, the Generative Fill option no longer functions for this art effects after creating the selection through Quick Mask Mode.The technique worked successfully in earlier versions but has been unavailable or inconsistent for approximately two years.This appears to be a regression rather than simply a change in interface, because the Quick Mask method allowed something that ordinary selection tools do not: precise control over the intensity of the generative effect through tonal mask values.Expected behaviourAfter exiting Quick Mask Mode, Photoshop should recognise the resulting selection and make Generative Fill available through:the Contextual Task Bar; the Edit menu; and any relevant Generative Fill panel.Selections created through Quick Mask should behave consistently with selections created using the Marquee, Lasso, Object Selection and other selection tools.Why this mattersThis was an unusually creative and valuable workflow for artists, illustrators, designers, photographers and educators. It allowed users to combine their own image-making decisions with generative tools rather than replacing the entire image with an uncontrolled AI interpretation.The adjustable grey value acted almost like a creative 'strength' control, allowing the user to decide how closely the generated result followed the source image.I use Photoshop professionally and teach creative software to art and design students. This technique was particularly useful for demonstrating:tonal masks and selection logic non-destructive experimentation the relationship between source imagery and generative interpretation watercolour, oil, drawing and print-inspired visual treatments, and responsible use of generative AI within an artist-led workflowRequested fixPlease restore full compatibility between Quick Mask selections, the Contextual Task Bar and Generative Fill in both Photoshop and Photoshop Beta.It would also be helpful for Adobe to test this specific workflow across different mask densities—for example 20%, 40%, 60% and 80% grey—to ensure that tonal intensity continues to influence the generated result as expected.Feature request: Generative PaintingPlease also consider developing this workflow into a supported feature, perhaps called Generative Painting or Generative Style Transfer.A dedicated feature could include:a strength or source-image preservation slider watercolour, oil, gouache, ink, pen and ink, pencil drawing, charcoal drawing, scribble drawing, pastel, and printmaking presets control over brush size, pigment texture and level of abstraction the ability to use a greyscale mask to vary the effect locally reference-image support preservation of important edges and composition generation onto a separate, editable layer, and the option to combine painted and photographic areas within one imageThis would turn an inventive workaround into a properly supported artist-facing tool. Photoshop is most powerful when AI extends the artist’s hand rather than removing it from the picture.Thank you for investigating this regression and considering the feature request.Kind regards,Kavitha ParamasivanGraphic Designer, Artist and Creative Software Educator

AndrewTheGreat
AndrewTheGreatKnown Participant

The Ultimate Premiere Pro Feature Request 2025Not Prioritized

Premiere Pro 2025 significantly lags behind other software, not even mentioning AI capabilities. To balance the scales, I believe Adobe should seriously consider adding truly useful and modern tools to Premiere Pro in the nearest future. The picturesque features shown at MAX 2025 looked impressive, but they were nothing more than prototypes and proof-of-concept demos. And the following tools and improvements are needed now. Some can even be added in the nearest weeks or months.  1. Fast and easy-to-use AI masking. I tested the beta version and it was genuinely good, but the way it is applied leaves much to be desired. There should be no need to create an empty tracking mask data and then apply it to effects. That workflow is outdated. Any effect — native or third-party — should have a dedicated mask tracking button.2. Proper native tracking. Premiere Pro is extremely weak in terms of tracking. Every modern video editing software has a fast, native tracking engine. Tracking in Premiere Pro feels primitive. A good native (not BorisFX-based, wink) AI-powered camera, planar, mesh, and point tracker should be added to Premiere Pro too. It should support simple “track to object” functionality — fast, one-click, with advanced options if needed. Tracking should also support "previous-frame" analysis to track objects that leave the frame.3. Native restoration tools. Premiere Pro should have long included a set of image restoration tools: denoise, deband, deflicker, deshake, and tools for removing fixed and dynamic dirt, scratches, and dust. It also needs a fast object removal tool with tracking and dynamic background reconstruction. The Content-Aware Fill in After Effects is frankly terrible, and users should not have to rely entirely on third-party plugins.4. AI-based facial and body refinement. With fast mask tracking now available, Premiere Pro should also include native tools for face and body isolation and refinement as a separate feature. There's a lot of software that can do a digital make up and adjust characters' body.5. A depth map generator. It is frankly embarrassing that even After Effects lacks a native depth map generator. Premiere Pro needs this even more, as it is the actual NLE which would definitely benefit from using such a tool.6. New, modern GPU-accelerated effects and transitions. “New” should mean original — not effects acquired from companies that have been selling the same plugin packs for over a decade.7. Simultaneous stabilization and time remapping without nesting.8. Full unnesting and Render and Replace improvements. Premiere Pro should be able to unnest and render and replace any media, including nests and multicam clips, with the ability to revert at any time. Render-and-replace should bake in effects, transitions, and alpha channels by default, to lift the need to do this manually every time from the user's shoulders.9. A complete redesign of time remapping. The current implementation is awful. If Adobe doesn’t know how to improve it — just copy the After Effects approach.10. Linked audio clips should behave like video clips when time remapping is applied. They should also be time remapped correspondingly!11. Better timeline organization tools.  Shifting clips on different tracks with a delay and clip swapping via hotkeys should be added, both horizontally and vertically.12. Converting nested sequences to multicams and vice versa.13. Togglable audio/video switching modes for already-created multicams, allowing users to change how camera angles and\or audio tracks are switched AFTER the multicam has been created.14. A proper audio noise cancellation tool. Speech Enhance is unusable and somehow worse than Adobe's own Podcast 2.0.15. Improved markers. Markers should be movable directly on clips without opening them in the Source Monitor. The marker list should be customizable: resizable rows, optional previews, full marker name visibility, and a proper custom color picker (the default eight colors are insufficient).16. Frame interpolation from After Effects (Pixel Motion). It produces much better results than Premiere Pro Optical Flow.17. Detail-preserving upscaling from After Effects or another high-quality upscaler, AI-based or not.18. Animation for all available (ALL!) text parameters in both Effect Controls and Properties panels.19. Real-time multicam cutting mode so cuts appear during playback, not after playback stops.20. Intelligent multicam auto-cutting based on camera angles, facial recognition, and motion/activity analysis. The current level of technology premits that.21. Advanced AI stabilization with edge reconstruction when cropping.22. Native edge mirroring and duplicating for the Transform effect.23. Ability to place effects before the Motion group (or make Transform the default replacement for Motion) in the Effects controls panel so that motion does not conflict with some effects.24. Vertical track reposition (move track up\down)25. Basic subtitle animation tools (letters, words, lines) and drag-and-drop motion presets affecting entire subtitle tracks.26. Transitions applied to the cut nearest to playhead via double-click. Somehow effects can be applied with a double-click and transitions can't.27. Face recognition based via smart search, with grouping and naming capabilities to quickly group similar results and find them in the footage faster.28. Program Monitor group clip viewing mode to review and cut all imported or selected clips without the need to create a second sequence and stack the sequences one above another.29. Decoding entirely on the GPU and iGPU, leaving CPU resources for computation. Add more codec flavours based on the CPU and GPU codec support.30. Make masks move, add points and resize the same way it's implemented in After Effects.31. Effect controls directly in the Program Monitor, like the current Transform and Crop, with APIs for third-party developers to build visually controllable tools.32. Audio leveler and de-bleed tools (based on denoise, gate or ducking), supporting multi-track interaction - to be able to target several tracks between each other.33. Complete Morph Cut redesign. AI-based, object-aware, mask-driven morphing without the current tedious scene analysis.34. Stabilization bake/freeze option so it does not reset on every change.35. AE-style effect curves in the Effect Controls panel.36. Send/bus-routing in the Audio Mixer, similar to Audition.37. UI space optimization with better button placement (especially in the Program Monitor and Timeline) and a toggleable maximize mode that hides top and bottom Premiere Pro bars.38. Real-time previews for effects and transitions upon hover or click, with thumbnails in the Effects panel, and support for third-party preview implementations.39. Drag-and-drop organization of templates and folders in the Graphics Templates panel.40. Toggleable continuous timeline playback mode where moving the playhead does not stop playback.41. Playback autoscroling improvements, allowing playback to start from any fixed playhead position and not in the center only.42. Disable or toggle automatic jumps to the start of extended markers when clicking them.43. Clear, informative and precise Error logs and Warning reports before render. Premiere Pro should show exact timecodes and clip names for unlinked graphics (the "missing" messanges), clips, or effects with warnings (Morph Cut, Warp Stabilizer), and avoid showing warnings for items NOT present on the timeline. The same accounts for render errors - a user must know the exact reason why an error happen and not just "renderer error at 01:10:21:08, Selector: 03, Error code: 9".44. Make audio waveforms for multicams VISIBLE! Always. Not when Premiere Pro wants it.45. Add a dedicated "Output LUT" slot at the very end of the Lumetri Color processing chain (after Vignette).46. Add a Watchfolder function for an automatic real-time syncing of the contents in an imported folder.47. Add an ability to save audio mixer plugin chain as presets.48. Add a better support for PSD and vector files from Photoshop and Illustrator to be able to edit text from there. Plus vectors actually be vectors, not rasters, in Premiere Pro.49. Unify all the possible hotkeys, behaviours and tools to act the same way in AE and Pr.50. Motion blur as a SYSTEM SETTING, not just an option in transform.51. Fx console for searching effects, transitions, generators and functiuons. 52. A reworked Project Manager which actually works, always, with no errors, with an intuitive operation. With a richer functionality similar to Plume Pack.53. An ability to save downgraded projects like in AE. Without the need to unzip and change XMLs or use third-party project downgrading sites.--------------------------------------------With great respect and hope for software improvement,AndyTheGreat 

Webwilliam
WebwilliamParticipant

Sugestão de Recursos Avançados de Processamento de ImagemReleased

Prezados Desenvolvedores,Gostaria de compartilhar uma ideia que considero de grande relevância para o aprimoramento da vossa plataforma. Recentemente, tive a oportunidade de observar as capacidades oferecidas pela tecnologia de processamento de imagem (Adobe Firefly), e acredito que podem elevar significativamente a experiência dos usuários ao implementar opções avançadas de edição de imagem impulsionadas pela IA.Haveria a possibilidade de fazer upload de imagens e, com base nessas imagens, utilizar a inteligência artificial para realizar a criação de cartoons, caricaturas, correção de fotos embaçadas, remover ruídos, figuras semelhantes e até mesmo realizar uma clonagem de fotos, tudo isso com uma qualidade excepcionalmente alta e uma IA mais eficiente em relação à fidelização da imagem.Tendo em mente a excelência associada ao nome da ADOBE, imagino um recurso que se destaque pelo seu nível superior de qualidade. Um exemplo que me inspira é o trabalho feito pela Adobe, reconhecido por sua expertise em edição de imagem. No entanto, acredito que podem ir além, oferecendo um processo mais preciso e uma maior fidelidade à imagem original.Entendo que a implementação de um recurso tão avançado pode demandar recursos substanciais em termos de desenvolvimento e pesquisa. Contudo, creio que os benefícios para os usuários e a posição de destaque que poderíam alcançar no mercado justificam plenamente esse investimento.Agradeço desde já por considerarem esta sugestão. Estou à disposição para discutir mais detalhes e trocar ideias sobre como poderíam transformar essa visão em realidade. Aguardo ansiosamente suas considerações sobre a possibilidade de incorporar esses recursos inovadores ao Adobe Firefly.Atenciosamente,William

Contextual Task Bar - Generative painting for watercolour and oil painting effects with quick maskOpen for Voting

Hello Adobe Photoshop Team,I would like to report a regression affecting the Quick Mask and Generative Fill workflow used to create watercolour, oil-painting and other generative art effects.Adobe previously demonstrated this workflow using Quick Mask to create an intensity-based selection, followed by Generative Fill through the Contextual Task Bar:https://www.youtube.com/watch?v=4THG0IPx9hchttps://www.adobe.com/learn/photoshop/web/create-art-styles-generative-fillWorkflow that previously workedOpen an image in Photoshop. Enter Quick Mask Mode. Fill the mask with a controlled percentage of grey to determine the strength of the generative transformation. Exit Quick Mask Mode to convert the mask into a selection. Use Generative Fill from the Contextual Task Bar. Enter a prompt such as “watercolour painting” or “oil painting.”This produced highly useful painterly interpretations while retaining the composition and visual structure of the original image.Current problemIn newer Photoshop updates, the Generative Fill option no longer functions for this art effects after creating the selection through Quick Mask Mode.The technique worked successfully in earlier versions but has been unavailable or inconsistent for approximately two years.This appears to be a regression rather than simply a change in interface, because the Quick Mask method allowed something that ordinary selection tools do not: precise control over the intensity of the generative effect through tonal mask values.Expected behaviourAfter exiting Quick Mask Mode, Photoshop should recognise the resulting selection and make Generative Fill available through:the Contextual Task Bar; the Edit menu; and any relevant Generative Fill panel.Selections created through Quick Mask should behave consistently with selections created using the Marquee, Lasso, Object Selection and other selection tools.Why this mattersThis was an unusually creative and valuable workflow for artists, illustrators, designers, photographers and educators. It allowed users to combine their own image-making decisions with generative tools rather than replacing the entire image with an uncontrolled AI interpretation.The adjustable grey value acted almost like a creative 'strength' control, allowing the user to decide how closely the generated result followed the source image.I use Photoshop professionally and teach creative software to art and design students. This technique was particularly useful for demonstrating:tonal masks and selection logic non-destructive experimentation the relationship between source imagery and generative interpretation watercolour, oil, drawing and print-inspired visual treatments, and responsible use of generative AI within an artist-led workflowRequested fixPlease restore full compatibility between Quick Mask selections, the Contextual Task Bar and Generative Fill in both Photoshop and Photoshop Beta.It would also be helpful for Adobe to test this specific workflow across different mask densities—for example 20%, 40%, 60% and 80% grey—to ensure that tonal intensity continues to influence the generated result as expected.Feature request: Generative PaintingPlease also consider developing this workflow into a supported feature, perhaps called Generative Painting or Generative Style Transfer.A dedicated feature could include:a strength or source-image preservation slider watercolour, oil, gouache, ink, pen and ink, pencil drawing, charcoal drawing, scribble drawing, pastel, and printmaking presets control over brush size, pigment texture and level of abstraction the ability to use a greyscale mask to vary the effect locally reference-image support preservation of important edges and composition generation onto a separate, editable layer, and the option to combine painted and photographic areas within one imageThis would turn an inventive workaround into a properly supported artist-facing tool. Photoshop is most powerful when AI extends the artist’s hand rather than removing it from the picture.Thank you for investigating this regression and considering the feature request.Kind regards,Kavitha ParamasivanGraphic Designer, Artist, and Creative Software Educator