update notes

CHANGELOG.md

@@ -4,24 +4,31 @@
 
 ### Highlights for 2024-06-21
 
-Following zero-day **SD3** release, a week later here's a refresh with more than a few improvements.  
-But there's more than SD3:
-- support for quantized **T5** text encoder in all models that use T5: FP4/FP8/FP16/INT8 (SD3, PixArt-Σ, etc)
-- support for **PixArt-Sigma** in small/medium/large variants
+Following zero-day **SD3** release, a week later here's a refresh with 10+ improvements  
+including full prompt attention, support for compressed weights, additional text-encoder quantization modes.  
+
+But there's more than SD3:  
+- support for quantized **T5** text encoder in all models that use T5: FP4/FP8/FP16/INT8 (SD3, PixArt-Σ, etc)  
+- support for **PixArt-Sigma** in small/medium/large variants  
 - support for **HunyuanDiT 1.1**  
 - (finally) new release of **Torch-DirectML**  
+- over 20 overall fixes  
 
 ### Model Improvements
 
 - **SD3**: enable tiny-VAE (TAESD) preview and non-full quality mode  
 - SD3: enable base LoRA support  
 - SD3: add support for FP4 quantized T5 text encoder  
-  simply select in *settings -> model -> text encoder*
+  simply select in *settings -> model -> text encoder*  
+  *note* for SD3 with T5, set SD.Next to use FP16 precision, not BF16 precision  
 - SD3: add support for INT8 quantized T5 text encoder, thanks @Disty0!  
 - SD3: enable cpu-offloading for T5 text encoder, thanks @Disty0!  
 - SD3: simplified loading of model in single-file safetensors format  
   model load can now be performed fully offline  
 - SD3: add support for NNCF compressed weights, thanks @Disty0!
+- SD3: full support for prompt parsing and attention, thanks @AI-Casanova!
+- SD3: ability to target different prompts to each of text-encoders, thanks @AI-Casanova!  
+  example: `dog TE2: cat TE3: bird`
 - SD3: add support for sampler shift for Euler FlowMatch  
   see *settings -> samplers*, also available as param in xyz grid  
   higher shift means model will spend more time on structure and less on details  
@@ -32,7 +39,6 @@ But there's more than SD3:
   simply select in *settings -> model -> text encoder* before or after model load  
 - **HunyuanDiT**: support for model version 1.1  
 
-
 ### Improvements: General
 
 - support FP4 quantized T5 text encoder, in addtion to existing FP8 and FP16

modules/sd_models.py

@@ -562,30 +562,30 @@ def detect_pipeline(f: str, op: str = 'model', warning=True, quiet=False):
             # guess by size
             if os.path.isfile(f) and f.endswith('.safetensors'):
                 size = round(os.path.getsize(f) / 1024 / 1024)
-                if size < 128:
+                if (size < 128):
                     warn(f'Model size smaller than expected: {f} size={size} MB')
                 elif (size >= 316 and size <= 324) or (size >= 156 and size <= 164): # 320 or 160
                     warn(f'Model detected as VAE model, but attempting to load as model: {op}={f} size={size} MB')
                     guess = 'VAE'
-                elif size >= 4970 and size <= 4976: # 4973
+                elif (size >= 4970 and size <= 4976): # 4973
                     guess = 'Stable Diffusion 2' # SD v2 but could be eps or v-prediction
                 # elif size < 0: # unknown
                 #    guess = 'Stable Diffusion 2B'
-                elif size >= 5791 and size <= 5799: # 5795
+                elif (size >= 5791 and size <= 5799): # 5795
                     if op == 'model':
                         warn(f'Model detected as SD-XL refiner model, but attempting to load a base model: {op}={f} size={size} MB')
                     guess = 'Stable Diffusion XL Refiner'
                 elif (size >= 6611 and size <= 7220): # 6617, HassakuXL is 6776, monkrenRealisticINT_v10 is 7217
                     guess = 'Stable Diffusion XL'
-                elif size >= 3361 and size <= 3369: # 3368
+                elif (size >= 3361 and size <= 3369): # 3368
                     guess = 'Stable Diffusion Upscale'
-                elif size >= 4891 and size <= 4899: # 4897
+                elif (size >= 4891 and size <= 4899): # 4897
                     guess = 'Stable Diffusion XL Inpaint'
-                elif size >= 9791 and size <= 9799: # 9794
+                elif (size >= 9791 and size <= 9799): # 9794
                     guess = 'Stable Diffusion XL Instruct'
-                elif size > 3138 and size < 3142: #3140
+                elif (size > 3138 and size < 3142): #3140
                     guess = 'Stable Diffusion XL'
-                elif size > 5692 and size < 5698 or size > 4134 and size < 4138:
+                elif (size > 5692 and size < 5698) or (size > 4134 and size < 4138) or (size > 10362 and size < 10366):
                     guess = 'Stable Diffusion 3'
             # guess by name
             """