Ryan Dick
5e2351f3bf
Fix FLUX output image clamping. And a few other minor fixes to make inference work with the full bfloat16 FLUX transformer model.
2024-08-21 09:10:22 -04:00
Brandon Rising
d705c3cf0e
Select dev/schnell based on state dict, use correct max seq len based on dev/schnell, and shift in inference, separate vae flux params into separate config
2024-08-21 09:10:20 -04:00
Brandon Rising
115f350f6f
Install sub directories with folders correctly, ensure consistent dtype of tensors in flux pipeline and vae
2024-08-21 09:09:39 -04:00
Brandon Rising
be6cb2c07c
Working inference node with quantized bnb nf4 checkpoint
2024-08-21 09:09:39 -04:00
Brandon Rising
4fb5529493
Remove unused param on _run_vae_decoding in flux text to image
2024-08-21 09:09:39 -04:00
Brandon Rising
b43ee0b837
Add nf4 bnb quantized format
2024-08-21 09:09:39 -04:00
Brandon Rising
3312fe8fc4
Run ruff, setup initial text to image node
2024-08-21 09:09:39 -04:00
Brandon Rising
01a2449dae
Add backend functions and classes for Flux implementation, Update the way flux encoders/tokenizers are loaded for prompt encoding, Update way flux vae is loaded
2024-08-21 09:09:37 -04:00
Brandon Rising
cfe9d0ce0a
Some UI cleanup, regenerate schema
2024-08-21 09:08:22 -04:00
Brandon Rising
46b6314482
Run Ruff
2024-08-21 09:06:38 -04:00
Brandon Rising
46d5107ff1
Run Ruff
2024-08-21 09:06:38 -04:00
Brandon Rising
6ea1278d22
Manage quantization of models within the loader
2024-08-21 09:06:34 -04:00
Brandon Rising
4556b57382
Remove changes to v1 workflow
2024-08-21 09:04:40 -04:00
Brandon Rising
f425d3aa3c
Setup flux model loading in the UI
2024-08-21 09:04:37 -04:00
Ryan Dick
d7a39a4d67
WIP on moving from diffusers to FLUX
2024-08-21 08:59:19 -04:00
Ryan Dick
3e8a550fab
More improvements for LLM.int8() - not fully tested.
2024-08-21 08:59:19 -04:00
Ryan Dick
0e96794c6e
LLM.int8() quantization is working, but still some rough edges to solve.
2024-08-21 08:59:19 -04:00
Ryan Dick
23a7328a66
Clean up NF4 implementation.
2024-08-21 08:59:19 -04:00
Ryan Dick
c3cf8c3b6b
NF4 inference working
2024-08-21 08:59:19 -04:00
Ryan Dick
110d58d107
NF4 loading working... I think.
2024-08-21 08:59:19 -04:00
Ryan Dick
3480e06688
wip
2024-08-21 08:59:19 -04:00
Ryan Dick
3ba60e1656
Split a FluxTextEncoderInvocation out from the FluxTextToImageInvocation. This has the advantage that we benfit from automatic caching when the prompt isn't changed.
2024-08-21 08:59:19 -04:00
Ryan Dick
cdd47b657b
Make quantized loading fast for both T5XXL and FLUX transformer.
2024-08-21 08:59:19 -04:00
Ryan Dick
68c712d254
Make quantized loading fast.
2024-08-21 08:59:19 -04:00
Ryan Dick
44d7a74b88
WIP - experimentation
2024-08-21 08:59:19 -04:00
Ryan Dick
e8fb8f4d12
Make float16 inference work with FLUX on 24GB GPU.
2024-08-21 08:59:19 -04:00
Ryan Dick
9381211508
Add support for 8-bit quantizatino of the FLUX T5XXL text encoder.
2024-08-21 08:59:19 -04:00
Ryan Dick
8cce4a40d4
Make 8-bit quantization save/reload work for the FLUX transformer. Reload is still very slow with the current optimum.quanto implementation.
2024-08-21 08:59:19 -04:00
Ryan Dick
4833746698
Minor improvements to FLUX workflow.
2024-08-21 08:59:19 -04:00
Ryan Dick
8b9bf55bba
Got FLUX schnell working with 8-bit quantization. Still lots of rough edges to clean up.
2024-08-21 08:59:19 -04:00
Ryan Dick
7b199fed4f
Use the FluxPipeline.encode_prompt() api rather than trying to run the two text encoders separately.
2024-08-21 08:59:18 -04:00
Ryan Dick
13513465c8
First draft of FluxTextToImageInvocation.
2024-08-21 08:59:18 -04:00
Ryan Dick
d5a949e6c3
Update HF download logic to work for black-forest-labs/FLUX.1-schnell.
2024-08-21 08:59:18 -04:00
Ryan Dick
eb38295263
Update imports for compatibility with bumped diffusers version.
2024-08-21 08:59:18 -04:00
psychedelicious
4f4ba7b462
tidy(ui): clean up ActiveStylePreset markup
2024-08-21 09:06:41 +10:00
Mary Hipp
2298be0e6b
fix(ui): error handling if unable to convert image URL to blob
2024-08-21 09:06:41 +10:00
Mary Hipp
63494dfca7
remove extra slash in exports path
2024-08-21 09:06:41 +10:00
Mary Hipp
36a1d39454
fix(ui): handle badge styling when template name is long
2024-08-21 09:06:41 +10:00
Mary Hipp
a6f6d5c400
fix(ui): add loading state to button when creating or updating a style preset
2024-08-21 09:06:41 +10:00
Mary Hipp
e85f221aca
fix(ui): clear prompt template when prompts are recalled
2024-08-21 09:04:35 +10:00
Mary Hipp
d4797e37dc
fix(ui): properly unwrap delete style preset API request so that error is caught
2024-08-19 16:12:39 -04:00
Mary Hipp
3e7923d072
fix(api): allow updating of type for style preset
2024-08-19 16:12:39 -04:00
psychedelicious
a85d69ce3d
tidy(ui): getViewModeChunks.tsx -> .ts
2024-08-19 08:25:39 +10:00
psychedelicious
96db006c99
fix(ui): edge case with getViewModeChunks
2024-08-19 08:25:39 +10:00
psychedelicious
8ca57d03d8
tests(ui): add tests for getViewModeChunks
2024-08-19 08:25:39 +10:00
psychedelicious
6c404ce5f8
fix(ui): prompt template preset preview out of order
2024-08-19 08:25:39 +10:00
psychedelicious
584e07182b
fix(ui): use translations for style preset strings
2024-08-17 21:27:53 +10:00
psychedelicious
f787e9acf6
chore: bump version v4.2.8rc2
2024-08-16 21:47:06 +10:00
psychedelicious
5a24b89e54
fix(app): include style preset defaults in build
2024-08-16 21:47:06 +10:00
psychedelicious
9b482e2a4f
chore: bump version to v4.2.8rc1
2024-08-16 10:53:19 +10:00
psychedelicious
182571df4b
Merge branch 'main' into maryhipp/export-presets
2024-08-16 10:17:07 +10:00
psychedelicious
3fb4e3050c
feat(ui): focus in textarea after inserting placeholder
2024-08-16 10:14:25 +10:00
psychedelicious
39c7ec3cd9
feat(ui): per type fallbacks for templates
2024-08-16 10:11:43 +10:00
psychedelicious
26bfbdec7f
feat(ui): use buttons instead of menu for preset import/export
2024-08-16 09:58:19 +10:00
psychedelicious
7a3eaa8da9
feat(api): save file as prompt_templates.csv
2024-08-16 09:51:46 +10:00
Mary Hipp
599db7296f
export only user style presets
2024-08-15 16:07:32 -04:00
Riccardo Giovanetti
042aab4295
translationBot(ui): update translation (Italian)
...
Currently translated at 98.6% (1340 of 1359 strings)
Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI
2024-08-15 20:44:02 +02:00
Mary Hipp
24f298283f
clean up, add context menu to import/download templates
2024-08-15 12:39:55 -04:00
Mary Hipp
68dac6349d
Merge remote-tracking branch 'origin/main' into maryhipp/export-presets
2024-08-15 11:21:56 -04:00
chainchompa
659019cfd6
Merge branch 'main' into chainchompa/preselect-workflows
2024-08-15 10:40:44 -04:00
Mary Hipp
810be3e1d4
update import directions to include JSON
2024-08-15 09:47:49 -04:00
psychedelicious
60d754d1df
feat(api): tidy style presets import logic
...
- Extract parsing into utility function
- Log import errors
- Forbid extra properties on the imported data
2024-08-15 09:47:49 -04:00
psychedelicious
bd07c86db9
feat(ui): make style preset menu trigger look like button
2024-08-15 09:47:49 -04:00
psychedelicious
bcbf8b6bd8
feat(ui): revert to using {prompt} for prompt template placeholder
2024-08-15 09:47:49 -04:00
psychedelicious
356661459b
feat(api): support JSON for preset imports
...
This allows us to support Fooocus format presets.
2024-08-15 09:47:49 -04:00
psychedelicious
deb917825e
feat(api): use pydantic validation during style preset import
...
- Enforce name is present and not an empty string
- Provide empty string as default for positive and negative prompt
- Add `positive_prompt` as validation alias for `prompt` field
- Strip whitespace automatically
- Create `TypeAdapter` to validate the whole list in one go
2024-08-15 09:47:49 -04:00
psychedelicious
15415c6d85
feat(ui): use dropzone for style preset upload
...
Easier to accept multiple file types and supper drag and drop in the future.
2024-08-15 09:47:49 -04:00
Mary Hipp
76b0380b5f
feat(ui): create component to upload CSV of style presets to import
2024-08-15 09:47:49 -04:00
Mary Hipp
2d58754789
feat(api): add endpoint to take a CSV, parse it, validate it, and create many style preset entries
2024-08-15 09:47:49 -04:00
chainchompa
9cdf1f599c
Merge branch 'main' into chainchompa/preselect-workflows
2024-08-15 09:25:19 -04:00
chainchompa
268be97ba0
remove ref, make options optional for useGetLoadWorkflow
2024-08-15 09:18:41 -04:00
Mary Hipp
a9014673a0
wip export
2024-08-15 09:00:11 -04:00
Phrixus2023
54a5c4e482
translationBot(ui): update translation (Chinese (Simplified))
...
Currently translated at 98.1% (1296 of 1320 strings)
Co-authored-by: Phrixus2023 <920414016@qq.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/zh_Hans/
Translation: InvokeAI/Web UI
2024-08-15 00:46:01 +02:00
Riccardo Giovanetti
5e09a244e3
translationBot(ui): update translation (Italian)
...
Currently translated at 98.5% (1336 of 1355 strings)
translationBot(ui): update translation (Italian)
Currently translated at 98.5% (1302 of 1321 strings)
translationBot(ui): update translation (Italian)
Currently translated at 98.6% (1302 of 1320 strings)
Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI
2024-08-15 00:46:01 +02:00
chainchompa
88648dca1a
change selectedWorkflow to selectedWorkflowId
2024-08-14 11:22:37 -04:00
chainchompa
8840df2b00
Merge branch 'main' into chainchompa/preselect-workflows
2024-08-14 09:02:12 -04:00
chainchompa
af159acbdf
cleanup
2024-08-14 08:58:38 -04:00
chainchompa
471719bbbe
add base prop for selectedWorkflow to allow loading a workflow on launch
2024-08-14 08:47:02 -04:00
psychedelicious
9938f12ef0
Merge branch 'main' into maryhipp/style-presets
2024-08-14 12:33:30 +10:00
psychedelicious
982c266073
tidy: remove extra characters in prompt templates
2024-08-14 12:31:57 +10:00
psychedelicious
5c37391883
fix(ui): do not show [prompt] in preset preview
2024-08-14 12:29:05 +10:00
psychedelicious
ddeafc6833
fix(ui): minimize layout shift when overlaying preset prompt preview
2024-08-14 12:24:57 +10:00
psychedelicious
41b2d5d013
fix(ui): prompt preview not working preset starts with [prompt]
2024-08-14 12:21:38 +10:00
psychedelicious
29d6f48901
fix(ui): prompt shows thru prompt label text
2024-08-14 12:01:49 +10:00
psychedelicious
d5c9f4e47f
chore(ui): revert framer-motion upgrade
...
`framer-motion` 11 breaks a lot of stuff in profoundly unintuitive ways, holy crap. UI lib rolled back its dep, pulling in latest version of that
2024-08-14 06:12:00 +10:00
psychedelicious
24d73387d8
build(ui): fix chakra deps
...
We had multiple versions of @emotion/react, stemming from an extraneous dependency on @chakra-ui/react. Removed the extraneosu dep
2024-08-14 06:12:00 +10:00
Mary Hipp
e0d3927265
feat: add flag for allowPrivateStylePresets that shows a type field when creating a style preset
2024-08-13 14:08:54 -04:00
Mary Hipp
e5f7c2a9b7
add type safety / validation to form data payloads and allow type to be passed through api
2024-08-13 13:00:31 -04:00
Mary Hipp
b0760710d5
add the rest of default style presets, update image service to return default images correctly by name, add tooltip popover to images in UI
2024-08-13 11:33:15 -04:00
Mary Hipp
764accc921
update config docstring
2024-08-12 15:17:40 -04:00
Mary Hipp
6a01fce9c1
fix payloads for stringified data
2024-08-12 15:16:22 -04:00
Mary Hipp
9c732ac3b1
Merge remote-tracking branch 'origin/main' into maryhipp/style-presets
2024-08-12 14:53:45 -04:00
Mary Hipp
b70891c661
update descriptoin of placeholder in modal
2024-08-12 13:37:04 -04:00
Mary Hipp
4dbf851741
ui: add labels to prompt boxes
2024-08-12 13:33:39 -04:00
Mary Hipp
6c927a9fd4
move mdoal state into nanostore
2024-08-12 12:46:02 -04:00
Mary Hipp
096f001634
ui: add ability to copy template
2024-08-12 12:32:31 -04:00
Mary Hipp
4837e578b2
api: update dir path for style preset images, update payload for create/update formdata
2024-08-12 12:00:14 -04:00
Mary Hipp
1e547ef912
UI more pr feedback
2024-08-12 11:59:25 -04:00
psychedelicious
f6b8970bd1
fix(app): create reference to events task to prevent accidental GC
...
This wasn't a problem, but it's advised in the official docs so I've done it.
2024-08-12 07:49:58 +10:00
psychedelicious
29325a7214
fix(app): use asyncio queue and existing event loop for events
...
Around the time we (I) implemented pydantic events, I noticed a short pause between progress images every 4 or 5 steps when generating with SDXL. It didn't happen with SD1.5, but I did notice that with SD1.5, we'd get 4 or 5 progress events simultaneously. I'd expect one event every ~25ms, matching my it/s with SD1.5. Mysterious!
Digging in, I found an issue is related to our use of a synchronous queue for events. When the event queue is empty, we must call `asyncio.sleep` before checking again. We were sleeping for 100ms.
Said another way, every time we clear the event queue, we have to wait 100ms before another event can be dispatched, even if it is put on the queue immediately after we start waiting. In practice, this means our events get buffered into batches, dispatched once every 100ms.
This explains why I was getting batches of 4 or 5 SD1.5 progress events at once, but not the intermittent SDXL delay.
But this 100ms wait has another effect when the events are put on the queue in intervals that don't perfectly line up with the 100ms wait. This is most noticeable when the time between events is >100ms, and can add up to 100ms delay before the event is dispatched.
For example, say the queue is empty and we start a 100ms wait. Then, immediately after - like 0.01ms later - we push an event on to the queue. We still need to wait another 99.9ms before that event will be dispatched. That's the SDXL delay.
The easy fix is to reduce the sleep to something like 0.01 seconds, but this feels kinda dirty. Can't we just wait on the queue and dispatch every event immediately? Not with the normal synchronous queue - but we can with `asyncio.Queue`.
I switched the events queue to use `asyncio.Queue` (as seen in this commit), which lets us asynchronous wait on the queue in a loop.
Unfortunately, I ran into another issue - events now felt like their timing was inconsistent, but in a different way than with the 100ms sleep. The time between pushing events on the queue and dispatching them was not consistently ~0ms as I'd expect - it was highly variable from ~0ms up to ~100ms.
This is resolved by passing the asyncio loop directly into the events service and using its methods to create the task and interact with the queue. I don't fully understand why this resolved the issue, because either way we are interacting with the same event loop (as shown by `asyncio.get_running_loop()`). I suppose there's some scheduling magic happening.
2024-08-12 07:49:58 +10:00
