add support for nunchaku-lite models and engine

Signed-off-by: Vladimir Mandic <[email protected]>

CHANGELOG.md

@@ -10,7 +10,12 @@
   - [Microsoft Mage-Flow](https://huggingface.co/mage-flow-community/Mage-Flow) in *Base* and *Turbo* (distilled) variants  
     Mage-Flow is a 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing  
     *note*: Microsoft released and then unpublished the model, but we still have a mirror available for download  
+  - [Nunchaku-Lite](https://huggingface.co/lite-infer) pre-quantized models  
+    included: *Z-Image, Flux.1-Dev/Schnell/Krea/Kontex, Qwen-Image/Image-Edit, Ernie-Image*
 - **Features**
+  - add support for [Nunchaku-Lite](https://github.com/rootonchair/nunchaku-lite) inference engine  
+    unlike Nunchaku, Nunchaku-Lite is based on Kernels and does not require any additional packages to be installed  
+    but like original Nunchaku, it is only available for CUDA and right now only for `torch==2.11/2.12`  
   - storage analyzer: new feature that analyzes your storage used by sdnext per type and location  
     *system -> storage*  
   - video: support for scripts/extensions  
@@ -30,6 +35,7 @@
   - sdnq check contiguous
   - torch reset compile cache on reload
   - bypass sdna for caption/prompt-enhance calls
+  - skip sdnq for small weights  
 
 ## Update for 2026-07-23
 

TODO.md

@@ -18,7 +18,6 @@
 
 ### Unassigned
 
-- [Nunchaku Lite](https://github.com/huggingface/diffusers/pull/14100)
 - [Object clear](https://huggingface.co/jixin0101/ObjectClear) remover for Kanvas
 - Video models: add to Reference
 - Video models: support custom entries, finetunes

cli/hf-info.py

@@ -702,6 +702,7 @@ def search(repo_id: str) -> int:
         "pipeline": pipeline_value,
         "gated": gated_value,
         "size": size_total_raw,
+        "size_gb": round(size_total_raw / (1024**3), 2) if isinstance(size_total_raw, int) else None,
         "class": model_class,
         "dit": ", ".join(main_dit_entries) if len(main_dit_entries) > 0 else None,
         "dit_params": model_params_raw,

data/reference-nunchaku.json

@@ -212,5 +212,67 @@
     "extras": "sampler: Default, cfg_scale: 1.0, steps: 4",
     "size": 19.38,
     "date": "2023 November"
+  },
+  "Z-Image-Turbo Nunchaku-Lite": {
+    "path": "lite-infer/z-image-turbo-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "Tongyi-MAI--Z-Image-Turbo.jpg",
+    "extras": "sampler: Default, cfg_scale: 1.0, steps: 9",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 6.17,
+    "date": "2026 July"
+  },
+  "Baidu ERNIE-Image Nunchaku-Lite": {
+    "path": "lite-infer/ERNIE-Image-Turbo-nunchaku-lite-int4-bnb4-text-encoder",
+    "preview": "baidu--ERNIE-Image.jpg",
+    "extras": "sampler: Default, cfg_scale: 4.0, steps: 50",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 6.88,
+    "date": "2026 July"
+  },
+  "BFL FLUX.1 Dev Nunchaku-Lite": {
+    "path": "lite-infer/flux.1-dev-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "black-forest-labs--FLUX.1-dev.jpg",
+    "extras": "sampler: Default, cfg_scale: 3.5",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 10.97,
+    "date": "2026 July"
+  },
+  "BFL FLUX.1 Schnell Nunchaku-Lite": {
+    "path": "lite-infer/flux.1-schnell-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "black-forest-labs--FLUX.1-schnell.jpg",
+    "extras": "sampler: Default, cfg_scale: 3.5",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 10.95,
+    "date": "2026 July"
+  },
+  "BFL FLUX.1 Kontext Nunchaku-Lite": {
+    "path": "lite-infer/flux.1-kontext-dev-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "black-forest-labs--FLUX.1-Kontext-dev.jpg",
+    "extras": "sampler: Default, cfg_scale: 3.5",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 10.97,
+    "date": "2026 July"
+  },
+  "BFL FLUX.1 Krea Nunchaku-Lite": {
+    "path": "lite-infer/flux.1-krea-dev-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "black-forest-labs--FLUX.1-Krea-dev.jpg",
+    "extras": "sampler: Default, cfg_scale: 4.5",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 10.97,
+    "date": "2026 July"
+  },
+  "Qwen-Image Nunchaku-Lite": {
+    "path": "lite-infer/Qwen-Image-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "Qwen--Qwen-Image.jpg",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 16.81,
+    "date": "2026 July"
+  },
+  "Qwen-Image-Edit-2509 Nunchaku-Lite": {
+    "path": "lite-infer/qwen-image-edit-2509-nunchaku-lite-int4_r32-bnb4-text-encoder",
+    "preview": "Qwen--Qwen-Image-Edit-2509.jpg",
+    "desc": "Nunchaku-Lite quantization using precompiled Kernels",
+    "size": 16.81,
+    "date": "2026 July"
   }
 }

installer.py

@@ -1377,6 +1377,7 @@ def set_environment():
     os.environ.setdefault('CUDA_MODULE_LOADING', 'LAZY')
     os.environ.setdefault('DO_NOT_TRACK', '1')
     os.environ.setdefault('FORCE_CUDA', '1')
+    os.environ.setdefault('DIFFUSERS_TRUST_REMOTE_KERNELS', 'true')
     os.environ.setdefault('GRADIO_ANALYTICS_ENABLED', 'False')
     os.environ.setdefault('K_DIFFUSION_USE_COMPILE', '0')
     os.environ.setdefault('KINETO_LOG_LEVEL', '3')

modules/attention.py

@@ -291,7 +291,7 @@ def set_diffusers_attention(pipe, quiet = False):
 orig_get_kernel = None
 def get_kernel_hijack(repo_id, revision=None, version=None, backend=None, user_agent=None, trust_remote_code: bool | list[str] = False): # pylint: disable=unused-argument
     log.debug(f'Attention dispatcher hub: repo="{repo_id}" revision={revision} version={version} backend={backend}')
-    user_agent = 'kernels/0.14.1'
+    user_agent = 'kernels/0.16.0'
     module = None
     try:
         module = orig_get_kernel(repo_id, revision=revision, version=version, backend=backend, user_agent=user_agent, trust_remote_code=True)
@@ -309,7 +309,7 @@ def get_hf_api_hijack(user_agent = None): # pylint: disable=unused-argument
 def hijack_kernels():
     global orig_get_kernel # pylint: disable=global-statement
     try:
-        install('kernels==0.14.1')
+        install('kernels==0.16.0')
         import kernels
         import kernels.utils
         log.debug(f'Attention dispatcher: kernels={kernels.__version__}')

modules/model_quant.py

@@ -198,6 +198,8 @@ def check_nunchaku(module: str = ''):
     from modules import shared
     if 'nunchaku' not in shared.opts.sd_model_checkpoint.lower():
         return False
+    if 'nunchaku-lite' in shared.opts.sd_model_checkpoint.lower():
+        return False
     base_path = shared.opts.sd_model_checkpoint.split('+')[0]
     for v in shared.reference_models.values():
         if v.get('path', '') != base_path:

pipelines/model_ernie.py

@@ -14,6 +14,10 @@ def load_ernie_image(checkpoint_info, diffusers_load_config=None):
     load_args, _quant_args = model_quant.get_dit_args(diffusers_load_config, allow_quant=False)
     log.debug(f'Load model: type=ERNIE-Image repo="{repo_id}" offload={shared.opts.diffusers_offload_mode} dtype={devices.dtype} args={load_args} pe={shared.opts.model_ernie_enable_pe}')
 
+    if 'nunchaku-lite' in repo_id.lower():
+        from modules.attention import hijack_kernels
+        hijack_kernels()
+
     from pipelines.ernie import ERNIE_SPEC
     transformer = generic.load_transformer(
         repo_id,

pipelines/model_flux.py

@@ -46,6 +46,10 @@ def load_flux(checkpoint_info, diffusers_load_config=None):
         from pipelines.flux.flux_nunchaku import load_flux_nunchaku
         transformer = load_flux_nunchaku(repo_id)
 
+    if 'nunchaku-lite' in repo_id.lower():
+        from modules.attention import hijack_kernels
+        hijack_kernels()
+
     # finally load transformer and text encoder if not already loaded
     if transformer is None:
         transformer = generic.load_transformer(repo_id, cls_name=diffusers.FluxTransformer2DModel, load_config=diffusers_load_config)

pipelines/model_qwen.py

@@ -16,6 +16,10 @@ def load_qwen(checkpoint_info, diffusers_load_config=None):
     load_args, _quant_args = model_quant.get_dit_args(diffusers_load_config, module='Model')
     log.debug(f'Load model: type=Qwen model="{checkpoint_info.name}" repo="{repo_id}" offload={shared.opts.diffusers_offload_mode} dtype={devices.dtype} args={load_args}')
 
+    if 'nunchaku-lite' in repo_id.lower():
+        from modules.attention import hijack_kernels
+        hijack_kernels()
+
     if '2509' in repo_id or '2511' in repo_id:
         cls_name = diffusers.QwenImageEditPlusPipeline
         diffusers.pipelines.auto_pipeline.AUTO_TEXT2IMAGE_PIPELINES_MAPPING["qwen-image"] = diffusers.QwenImageEditPlusPipeline

pipelines/model_z_image.py

@@ -43,6 +43,9 @@ def load_z_image(checkpoint_info, diffusers_load_config=None):
     transformer = None
     if model_quant.check_nunchaku('Model'): # only available model
         transformer = init_nunchaku()
+    if 'nunchaku-lite' in repo_id.lower():
+        from modules.attention import hijack_kernels
+        hijack_kernels()
     if transformer is None:
         transformer = generic.load_transformer(repo_id, cls_name=diffusers.ZImageTransformer2DModel, load_config=diffusers_load_config)