add smollm3, add auraflow-0.2, enable taesd for auraflox

Signed-off-by: Vladimir Mandic <mandic00@live.com>

CHANGELOG.md

@@ -1,8 +1,8 @@
 # Change Log for SD.Next
 
-## Update for 2025-07-12
+## Update for 2025-07-14
 
-### Highlights for 2025-07-12
+### Highlights for 2025-07-14
 
 In this release we finally break with legacy with the removal of the original [A1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui/) codebase which has not been maintained for a while now  
 This plus major cleanup of codebase and external dependencies resulted in ~53k LoC (*lines-of-code*) reduction and spread over [~720 files](https://github.com/vladmandic/sdnext/pull/4017)!  
@@ -23,7 +23,7 @@ Although upgrades and existing installations are tested and should work fine!
 
 [ReadMe](https://github.com/vladmandic/automatic/blob/master/README.md) | [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [WiKi](https://github.com/vladmandic/automatic/wiki) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867)
 
-### Details for 2025-07-12
+### Details for 2025-07-14
 
 - **License**  
   - SD.Next [license](https://github.com/vladmandic/sdnext/blob/dev/LICENSE.txt) switched from **aGPL-v3.0** to **Apache-v2.0**  
@@ -40,8 +40,12 @@ Although upgrades and existing installations are tested and should work fine!
     available via *networks -> models -> reference*  
   - add **FLUX.1-Kontext-Dev** inpaint workflow  
   - support **FLUX.1** all-in-one safetensors  
-  - support **TAESD** preview and remote VAE for **HunyuanDit**  
-  - support for [Gemma 3n](https://huggingface.co/google/gemma-3n-E4B-it) E2B and E4B LLM/VLM models in **prompt enhance** and process **captioning**  
+  - support for [Google Gemma 3n](https://huggingface.co/google/gemma-3n-E4B-it) E2B and E4B LLM/VLM models  
+    available in **prompt enhance** and process **captioning**  
+  - support for [HuggingFace SmolLM3](https://huggingface.co/HuggingFaceTB/SmolLM3-3B) 3B LLM model  
+    available in **prompt enhance**  
+  - add [fal AuraFlow 0.2](https://huggingface.co/fal/AuraFlow-v0.2) in addition to existing [fal AuraFlow 0.3](https://huggingface.co/fal/AuraFlow-v0.3) due to large differences in model behavior  
+    available via *networks -> models -> reference*  
 - **Video**
   - redesigned **Video** interface  
   - support for **Generic** video models  
@@ -73,6 +77,8 @@ Although upgrades and existing installations are tested and should work fine!
   - **Styles** can now include both generation params and server settings  
     see [Styles docs](https://vladmandic.github.io/sdnext-docs/Styles/) for details  
   - **TAESD** is now default preview type since its the only one that supports most new models  
+  - support **TAESD** preview and remote VAE for **HunyuanDit**  
+  - support **TAESD** preview and remote VAE for **AuraFlow**  
   - SD.Next now starts with *locked* state preventing model loading until startup is complete  
   - warn when modifying legacy settings that are no longer supported, but available for compatibilty  
 - **API**  
@@ -89,6 +95,8 @@ Although upgrades and existing installations are tested and should work fine!
   - fix api `/sdapi/v1/embeddings` endpoint  
   - fix incorrect reporting of deleted and modified files  
   - allow upscaling with models that have implicit VAE processing  
+  - sdnq use inference context during quantization  
+  - framepack improve offloading  
   - improve infotext param parsing  
   - improve extensions ui search  
   - improve model type autodetection  

html/reference.json

@@ -273,6 +273,12 @@
     "preview": "fal--AuraFlow-v0.3.jpg",
     "skip": true
   },
+  "AuraFlow 0.2": {
+    "path": "fal/AuraFlow-v0.2",
+    "desc": "AuraFlow v0.2 is the fully open-sourced largest flow-based text-to-image generation model. The model was trained with more compute compared to the previous version, AuraFlow-v0.1",
+    "preview": "fal--AuraFlow-v0.3.jpg",
+    "skip": true
+  },
 
   "Segmind Vega": {
     "path": "huggingface/segmind/Segmind-Vega",

modules/sd_vae_remote.py

@@ -17,6 +17,7 @@ hf_decode_endpoints = {
 hf_decode_endpoints['pixartalpha'] = hf_decode_endpoints['sd']
 hf_decode_endpoints['pixartsigma'] = hf_decode_endpoints['sdxl']
 hf_decode_endpoints['hunyuandit'] = hf_decode_endpoints['sdxl']
+hf_decode_endpoints['auraflow'] = hf_decode_endpoints['sdxl']
 hf_decode_endpoints['omnigen'] = hf_decode_endpoints['sdxl']
 hf_decode_endpoints['h1'] = hf_decode_endpoints['f1']
 hf_decode_endpoints['chroma'] = hf_decode_endpoints['f1']
@@ -31,6 +32,7 @@ hf_encode_endpoints = {
 hf_encode_endpoints['pixartalpha'] = hf_encode_endpoints['sd']
 hf_encode_endpoints['pixartsigma'] = hf_encode_endpoints['sdxl']
 hf_encode_endpoints['hunyuandit'] = hf_encode_endpoints['sdxl']
+hf_encode_endpoints['auraflow'] = hf_encode_endpoints['sdxl']
 hf_encode_endpoints['omnigen'] = hf_encode_endpoints['sdxl']
 hf_encode_endpoints['h1'] = hf_encode_endpoints['f1']
 hf_encode_endpoints['lumina2'] = hf_encode_endpoints['f1']

modules/sd_vae_taesd.py

@@ -59,7 +59,7 @@ def get_model(model_type = 'decoder', variant = None):
         model_cls = 'sd'
     elif model_cls in {'h1', 'lumina2', 'chroma'}:
         model_cls = 'f1'
-    elif model_cls in {'pixartsigma', 'hunyuandit', 'omnigen'}:
+    elif model_cls in {'pixartsigma', 'hunyuandit', 'omnigen', 'auraflow'}:
         model_cls = 'sdxl'
     elif model_cls not in supported:
         warn_once(f'cls={shared.sd_model.__class__.__name__} type={model_cls} unsuppported', variant=variant)

scripts/prompt_enhance.py

@@ -50,6 +50,7 @@ class Options:
         'HuggingFaceTB/SmolLM2-135M-Instruct': {},
         'HuggingFaceTB/SmolLM2-360M-Instruct': {},
         'HuggingFaceTB/SmolLM2-1.7B-Instruct': {},
+        'HuggingFaceTB/SmolLM3-3B': {},
         'meta-llama/Llama-3.2-1B-Instruct': {},
         'meta-llama/Llama-3.2-3B-Instruct': {},
         'cognitivecomputations/Dolphin3.0-Llama3.2-1B': {},