a830529ec745def5596eee3148666b9a548dfbf9ae63e988fc9f6d32e06d6fc5

README.md

@@ -35,7 +35,10 @@ metrics:
 
 ![image info](./plots.png)
 
-These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in config.json. Results may vary in other settings (e.g. other hardware, image size, batch size, ...).
+**Important remarks:**
+- The quality of the model output might slightly vary compared to the base model. There might be minimal quality loss.
+- These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in config.json and are obtained after a hardware warmup. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...).
+- You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
 
 ## Setup
 
@@ -75,7 +78,7 @@ The configuration info are in `config.json`.
 
 ## License
 
-We follow the same license as the original model. Please check the license of the original model segmind-Segmind-Vega before using this model.
+We follow the same license as the original model. Please check the license of the original model segmind/Segmind-Vega before using this model.
 
 ## Want to compress other models?
 

config.json

@@ -1 +1 @@
-{"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.005, "compilers": "['diffusers2']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "save_dir": "/ceph/hdd/staff/charpent/models/.models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "model_name": "segmind/Segmind-Vega", "weight_name": "None", "save_load_fn": "stable_fast"}
+{"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.005, "compilers": "['diffusers2', 'tiling', 'step_caching']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "save_dir": "/ceph/hdd/staff/charpent/models/.models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "model_name": "segmind/Segmind-Vega", "weight_name": "None", "save_load_fn": "stable_fast"}

model/smash_config.json

@@ -1 +1 @@
-{"api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "smash_config": {"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.005, "compilers": "['diffusers2']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": "/ceph/hdd/staff/charpent/.cache/models", "save_dir": "/ceph/hdd/staff/charpent/models/.models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "model_name": "segmind/Segmind-Vega", "weight_name": "None", "save_load_fn": "stable_fast"}}
+{"api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "smash_config": {"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.005, "compilers": "['diffusers2', 'tiling', 'step_caching']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": "/ceph/hdd/staff/charpent/.cache/models", "save_dir": "/ceph/hdd/staff/charpent/models/.models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "model_name": "segmind/Segmind-Vega", "weight_name": "None", "save_load_fn": "stable_fast"}}