80 Commits

Author SHA1 Message Date
Vladimir Mandic 63a5722429 prepare queue mgmt
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2026-08-22 11:24:41 +02:00
Vladimir Mandic 48cf0166f3 separate progress monitoring from live preview, live preview improvements, progress details
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2026-08-07 11:41:40 +02:00
CalamitousFelicitousness 48fad8524e feat(krea2): add Krea 2 (K2) image model support
Krea 2 is a 12.9B single-stream flow-matching DiT trained from scratch, using a Qwen3-VL-4B text encoder and the Qwen-Image VAE. The transformer is vendored as a diffusers ModelMixin whose module tree mirrors the checkpoint, so weights load with no key conversion; the pipeline ports the reference encode, flow-matching denoise, and VAE decode. The text encoder is shared at runtime via the existing dedup registry, so Base and Turbo reuse one Qwen3-VL-4B copy.

Covers text-to-image, image-to-image, native LoRA, and the single-file UNET override. Also completes SD.Next's partial Qwen-Image VAE support (5D decode input and TAESD preview mapping) that K2 shares.
2026-06-23 04:41:54 +01:00
CalamitousFelicitousness 2f3d0e719d feat(ideogram4): add Ideogram 4 model support
Diffusers-native port of the 9.3B flow-matching DiT: dual-transformer asymmetric CFG, a 13-layer Qwen3-VL tap encoder deduped with VQA and prompt-enhance, the Flux.2 VAE, and a logit-normal schedule. Loads a published bf16 repo with SDNQ at load.
2026-06-05 01:54:18 +01:00
CalamitousFelicitousness 4af3a57741 feat(anima): native lora across transformer, llm_adapter, text encoder
Dispatch anima loras through a dedicated native loader covering kohya,
bfl/ai-toolkit, and hybrid (bfl with alpha plus qwen3 text encoder)
formats. Cosmos 2.0 path rename is mirrored from diffusers in flat
(underscore) form so rewritten paths match network_layer_mapping keys
without further conversion.

Split model_type from cosmos to anima so a future base-cosmos2 lora
path stays separable. Update flow_models, taesd supported list, and the
taesd wanvideo bucket so samplers and preview decoding keep working
after the split.

Extend assign_network_names_to_compvis_modules to walk pipe.llm_adapter
under the lora_llm_adapter_ prefix, and add llm_adapter to
default_components so activate and deactivate include it for anima
models while staying inert elsewhere via the existing getattr guards.
2026-04-25 03:16:03 +01:00
vladmandic 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
Vladimir Mandic e5c494f999 cleanup logger 2026-02-19 11:09:13 +01:00
Vladimir Mandic a3074baf8b unified logger 2026-02-19 09:46:42 +01:00
vladmandic da1cf2f996 refactor image methods
Signed-off-by: vladmandic <mandic00@live.com>
2026-02-11 12:29:00 +01:00
CalamitousFelicitousness 76aa949a26 refactor: integrate sharpfin for high-quality image resize
Vendor sharpfin library (Apache 2.0) and add centralized wrapper
module (images_sharpfin.py) replacing torchvision tensor/PIL
conversion and resize operations throughout the codebase.

- Add modules/sharpfin/ vendored library with MKS2021, Lanczos3,
  Mitchell, Catmull-Rom kernels and optional Triton sparse acceleration
- Add modules/images_sharpfin.py wrapper with to_tensor(), to_pil(),
  pil_to_tensor(), normalize(), resize(), resize_tensor()
- Add resize_quality and resize_linearize_srgb settings
- Add MKS2021 and Lanczos3 upscaler entries
- Replace torchvision.transforms.functional imports across 18 files
- to_pil() auto-detects HWC/BHWC layout, adds .round() before uint8
- Sparse Triton path falls back to dense GPU on compilation failure
- Mixed-axis resize splits into two single-axis scale() calls
- Masks and non-sRGB data always use linearize=False
2026-02-11 09:57:37 +01:00
Vladimir Mandic e8ff09a2d2 fix lora unload and improve preview error handler
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2026-02-07 09:07:34 +00:00
vladmandic cc03ebc584 move vae to subfolder
Signed-off-by: vladmandic <mandic00@live.com>
2026-01-30 11:34:25 +01:00
vladmandic 71d3482168 cleanup model types
Signed-off-by: vladmandic <mandic00@live.com>
2026-01-15 08:30:48 +01:00
vladmandic 409ad8d2bd add longcat image and image-edit
Signed-off-by: vladmandic <mandic00@live.com>
2025-12-16 08:58:22 +01:00
Disty0 f7b0bbb6e1 Complete Z-Image support 2025-11-27 17:25:36 +03:00
vladmandic ad6458aa7b add flux2
Signed-off-by: vladmandic <mandic00@live.com>
2025-11-26 15:47:17 +00:00
Vladimir Mandic f69b4c5589 disabling live preview should not disable progress updates
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-10-21 11:07:47 -04:00
Disty0 ab8b9b0eab Cleanup Omnigen 2 2025-06-28 13:53:37 +03:00
Vladimir Mandic bff75f0db3 add omnigen2
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-27 20:20:43 -04:00
Vladimir Mandic 533aa04bbd improve taesd live preview downscaling
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-27 18:16:32 -04:00
Vladimir Mandic d5a74d4a4a Merge branch 'dev' into feature/chroma-support 2025-06-26 13:06:31 -04:00
Vladimir Mandic ada38d57b4 add nvidia-cosmos-predict-2
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-26 12:21:43 -04:00
Enes Sadık Özbek 4b3ce06916 Initial support for Chroma 2025-06-18 00:38:17 +00:00
Disty0 046840c8be Fix HiDream sampling 2025-05-31 00:52:56 +03:00
Vladimir Mandic a5d3a68107 add cogview4
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-15 13:20:17 -04:00
Vladimir Mandic a7ccea60ff add lumina2
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-02-12 08:54:00 -05:00
Vladimir Mandic 49f5c8ab12 refactor taesd and add multiple variants in settings
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-01-12 14:09:55 -05:00
Vladimir Mandic 1f0ad43c50 teacache for ltxvideo
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-30 14:08:14 -05:00
Vladimir Mandic e010c57749 live preview error handling
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-29 13:54:14 -05:00
Vladimir Mandic ea6d3107ab update all todo statements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-22 08:39:31 -05:00
Vladimir Mandic 0803946c08 update changelog and cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-19 11:34:19 -05:00
Vladimir Mandic ab07788ab5 add sana
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-16 11:30:15 -05:00
Vladimir Mandic 3e8dec9297 add freescale
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-15 12:40:54 -05:00
Vladimir Mandic 8f21e96f73 update bnb and increase ui timeouts
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-11 15:22:51 -05:00
Vladimir Mandic 7c88bfb60a fix preview choice
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-09 14:16:26 -05:00
Vladimir Mandic 58146c0fc7 correct preview stats
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-11-25 14:42:46 -05:00
Vladimir Mandic b569d68b4f add ostris: experimental
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-10-26 21:51:36 -04:00
Vladimir Mandic 8457d45e26 fix alphavllm-lumina 2024-09-21 11:56:11 -04:00
Vladimir Mandic f2c5cbbb36 lint updates and diffusers installer 2024-09-06 14:10:53 -04:00
Disty0 fa1e77cc6d Fix Full VAE previews 2024-07-28 02:03:53 +03:00
Vladimir Mandic ea61900a4c fix bfloat and pag 2024-06-20 18:03:15 -04:00
Vladimir Mandic 1a6d313340 cleanup 2024-06-20 13:46:31 -04:00
Vladimir Mandic ad8419945a sd3 add taesd preview 2024-06-15 10:20:59 -04:00
Vladimir Mandic 5574833f0d refactor backend detection 2024-06-06 20:41:10 -04:00
Vladimir Mandic cf7118be4d refactor stable-cascade, fix taesd bf16, add skip-env cmd flag 2024-02-21 17:13:53 -05:00
Disty0 e631fd85e2 Stable Cascade previewer and fixes 2024-02-15 18:50:54 +03:00
Vladimir Mandic a22765274b major refactor: processing, taesd, scripts 2024-02-01 14:00:50 -05:00
Vladimir Mandic 325b9eb652 add live preview thread lock 2024-01-29 13:02:56 -05:00
Disty0 b13d40d52c Diffusers lock preview latent range 2024-01-29 20:26:55 +03:00
Vladimir Mandic 682da607a9 improve live preview 2024-01-29 08:53:48 -05:00