Config Variation

README.md

@@ -9,6 +9,8 @@ tags:
 - di.ffusion.ai
 - art
 - base model
+- diffusers
+inference: true
 library_name: diffusers
 widget:
 - text: >-
@@ -52,6 +54,14 @@ widget:
 ![ffusion-basesm32.jpg](https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/FHidip3rT8mL1UdGDyfSd.jpeg)
 
 ## Model Overview: Unleashing the Power of Imagination!
+<div style="display: flex; flex-wrap: wrap; gap: 2px;">
+  <a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/🧠%20Model%20Type-Diffusion--based%20text--to--image%20generation%20model-blueviolet" alt="Model Type"></a>
+  <a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/🔏%20License-CreativeML%20Open%20RAIL++--M%20License-orange" alt="License"></a>
+  <a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/🖥️%20Hardware%20Type-A100%20PCIe%2040GB-green" alt="Hardware Type"></a>
+  <a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/⏰%20Hours%20Used-1190-red" alt="Hours Used"></a>
+  <a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/🌩️%20Cloud%20Provider-CoreWeave%20%26%20Runpod-blue" alt="Cloud Provider"></a>
+  <a href="https://huggingface.co/FFusion/"><img src="https://img.shields.io/badge/🍃%20Carbon%20Emitted-124.95%20kg%20of%20CO2-brightgreen" alt="Carbon Emitted"></a>
+</div>
 
 FFUSION AI is a state-of-the-art image generation and transformation tool, developed around the leading Latent Diffusion Model. Leveraging Stable Diffusion 2.1, FFUSION AI converts your prompts into captivating artworks. Discover an imaginative landscape where ideas come to life in vibrant, surreal visuals.
 

scheduler/scheduler_config.json

@@ -9,11 +9,8 @@
   "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "v_prediction",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "steps_offset": 1,
-  "thresholding": false,
-  "timestep_spacing": "leading",
+  "skip_prk_steps": true,
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/text_encoder",
+
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 23,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "vocab_size": 49408
 }

tokenizer/tokenizer_config.json

@@ -8,7 +8,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -20,7 +19,9 @@
   },
   "errors": "replace",
   "model_max_length": 77,
+  "name_or_path": "stabilityai/stable-diffusion-2-1",
   "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -2,9 +2,6 @@
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.19.0.dev0",
   "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
   "attention_head_dim": [
     5,
     10,
@@ -18,12 +15,7 @@
     1280
   ],
   "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
   "cross_attention_dim": 1024,
-  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -32,38 +24,24 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "layers_per_block": 2,
-  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
   "num_attention_heads": null,
   "num_class_embeds": null,
   "only_cross_attention": false,
   "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
-  "resnet_time_scale_shift": "default",
-  "sample_size": 96,
-  "time_cond_proj_dim": null,
-  "time_embedding_act_fn": null,
-  "time_embedding_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "transformer_layers_per_block": 1,
+  "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": null,
+  "upcast_attention": false,
   "use_linear_projection": true
 }

vae/config.json

@@ -20,8 +20,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
-  "scaling_factor": 0.18215,
+  "sample_size": 256,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",