archives/edge-gallery
archives/edge-gallery
2
0
Fork 0
mirror of https://github.com/google-ai-edge/gallery.git synced 2025-07-04 13:47:04 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
77 commits 8 branches 11 tags 1.6 MiB
Commit graph

39 commits

Author SHA1 Message Date
Wai Hon Law
d97e115993 [gallery] add firebase integration
Some checks are pending
Build Android APK / Build Android APK (push) Waiting to run
Details 
PiperOrigin-RevId: 778082730
 2025-07-01 09:52:14 -07:00
Google AI Edge Gallery
323124a628 Refactor code to migrate manual dependency injection to using Hilt 
PiperOrigin-RevId: 776356661
 2025-06-26 18:09:11 -07:00
Google AI Edge Gallery
665c86a640 Update the max number of audio clips to 1 
PiperOrigin-RevId: 775879562
 2025-06-25 16:22:18 -07:00
Google AI Edge Gallery
db0242fe88 [gallery] improve demo experience to keep the screen always on. 
PiperOrigin-RevId: 775825781
 2025-06-25 13:55:18 -07:00
Google AI Edge Gallery
2a95e5853b Add a simple local test for allowlisted model. 
PiperOrigin-RevId: 775265777
 2025-06-24 09:24:43 -07:00
Google AI Edge Gallery
d0989adce1 Add audio support. 
- Add a new task "audio scribe".
- Allow users to record audio clips or pick wav files to interact with model.
- Add support for importing models with audio capability.
- Fix a typo in Settings dialog (Thanks https://github.com/rhnvrm!)

PiperOrigin-RevId: 774832681
 2025-06-23 10:24:54 -07:00
Chunlei Niu
74a013c2e2 Remove OpenCL native lib from Android manifest, which is already provided in GenAI tasks dependency. 
PiperOrigin-RevId: 772508137
 2025-06-17 09:37:39 -07:00
Google AI Edge Gallery
0a49219915 Update the memory warning trigger condition. 
PiperOrigin-RevId: 772158962
 2025-06-16 13:52:45 -07:00
Google AI Edge Gallery
207cc50878 - Update genai task and app version. 
- Fix edge-to-edge on three-button nav bar (thanks https://github.com/Goooler!)
- Fix a layout issue where the added images are not properly positioned when text input grows in height.

PiperOrigin-RevId: 771175188
 2025-06-13 12:01:02 -07:00
Google AI Edge Gallery
f4006b35b0 No public description 
PiperOrigin-RevId: 770859221
 2025-06-13 09:26:16 -07:00
Jing Jin
ebb605131d - Try to limit the image size taken by the camera in ask image task 2025-05-22 16:51:22 -07:00
Jing Jin
61ee4fd5d7 - Fix some potential memory leak in image capture sheet. 2025-05-22 16:37:30 -07:00
Jing Jin
517f220d1b - Use camerax to implement image capture in-app instead of using the native camera app to reduce the possibility of app being killed due to GPU OOM. 
- Show accelerator name in chat message sender labels.
- Attach download workers with silent foreground notifications to make them less likely to be killed.
- Update app icon to be consistent with Google style.
- Bump up version to 1.0.2.
 2025-05-21 17:34:39 -07:00
Jing Jin
f9cab2f06d - Improve UX 
- Fix a bug related to LLM inference engine cleanup.
 2025-05-21 12:36:57 -07:00
Jing Jin
b8afe01e76 Bump version 2025-05-20 09:24:47 -07:00
Jing Jin
eff2c62276 Better image viewer 2025-05-19 22:59:10 -07:00
Jing Jin
0b67ccce1a Fix a download resume bug. 2025-05-19 20:23:05 -07:00
Jing Jin
6785ad881a Bump version 2025-05-19 17:02:53 -07:00
Jing Jin
96f838b550 Update package to com.google.ai.edge.gallery 2025-05-19 16:59:37 -07:00
Jing Jin
7d567c3499 - Fix a bug where deleting a local model when there are >1 local models shows the wrong download status. 
- Don't go back to model selection screen automatically when there is an error during model initialization, so that users have a chance to change model parameters (e.g. accelerator) to retry the initialization.
- Show error dialog properly in prompt lab screen.
 2025-05-19 14:46:06 -07:00
Jing Jin
e89fd9a23b - Better text formatting on home screen for smaller screen. 
- Set default backend based on the order of "accelerators" field in model allowlist
 2025-05-19 11:44:00 -07:00
Jing Jin
9544b8ddcc Re-enable image pickers when config is changed, and other UI bug fixes. 2025-05-19 11:08:03 -07:00
Jing Jin
0f5142e67e Bump version 2025-05-18 17:28:34 -07:00
Jing Jin
e7dda4b4ad Save the loaded model allowlist to a local file so that it can be read when the allowlist cannot be loaded from internet. 
Also improve the image clipping transitioning from full image back to the image thumbnail in chat ui.
 2025-05-18 17:26:31 -07:00
Jing Jin
37a58d1a41 Various bug fixes. 2025-05-17 15:12:12 -07:00
Jing Jin
bedc488a15 Add support for image to text models 2025-05-16 00:17:24 -07:00
Jing Jin
ef290cd7b0 Add initial support for model allowlist, and stop generating response. 2025-05-15 00:31:45 -07:00
Jing Jin
f9f1d71b38 Update tasks and models. 2025-04-28 16:49:03 -07:00
Jing Jin
d0beaab31e Better support for sliding to change model 2025-04-27 18:59:01 -07:00
Jing Jin
3341286efa Minor ux improvements 2025-04-27 11:23:17 -07:00
Jing Jin
705b16f062 Minor ux improvements 2025-04-27 11:18:10 -07:00
Jing Jin
d94fec0674 Add support for LLM single-turn experience 2025-04-26 21:35:03 -07:00
Jing Jin
46aaee2654 Bump version 2025-04-21 09:48:35 -07:00
Jing Jin
d197f8e0fb Show a snackbar when import succeeded. 
Also handle duplicated import better.
 2025-04-19 19:57:58 -07:00
Jing Jin
604972fe23 Make importing model functionality better. 
- Allow users to specify default parameters before importing.
 2025-04-18 23:10:55 -07:00
Jing Jin
29b614355e Add initial support for importing local model. 2025-04-17 17:54:57 -07:00
Jing Jin
b2f35a86e7 Update gitignore to exclude /release 2025-04-16 15:17:21 -07:00
Jing Jin
42d442389d - Add "show stats" after each LLM response to see token related stats more easily. 
- Back to multi-turn (no exception handling yet).
- Show app's version in App Info screen.
- Show API doc link and source code link in the model list screen.
- Jump to model info page in HF when clicking "learn more".
 2025-04-16 14:51:45 -07:00
Jing Jin
ea31fd0544 Initial checkin 2025-04-14 16:42:40 -07:00