update changelog and cleanup

CHANGELOG.md

@@ -53,12 +53,13 @@ To use and of the new models, simply select model from *Networks -> Reference* a
 
 **New Features...**
 
+- support for **Balanced Offload**, thanks @Disty0!  
+  balanced offload will dynamically split and offload models from the GPU based on the max gpu and cpu memory size: model parts that dont fit in the GPU will be dynamically sliced and offloaded to the CPU  
+  see *Settings -> Diffusers Settings -> Max GPU memory and Max CPU memory*  
+  *note*: balanced offload will force loading LoRA with Diffusers method and it is not compatible with Optimum Quanto  
 - support for **Optimum Quanto** with 8 bit and 4 bit quantization options, thanks @Disty0 and @Trojaner!  
   to use, go to Settings -> Compute Settings and enable "Quantize Model weights with Optimum Quanto" option  
   note: Optimum Quanto requires PyTorch 2.4  
-- support for **Balanced Offload**, thanks @Disty0!  
-  balanced offload will dynamically split and offload models from the gpu based on the max gpu and cpu memory size  
-  *note*: balanced offload will force loading LoRA with Diffusers method and it is not compatible with Optimum Quanto  
 - new prompt attention mode: **xhinker** which brings support for prompt attention to new models such as FLUX.1 and SD3  
   to use, enable in Settings -> Execution -> Prompt attention
 
@@ -87,6 +88,7 @@ To use and of the new models, simply select model from *Networks -> Reference* a
 - fix LoRA apply with force-diffusers
 - fix LoRA scales with force-diffusers
 - fix control API
+- fix VAE load refrerencing incorrect configuration
 - fix NVML gpu monitoring
 
 ## Update for 2024-07-08

modules/processing_callbacks.py

@@ -83,7 +83,7 @@ def diffusers_callback(pipe, step: int, timestep: int, kwargs: dict):
             for key in {"prompt_embeds", "negative_prompt_embeds", "add_text_embeds", "add_time_ids"} & set(kwargs):
                 kwargs[key] = kwargs[key].chunk(2)[-1]
     if hasattr(pipe, "_unpack_latents") and hasattr(pipe, "vae_scale_factor"): # FLUX
-        shared.state.current_latent = pipe._unpack_latents(kwargs['latents'], p.height, p.width, pipe.vae_scale_factor)
+        shared.state.current_latent = pipe._unpack_latents(kwargs['latents'], p.height, p.width, pipe.vae_scale_factor) # pylint: disable=protected-access
     else:
         shared.state.current_latent = kwargs['latents']
     if shared.cmd_opts.profile and shared.profiler is not None:

modules/sd_models.py

@@ -1674,7 +1674,6 @@ def reload_text_encoder(initial=False):
         return # dont unload
     signature = inspect.signature(shared.sd_model.__class__.__init__, follow_wrapped=True, eval_str=True).parameters
     t5 = [k for k, v in signature.items() if 'T5EncoderModel' in str(v)]
-    print('HERE', signature.items())
     if len(t5) > 0:
         from modules.model_t5 import set_t5
         shared.log.debug(f'Load: t5={shared.opts.sd_text_encoder} module="{t5[0]}"')