sharpenb commited on
Commit
31b42fa
1 Parent(s): 3c3ca71

Upload folder using huggingface_hub (#2)

Browse files

- 2fa0832280637b688206fe1bab760bfbbe150444df3fd8acee20f5f31a495dc0 (968f3a9564aea232b44fb564faa059ee5dc51ce3)
- 84c6967a44e55d7b332ea26e59d5217c321b2c55346bfe709508f821d4f8b58a (e2a3c3ae0dd190abced8c4972a80e7d11a6a2d9c)

README.md CHANGED
@@ -35,7 +35,10 @@ metrics:
35
 
36
  ![image info](./plots.png)
37
 
38
- 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, ...).
 
 
 
39
 
40
  ## Setup
41
 
@@ -75,7 +78,7 @@ The configuration info are in `config.json`.
75
 
76
  ## License
77
 
78
- We follow the same license as the original model. Please check the license of the original model nitrosocke-Arcane-Diffusion-turbo before using this model.
79
 
80
  ## Want to compress other models?
81
 
 
35
 
36
  ![image info](./plots.png)
37
 
38
+ **Important remarks:**
39
+ - The quality of the model output might slightly vary compared to the base model. There might be minimal quality loss.
40
+ - 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, ...).
41
+ - 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).
42
 
43
  ## Setup
44
 
 
78
 
79
  ## License
80
 
81
+ We follow the same license as the original model. Please check the license of the original model nitrosocke/Arcane-Diffusion before using this model.
82
 
83
  ## Want to compress other models?
84
 
config.json CHANGED
@@ -1 +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": false, "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": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "model_name": "nitrosocke/Arcane-Diffusion", "weight_name": "None", "save_load_fn": "stable_fast"}
 
1
+ {"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": false, "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": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "model_name": "nitrosocke/Arcane-Diffusion", "weight_name": "None", "save_load_fn": "stable_fast"}
model/optimized_model.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bde853ca0bf8908fbff664cb45bb286c4645f2dfbccc9c6e862cfe32bdae8fdd
3
- size 2743383882
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51117358bc64a4d5da0d45f41712525ad9cdc799e77b9b26f8d7414f4083cbc
3
+ size 2743420727
model/smash_config.json CHANGED
@@ -1 +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": false, "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": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "model_name": "nitrosocke/Arcane-Diffusion", "weight_name": "None", "save_load_fn": "stable_fast"}}
 
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', 'tiling', 'step_caching']", "static_batch": true, "static_shape": false, "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": 512, "image_width": 512, "version": "1.5", "task": "txt2img", "model_name": "nitrosocke/Arcane-Diffusion", "weight_name": "None", "save_load_fn": "stable_fast"}}
plots.png CHANGED