Adding `diffusers` weights of this model

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to FFusion/FFusion-BaSE

model_index.json

@@ -1,11 +1,11 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.19.0.dev0",
   "feature_extractor": [
     null,
     null
   ],
-  "requires_safety_checker": null,
+  "requires_safety_checker": false,
   "safety_checker": [
     null,
     null

scheduler/scheduler_config.json

@@ -1,14 +1,19 @@
 {
   "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.19.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "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,
-  "skip_prk_steps": true,
   "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -18,7 +19,7 @@
   "num_hidden_layers": 23,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27abfac2a818730effdf31368547e447a228230e5c0fa0d6cd67dffe7edf4f3
+size 680820392

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e400fca9292630a9647d4a046b8f23b8d625cafdc077102313c83d3e6c21c64
-size 1361597016
+oid sha256:c9c407c896a28b174b59eb4b65634b909fbb8f8183cc90927b88866ad9831771
+size 1168458360

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb0c8eec01e768ad0a8b2c2c3804297a05b750768628167469f38411bba29da
-size 1361674657
+oid sha256:a3c78800b3082d1bbbf1d0f6ecdf0f2a278da7207c34370c55142374b9a22a13
+size 1361655149

text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db18e4fced8981288f10a05cea6fd51691f1080a2b71534ada82cc93134e90e
+size 680899947

tokenizer/tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -19,9 +20,7 @@
   },
   "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

@@ -1,7 +1,10 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.2",
+  "_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,
@@ -15,7 +18,12 @@
     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",
@@ -24,23 +32,38 @@
   ],
   "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,
-  "sample_size": 64,
+  "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,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
+  "upcast_attention": null,
   "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b7edb76bebc5dbcf128424c54bae9793bcff43cee0e17cc35f0663e11e0adf
+oid sha256:509bb04d8940dba0f28c0200084936d26fa1885961367f45305a5eb386d9ac79
 size 3463925093

unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e48d95bec4a63c348a09bb319ae7e9f64120e677c9023b04f9667516640c92
+size 1732107093

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58da91d7052213c5831efadffb1bbc8e1e9eebeccb0b8d3961f619f95dcdd31
+size 1731904736

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.19.0.dev0",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -14,12 +14,14 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 256,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd1d1807563c2d1c8c5ab84dfc2f455fcad0064727d264dd5172c569b5c45b2
-size 334711857
+oid sha256:0eaa055d84ddad2df8593f4a3a2fdc58a905ecf2f17dee42e9bca32f70373b59
+size 334712113

vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d55c592ee39c6619b6c0232057b7979bbb8b8c91bcde23e4216c7d7a54b2768
+size 167405651

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b6885891b67baa7f872fe9d00c44acd1cfd72475d289d83d93031ea8b32115
+size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f14834bedf1e853c99644d00c92404f185e2798de52337f8fb6bb5bddb48703
-size 334643276
+oid sha256:f2b6e3f78759255c499bd0b1c3a4c3c9ecf4e489d09f7b21225906dabfb3ce3c
+size 334643268