add pony-v7

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

CHANGELOG.md

@@ -21,6 +21,8 @@
 - **Models**
   - [Tencent HunyuanImage 2.1](https://huggingface.co/tencent/HunyuanImage-2.1) in *full*, *distilled* and *refiner* variants  
     HunyuanImage-2.1 is a large (51GB) T2I model capable of natively generating 2K images and uses Qwen2.5 + T5 text-encoders and 32x VAE  
+  - [Pony 7](https://huggingface.co/purplesmartai/pony-v7-base)  
+    Pony 7 steps in a different direction from previous Pony models and is based on AuraFlow architecture and UMT5 encoder  
 - **Features**
   - **offline mode**: enable in *settings -> hugginface*  
     enables fully offline mode where previously downloaded models can be used as-is  

html/reference.json

@@ -1134,6 +1134,15 @@
     "tags": "community",
     "date": "2025 September"
   },
+  "purplesmartai Pony 7": {
+    "path": "purplesmartai/pony-v7-base",
+    "preview": "purplesmartai--pony-v7-base.jpg",
+    "skip": true,
+    "desc": "Pony V7 is a versatile character generation model based on AuraFlow architecture. It supports a wide range of styles and species types (humanoid, anthro, feral, and more) and handles character interactions through natural language prompts.",
+    "extras": "",
+    "tags": "community",
+    "date": "October September"
+  },
   "ShuttleAI Shuttle 3.0 Diffusion": {
     "path": "shuttleai/shuttle-3-diffusion",
     "desc": "Shuttle uses Flux.1 Schnell as its base. It can produce images similar to Flux Dev or Pro in just 4 steps, and it is licensed under Apache 2. The model was partially de-distilled during training. When used beyond 10 steps, it enters refiner mode enhancing image details without altering the composition",

modules/sd_detect.py

@@ -68,7 +68,7 @@ def guess_by_name(fn, current_guess):
         return 'Lumina 2'
     elif 'kolors' in fn.lower():
         return 'Kolors'
-    elif 'auraflow' in fn.lower():
+    elif 'auraflow' in fn.lower() or 'pony-v7' in fn.lower():
         return 'AuraFlow'
     elif 'cogview3' in fn.lower():
         return 'CogView 3'

modules/sd_models.py

@@ -47,6 +47,7 @@ pipe_switch_task_exclude = [
     'StableDiffusionXLInstantIDPipeline',
     'XOmniPipeline',
     'HunyuanImagePipeline',
+    'AuraFlowPipeline',
 ]
 i2i_pipes = [
     'LEditsPPPipelineStableDiffusion', 'LEditsPPPipelineStableDiffusionXL',

modules/shared_items.py

@@ -7,6 +7,7 @@ pipelines = {
     'Custom Diffusers Pipeline': getattr(diffusers, 'DiffusionPipeline', None),
 
     # standard pipelines
+    'Diffusion': getattr(diffusers, 'DiffusionPipeline', None),
     'Stable Diffusion': getattr(diffusers, 'StableDiffusionPipeline', None),
     'Stable Diffusion Inpaint': getattr(diffusers, 'StableDiffusionInpaintPipeline', None),
     'Stable Diffusion Instruct': getattr(diffusers, 'StableDiffusionInstructPix2PixPipeline', None),

modules/ui_models.py

@@ -113,7 +113,7 @@ def create_ui():
                             else:
                                 typ = 'unknown'
                                 size = 'unknown'
-                            guess = 'Stable Diffusion XL' if 'XL' in f.upper() else 'Stable Diffusion' # set default guess
+                            guess = 'Diffusion' # set default guess
                             guess = sd_detect.guess_by_size(f, guess)
                             guess = sd_detect.guess_by_name(f, guess)
                             guess, pipeline = sd_detect.guess_by_diffusers(f, guess)