Upload folder using huggingface_hub (#1)

- bc002df471ecd4a392b7779f08feb8486f6e16c5be2ad927c8f7ed77b6199f55 (070cd8c166ac4606b2b8df859636344c45cc60ca)
- 902e60282882d2690bb2259eec68e8fc2dc9817edae6f18a1a444d4615ed4c40 (2e3eea7e69a48000d6560c6caa7ee6919b0b8529)
- 8c69c5983bc1b10383d46645c1e29545bc855abda2445a2b218a969f75a68ade (9f77e1ac2e8f6b8ce321e4294b8537efd2a263c4)
- 805a314f908418b0cc8d5eafc06217b84853ee2c52702afdecba630c7ee9606f (0e635fa223234596ca713672411ce8c72f5bfcc5)

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+images/page2.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+language:
+- en
+license: creativeml-openrail-m
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- safetensors
+- diffusers
+thumbnail: https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page1.jpg
+inference: true
+---
+# Overview
+
+This is simply wavymulder/Analog-Diffusion with the safety checker disabled.
+
+**DO NOT** attempt to use this model to generate harmful or illegal content.
+
+
+
+
+**Analog Diffusion**
+![Header](https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page1.jpg)
+[*CKPT DOWNLOAD LINK*](https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/analog-diffusion-1.0.ckpt) - This is a dreambooth model trained on a diverse set of analog photographs.
+
+In your prompt, use the activation token: `analog style`
+
+You may need to use the words `blur` `haze` `naked` in your negative prompts. My dataset did not include any NSFW material but the model seems to be pretty horny. Note that using `blur` and `haze` in your negative prompt can give a sharper image but also a less pronounced analog film effect.
+
+Trained from 1.5 with VAE.
+
+Please see [this document where I share the parameters (prompt, sampler, seed, etc.) used for all example images.](https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/parameters_used_examples.txt)
+
+## Gradio
+
+We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run Analog-Diffusion:
+
+[Open in Spaces](https://huggingface.co/spaces/akhaliq/Analog-Diffusion)
+
+
+![Environments Example](https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page2.jpg)
+![Characters Example](https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page3.jpg)
+
+Here's a [link to non-cherrypicked batches.](https://imgur.com/a/7iOgTFv)

analog-diffusion-1.0.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a1c90893cc7892dfd7438004fa954696f94208c84773b1cabb434e5a856a0c
+size 2132856622

analog-diffusion-1.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f6fff5088a9c5f5aa7cefa0a5a859d0424fc68fdc440e0ee5608a2b82e5ff9
+size 2132625462

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1 @@
+{"_class_name": "StableDiffusionPipeline", "_diffusers_version": "0.10.0.dev0", "feature_extractor": ["transformers", "CLIPImageProcessor"], "requires_safety_checker": false, "safety_checker": [null, null], "scheduler": ["diffusers", "PNDMScheduler"], "text_encoder": ["transformers", "CLIPTextModel"], "tokenizer": ["transformers", "CLIPTokenizer"], "unet": ["diffusers", "UNet2DConditionModel"], "vae": ["diffusers", "AutoencoderKL"]}

parameters_used_examples.txt

@@ -0,0 +1,115 @@
+
+https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page1.jpg
+
+Page 1, in order left to right, top to bottom:
+
+analog style closeup portrait of cowboy George Washington
+Negative prompt: blur haze
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3730721345, Size: 768x1024, Denoising strength: 0.4, First pass size: 0x0
+
+(I don't know why "cowboy" made this work how it did lol)
+
+analog style blonde Princess Peach in the mushroom kingdom
+Negative prompt: blur haze
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2346235940, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style portrait of cosmonaut Johnny Cash
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1624745865, Size: 768x1024, Denoising strength: 0.4, First pass size: 0x0
+
+analog style closeup portrait of Emma Stone, background futuristic neon at night storefront
+Negative prompt: blur haze
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 1191447504, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style portrait of beautiful young Zoe Saldana 1950s hollywood glamour
+Negative prompt: blur haze naked
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3466625277, Size: 576x832, Denoising strength: 0.4, First pass size: 0x0
+
+analog style photograph of young Harrison Ford as Han Solo, star wars behind the scenes
+Negative prompt: blur haze weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 185589077, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style Lady Gaga as a 1960s
+Negative prompt: blur haze hdr naked
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 4050111649, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style portrait of Heath Ledger as a 1930s baseball player
+Negative prompt: blur haze weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 869197698, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+
+
+
+
+
+https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page2.jpg
+
+Page 2, in order left to right, top to bottom:
+
+analog style christmas lights night neighborhood decorated
+Negative prompt: blur haze naked weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 1191229171, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style an amazing vista
+Negative prompt: blur haze
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4154556393, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style a gaudy mansion interior
+Negative prompt: blur haze
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1182670394, Size: 1024x768, Denoising strength: 0.4, First pass size: 0x0
+
+analog style film still of Audrey Hepburn at a neon convenience storefront
+Negative prompt: blur haze hdr
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1102981569, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style cozy comfy cabin interior
+Negative prompt: blur haze naked weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2559884475, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style at night a campsite under the stars
+Negative prompt: blur haze
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3798055821, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style a wes anderson art deco building
+Negative prompt: blur haze
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 943802667, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style epic explosion
+Negative prompt: blur haze
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4190436474, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+analog style spooky haunted house in a cemetery
+Negative prompt: blur c
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2250388373, Size: 960x704, Denoising strength: 0.4, First pass size: 0x0
+
+
+
+
+
+
+https://huggingface.co/wavymulder/Analog-Diffusion/resolve/main/images/page3.jpg
+
+Page 3, in order left to right, top to bottom:
+
+analog style portrait of a lion
+Negative prompt: blur haze
+Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 923811059, Size: 704x1024, Denoising strength: 0.3, First pass size: 0x0
+
+analog style portrait of a knight on Mars
+Negative prompt: blur haze naked weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2315617348, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style cyberpunk portrait of a cute girl, beautiful
+Negative prompt: blur haze naked weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 1809542040, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style cyberpunk portrait of a handsome young man
+Negative prompt: blur haze naked weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3026358048, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style portrait of a hipster
+Negative prompt: blur haze naked weapon
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 4209566602, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0
+
+analog style owl
+Negative prompt: blur haze
+Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3349041283, Size: 704x960, Denoising strength: 0.4, First pass size: 0x0

safety_checker/config.json

@@ -0,0 +1,181 @@
+{
+  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
+  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14
+  }
+}

safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.10.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eac1795aca396db76dc02aeab649aac7ca620a13979a188d282575a52b995b5
+size 492307041

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "openai/clip-vit-large-patch14",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4dabbecbbeada4c1e015619a021884b83719659283182acb7543b1a24c8c466
+size 3438366373

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf4507d99b88db73f3916e2a20169fe74ada6b5582e9af56cfa80f5f3141765
+size 334711857