c86ba31214
add nucleus-image
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-04-15 11:49:10 +00:00
db8c6e9243
add ernie-image
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-04-15 11:06:32 +00:00
f033eaf58a
add explicit vae method=none and allow images in history
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-14 11:51:27 +02:00
8070e51777
openvino backend
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-12 19:07:20 +02:00
a00ea46114
add step1x-edit and vibe-edit
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-12 19:06:08 +02:00
da01e6ced2
add lumina-dimoo
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-12 19:06:08 +02:00
4ef2c7ab3b
fix check-models
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-12 19:06:08 +02:00
b9a38b5955
ai-agents
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-12 18:54:22 +02:00
a07e9cc7e1
hijack hf download
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-06 09:19:43 +02:00
9d0ecde462
add sdxs
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-04-02 20:15:30 +02:00
999cbe5d3a
Merge branch 'dev' into various1
2026-04-02 08:36:24 +02:00
849ab8fe1e
fix loader
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-03-30 09:58:42 +02:00
7f07d4cb31
Update to match actual code logic
2026-03-28 17:31:37 -07:00
375591ecdd
Revert non-critical changes
...
The following errors are re-introduced and will need follow-up:
- models.py, line 92
- sd_unet.py, line 41
- sd_models.py, line 1440
2026-03-25 13:47:27 -07:00
ff247d8fd2
Merge branch 'dev' into RUF013
2026-03-24 07:12:51 -07:00
f0bb0a921a
RUF013 updates and value handling fix
2026-03-24 05:13:11 -07:00
dbd2293586
remove hf token from load args
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-03-23 17:53:47 +01:00
12fd4d30f1
fb merge phase 2
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-03-16 08:09:07 +01:00
9eced4ff86
cleanup
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-03-13 15:05:47 +01:00
edfbae0783
merge: modules/sd_models.py
2026-03-13 14:45:21 +01:00
403e9c2241
reduce race condition
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-02-27 12:07:56 +01:00
a485347896
fix kandinsky5
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-02-24 18:19:23 +01:00
554c8fbf2f
remove model: hdm
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-02-24 18:19:23 +01:00
d79d4edddb
add explicit sdnq import
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2026-02-21 13:26:20 +00:00
494e4a7a7b
fixes
2026-02-19 16:20:17 +01:00
f78f0eb4a5
refactor imports
2026-02-19 15:28:24 +01:00
d65a2d1ebc
ruff lint
2026-02-19 11:13:44 +01:00
e5c494f999
cleanup logger
2026-02-19 11:09:13 +01:00
a3074baf8b
unified logger
2026-02-19 09:46:42 +01:00
bfe014f5da
modernize typing
2026-02-19 09:15:37 +01:00
d3dff5df15
one-more-offload
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-02-04 15:05:22 +01:00
af9fe036a3
feat: add Anima (Cosmos-Predict-2B variant) pipeline support
...
Anima replaces the Cosmos T5-11B text encoder with Qwen3-0.6B + a
6-layer LLM adapter and uses CONST preconditioning instead of EDM.
- Add pipelines/model_anima.py loader with dynamic import of custom
AnimaTextToImagePipeline and AnimaLLMAdapter from model repo
- Register 'Anima' pipeline in shared_items.py
- Add name-based detection in sd_detect.py
- Fix list-format _class_name handling in guess_by_diffusers()
- Wire loader in sd_models.py load_diffuser_force()
- Skip noise_pred callback injection for Anima (uses velocity instead)
- Add output_type='np' override in processing_args.py
2026-02-02 00:44:51 +00:00
a7c32caae3
relocate all jsons to data
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-24 13:54:40 +01:00
c2c32d7847
Improve/update types and data handling
2026-01-21 14:13:00 -08:00
b3d65f4559
logging cleanup
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-16 11:32:09 +01:00
66fc59ceb7
load error trace
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-16 10:06:02 +01:00
680fddc036
disable fallback on models with custom loaders
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-16 09:59:42 +01:00
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
71d3482168
cleanup model types
...
Signed-off-by: vladmandic <mandic00@live.com >
2026-01-15 08:30:48 +01:00
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
bb13aabe17
add ovis-image
...
Signed-off-by: vladmandic <mandic00@live.com >
2025-12-26 08:05:25 +01:00
0b1e6d2d3c
improve offloading
...
Signed-off-by: Vladimir Mandic <mandic00@live.com >
2025-12-25 10:24:02 +00:00
a319a98e59
error handling of meta embeds
...
Signed-off-by: vladmandic <mandic00@live.com >
2025-12-23 10:23:14 +01:00
dcb7164d30
Update readfile type safety
2025-12-17 16:43:54 -08:00
c22ca8d76e
Create and opt in to dict type safety from JSON
...
Opt in via the keyword-only argument `dict_only`
2025-12-17 13:18:13 -08:00
409ad8d2bd
add longcat image and image-edit
...
Signed-off-by: vladmandic <mandic00@live.com >
2025-12-16 08:58:22 +01:00
acca58f50c
add kandinsky5
...
Signed-off-by: vladmandic <mandic00@live.com >
2025-12-09 09:47:22 +01:00
d3a2f6c7ed
fix loading local prequant models
...
Signed-off-by: vladmandic <mandic00@live.com >
2025-12-02 20:53:19 +01:00
0ad40d2b8b
lint
...
Signed-off-by: vladmandic <mandic00@live.com >
2025-12-02 12:25:04 +01:00
55c089ae48
Update runai-model-streamer logging integration
...
- Remove stdout redirect monkeypatch (fixed in runai v0.15.1 via PR #97 )
- Add RUNAI_STREAMER_LOG_LEVEL controlled by SD_LOAD_DEBUG
- Add one-time runai config log when hijack is activated
- Add `loader=runai|default` to model loading logs
- Remove per-file logging clutter from sd_hijack_safetensors.py
2025-12-02 02:01:51 +00:00
Vladimir Mandic
awsr
CalamitousFelicitousness