eaa8dbcd42
fix: correct comments and cleanup model descriptions
...
- Fix Klein text encoder comment to specify correct sizes per variant
- Lock TAESD decode logging behind SD_PREVIEW_DEBUG env var
- Fix misleading comment about FLUX.2 128-channel reshape (is fallback)
- Remove VRAM requirements from model descriptions in reference files
2026-01-16 03:24:39 +00:00
5e2bc01367
fix(taesd): remove unused variable warning
2026-01-16 03:06:48 +00:00
749371364b
lint
2026-01-16 03:03:47 +00:00
c605a1bb62
feat(taesd): add FLUX.2 preview support
...
Enable live preview during FLUX.2 and FLUX.2 Klein image generation
using the TAE FLUX.2 decoder from madebyollin/taesd.
- Add dedicated TAE entries (FLUX.1, FLUX.2, SD3) that auto-select
based on model type, making the dropdown only affect SD/SDXL models
- Add FLUX.2 latent unpacking in callback to convert packed
[B, seq_len, 128] format to spatial [B, 32, H, W] for preview
- Support FLUX.2's 32 latent channels (vs 16 for FLUX.1/SD3)
2026-01-16 03:01:52 +00:00
fe99d3fe5d
feat: add FLUX.2 Klein model support
...
Add support for FLUX.2 Klein distilled models (4B and 9B variants):
- Add pipeline loader for Flux2KleinPipeline
- Add model detection for 'flux.2' + 'klein' patterns
- Add pipeline mapping in shared_items
- Add shared Qwen3ForCausalLM text encoder handling:
- 4B variants use Z-Image-Turbo's Qwen3-8B
- 9B variants use FLUX.2-klein-9B's Qwen3-14B
- Add reference entries for distilled (4B, 9B) and base models
- Update diffusers commit for Flux2KleinPipeline support
2026-01-16 01:35:20 +00:00
6f86cc633f
Merge branch 'dev' of https://github.com/vladmandic/sdnext into dev
2026-01-15 21:20:37 +01:00
c0dc5f510f
update changelog
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-15 21:20:34 +01:00
60721979c2
Merge pull request #4550 from alerikaisattera/taesd-expand
...
Expand TAESD previews to a few more models
2026-01-15 21:19:13 +01:00
12098eea15
Fix
2026-01-15 16:49:18 +06:00
4edcb6bec1
Add Kandinsky Image 5 and CogView
2026-01-15 16:48:27 +06:00
f3948b6244
Merge branch 'dev' into taesd-expand
2026-01-15 16:42:40 +06:00
1a3e9ff399
log env
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-01-15 09:49:22 +00:00
30da7803b5
futureproof
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-01-15 09:29:26 +00:00
3800bbf2ef
update changelog and todo
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-15 08:43:11 +01:00
f7328fb907
add chroma-inpaint
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-15 08:37:44 +01:00
71d3482168
cleanup model types
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-15 08:30:48 +01:00
387b3c7c36
split reference.json
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-15 08:23:07 +01:00
d35658536b
Merge pull request #4548 from CalamitousFelicitousness/feat/glm-image-support
...
add GLM-Image pipeline support
2026-01-15 08:01:32 +01:00
b262d1445a
Expand TAESD previews to a few more models
2026-01-14 22:00:29 +06:00
c2bc47e0c1
SDNQ expose Dyn quant on settings
2026-01-14 16:54:50 +03:00
034b0844fe
register sdnq classes
2026-01-14 16:25:56 +03:00
784cda80aa
update sdnq
2026-01-14 16:23:26 +03:00
7fb58f22c2
fix(glm): rename _wrap_vision_language_generate to hijack_vision_language_generate
2026-01-14 11:34:25 +00:00
4dbdee10e3
switch lora logic and improve ui networks filter
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-14 10:31:21 +01:00
e5176ef1f3
update requirements
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-14 09:03:44 +01:00
ff06011349
Merge pull request #4547 from awsr/typing
...
Typing and related
2026-01-14 08:38:21 +01:00
de3b2b62eb
Update reference.json
2026-01-14 05:20:53 +00:00
c1ca2ff2f5
add GLM-Image reference model preview image
2026-01-14 04:58:20 +00:00
1be9ceeea1
add GLM-Image to reference models
2026-01-14 03:45:53 +00:00
3f259cff9a
add GLM-Image pipeline support
...
- Add GLM-Image (zai-org/GLM-Image) model detection and loading
- Custom pipeline loader with proper component handling:
- ByT5 text encoder (cannot use shared T5 due to different hidden size)
- Vision-language encoder (9B AR model)
- DiT transformer (7B)
- Fix EOS token early stopping in AR generation
- Add AR token generation progress tracking with terminal progress bar
- Fix uninitialized audio variable in processing
- Add TAESD support for GLM-Image (using f1 variant)
2026-01-14 03:33:49 +00:00
494dd1c4b1
Remove unnecessary typing
2026-01-13 16:54:17 -08:00
6335130ca5
Rewrite to satisfy type checker
2026-01-13 16:44:54 -08:00
b2798b15db
Improved Options init
2026-01-13 16:08:58 -08:00
071ba20cc3
Trim leading and trailing space from doc
2026-01-13 15:41:30 -08:00
56d90b629c
Reorder imports
2026-01-13 15:33:29 -08:00
de52f6bfda
Update ui_models.py
2026-01-13 15:33:18 -08:00
1dffdc17a9
Revert classvar removal. Simplify and update
2026-01-13 14:30:34 -08:00
8500156888
improve queue management
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-01-13 12:58:14 +00:00
cf41ba15d9
More robust type enforcement
2026-01-13 04:10:35 -08:00
3654d0fa18
Update typing, remove incorrect typing
2026-01-13 04:09:58 -08:00
6cec9828e8
Fix OptionInfo typing
...
Warning: This effectively disables type checking for `shared.opts`
2026-01-13 04:08:48 -08:00
08c871e8d1
Remove unused class vars
2026-01-13 04:08:48 -08:00
a30229c6f0
Type update and minor consolidation
2026-01-13 02:23:19 -08:00
ec86e52ded
Correct type enforcement
2026-01-13 02:11:58 -08:00
2394a7fac1
Ignore false positives with static typing
2026-01-13 02:10:38 -08:00
1a083a54f4
Use generic type
2026-01-13 02:08:11 -08:00
e7809b11cd
reapply offload hooks on diffusers lora load
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-01-13 10:07:30 +00:00
f21a943028
gallery save/delete checks
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-13 09:57:22 +01:00
3c9e349176
Explicit conversion to list
2026-01-12 14:39:36 -08:00
8932f11837
Use cast to resolve type error
...
No impact during runtime
2026-01-12 14:38:30 -08:00
CalamitousFelicitousness
vladmandic
Aleri Kaisattera
Disty0
awsr