Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
stablediffusionapi.com
stable-diffusion-api
ultra-realistic
Instructions to use Winboy/Suva with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Winboy/Suva with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Winboy/Suva", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload folder using huggingface_hub
Browse files- .gitignore +2 -0
- README.md +66 -3
- model_index.json +42 -0
- scheduler/scheduler_config.json +23 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- text_encoder/pytorch_model.bin +3 -0
- text_encoder_2/config.json +25 -0
- text_encoder_2/model.safetensors +3 -0
- text_encoder_2/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +30 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +30 -0
- tokenizer_2/tokenizer_config.json +38 -0
- tokenizer_2/vocab.json +0 -0
- unet/config.json +73 -0
- unet/diffusion_pytorch_model.bin +3 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +37 -0
- vae/diffusion_pytorch_model.bin +3 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
.gitignore
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
step_*
|
| 2 |
+
epoch_*
|
README.md
CHANGED
|
@@ -1,3 +1,66 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: creativeml-openrail-m
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- stablediffusionapi.com
|
| 5 |
+
- stable-diffusion-api
|
| 6 |
+
- text-to-image
|
| 7 |
+
- ultra-realistic
|
| 8 |
+
pinned: true
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# NewDream-SDXL 2.0 API Inference
|
| 12 |
+
|
| 13 |
+

|
| 14 |
+
## Get API Key
|
| 15 |
+
|
| 16 |
+
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
|
| 17 |
+
|
| 18 |
+
Replace Key in below code, change **model_id** to "newdream-sdxl-20"
|
| 19 |
+
|
| 20 |
+
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
|
| 21 |
+
|
| 22 |
+
Try model for free: [Generate Images](https://stablediffusionapi.com/models/newdream-sdxl-20)
|
| 23 |
+
|
| 24 |
+
Model link: [View model](https://stablediffusionapi.com/models/newdream-sdxl-20)
|
| 25 |
+
|
| 26 |
+
Credits: [View credits](https://civitai.com/?query=NewDream-SDXL%202.0)
|
| 27 |
+
|
| 28 |
+
View all models: [View Models](https://stablediffusionapi.com/models)
|
| 29 |
+
|
| 30 |
+
import requests
|
| 31 |
+
import json
|
| 32 |
+
|
| 33 |
+
url = "https://stablediffusionapi.com/api/v4/dreambooth"
|
| 34 |
+
|
| 35 |
+
payload = json.dumps({
|
| 36 |
+
"key": "your_api_key",
|
| 37 |
+
"model_id": "newdream-sdxl-20",
|
| 38 |
+
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
|
| 39 |
+
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
|
| 40 |
+
"width": "512",
|
| 41 |
+
"height": "512",
|
| 42 |
+
"samples": "1",
|
| 43 |
+
"num_inference_steps": "30",
|
| 44 |
+
"safety_checker": "no",
|
| 45 |
+
"enhance_prompt": "yes",
|
| 46 |
+
"seed": None,
|
| 47 |
+
"guidance_scale": 7.5,
|
| 48 |
+
"multi_lingual": "no",
|
| 49 |
+
"panorama": "no",
|
| 50 |
+
"self_attention": "no",
|
| 51 |
+
"upscale": "no",
|
| 52 |
+
"embeddings": "embeddings_model_id",
|
| 53 |
+
"lora": "lora_model_id",
|
| 54 |
+
"webhook": None,
|
| 55 |
+
"track_id": None
|
| 56 |
+
})
|
| 57 |
+
|
| 58 |
+
headers = {
|
| 59 |
+
'Content-Type': 'application/json'
|
| 60 |
+
}
|
| 61 |
+
|
| 62 |
+
response = requests.request("POST", url, headers=headers, data=payload)
|
| 63 |
+
|
| 64 |
+
print(response.text)
|
| 65 |
+
|
| 66 |
+
> Use this coupon code to get 25% off **DMGG0RBN**
|
model_index.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableDiffusionXLPipeline",
|
| 3 |
+
"_diffusers_version": "0.29.0",
|
| 4 |
+
"_name_or_path": "model",
|
| 5 |
+
"feature_extractor": [
|
| 6 |
+
null,
|
| 7 |
+
null
|
| 8 |
+
],
|
| 9 |
+
"force_zeros_for_empty_prompt": true,
|
| 10 |
+
"image_encoder": [
|
| 11 |
+
null,
|
| 12 |
+
null
|
| 13 |
+
],
|
| 14 |
+
"scheduler": [
|
| 15 |
+
"diffusers",
|
| 16 |
+
"EulerDiscreteScheduler"
|
| 17 |
+
],
|
| 18 |
+
"text_encoder": [
|
| 19 |
+
"transformers",
|
| 20 |
+
"CLIPTextModel"
|
| 21 |
+
],
|
| 22 |
+
"text_encoder_2": [
|
| 23 |
+
"transformers",
|
| 24 |
+
"CLIPTextModelWithProjection"
|
| 25 |
+
],
|
| 26 |
+
"tokenizer": [
|
| 27 |
+
"transformers",
|
| 28 |
+
"CLIPTokenizer"
|
| 29 |
+
],
|
| 30 |
+
"tokenizer_2": [
|
| 31 |
+
"transformers",
|
| 32 |
+
"CLIPTokenizer"
|
| 33 |
+
],
|
| 34 |
+
"unet": [
|
| 35 |
+
"diffusers",
|
| 36 |
+
"UNet2DConditionModel"
|
| 37 |
+
],
|
| 38 |
+
"vae": [
|
| 39 |
+
"diffusers",
|
| 40 |
+
"AutoencoderKL"
|
| 41 |
+
]
|
| 42 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "EulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.29.0",
|
| 4 |
+
"beta_end": 0.012,
|
| 5 |
+
"beta_schedule": "scaled_linear",
|
| 6 |
+
"beta_start": 0.00085,
|
| 7 |
+
"clip_sample": false,
|
| 8 |
+
"final_sigmas_type": "zero",
|
| 9 |
+
"interpolation_type": "linear",
|
| 10 |
+
"num_train_timesteps": 1000,
|
| 11 |
+
"prediction_type": "epsilon",
|
| 12 |
+
"rescale_betas_zero_snr": false,
|
| 13 |
+
"sample_max_value": 1.0,
|
| 14 |
+
"set_alpha_to_one": false,
|
| 15 |
+
"sigma_max": null,
|
| 16 |
+
"sigma_min": null,
|
| 17 |
+
"skip_prk_steps": true,
|
| 18 |
+
"steps_offset": 1,
|
| 19 |
+
"timestep_spacing": "leading",
|
| 20 |
+
"timestep_type": "discrete",
|
| 21 |
+
"trained_betas": null,
|
| 22 |
+
"use_karras_sigmas": false
|
| 23 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "model/text_encoder",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float16",
|
| 23 |
+
"transformers_version": "4.41.2",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57f094c002b6f50986b68a714285e72a23c17d9e1b146b078a2219397c51e37a
|
| 3 |
+
size 246144152
|
text_encoder/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:192a06f4ef7ece4acb33fc3c717790ee37b1f5d85e48e0dcac54dfea93e584a2
|
| 3 |
+
size 246185562
|
text_encoder_2/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "model/text_encoder_2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModelWithProjection"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_size": 1280,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5120,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 20,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 1280,
|
| 22 |
+
"torch_dtype": "float16",
|
| 23 |
+
"transformers_version": "4.41.2",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
text_encoder_2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a0d55a94e8508c869f35163fb6fcf34e02ea1b614d9259b47f97c562cff9575
|
| 3 |
+
size 1389382176
|
text_encoder_2/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8841d5e4c05ce74941eb536ec3835f600cc82d36763fc5f30c69d09a886158c9
|
| 3 |
+
size 1389490462
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|startoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": true,
|
| 23 |
+
"do_lower_case": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 77,
|
| 27 |
+
"pad_token": "<|endoftext|>",
|
| 28 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 29 |
+
"unk_token": "<|endoftext|>"
|
| 30 |
+
}
|
tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "!",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "!",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49406": {
|
| 13 |
+
"content": "<|startoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"49407": {
|
| 21 |
+
"content": "<|endoftext|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"bos_token": "<|startoftext|>",
|
| 30 |
+
"clean_up_tokenization_spaces": true,
|
| 31 |
+
"do_lower_case": true,
|
| 32 |
+
"eos_token": "<|endoftext|>",
|
| 33 |
+
"errors": "replace",
|
| 34 |
+
"model_max_length": 77,
|
| 35 |
+
"pad_token": "!",
|
| 36 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 37 |
+
"unk_token": "<|endoftext|>"
|
| 38 |
+
}
|
tokenizer_2/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.29.0",
|
| 4 |
+
"_name_or_path": "model/unet",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": "text_time",
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": 256,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20
|
| 13 |
+
],
|
| 14 |
+
"attention_type": "default",
|
| 15 |
+
"block_out_channels": [
|
| 16 |
+
320,
|
| 17 |
+
640,
|
| 18 |
+
1280
|
| 19 |
+
],
|
| 20 |
+
"center_input_sample": false,
|
| 21 |
+
"class_embed_type": null,
|
| 22 |
+
"class_embeddings_concat": false,
|
| 23 |
+
"conv_in_kernel": 3,
|
| 24 |
+
"conv_out_kernel": 3,
|
| 25 |
+
"cross_attention_dim": 2048,
|
| 26 |
+
"cross_attention_norm": null,
|
| 27 |
+
"down_block_types": [
|
| 28 |
+
"DownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"CrossAttnDownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"dropout": 0.0,
|
| 34 |
+
"dual_cross_attention": false,
|
| 35 |
+
"encoder_hid_dim": null,
|
| 36 |
+
"encoder_hid_dim_type": null,
|
| 37 |
+
"flip_sin_to_cos": true,
|
| 38 |
+
"freq_shift": 0,
|
| 39 |
+
"in_channels": 4,
|
| 40 |
+
"layers_per_block": 2,
|
| 41 |
+
"mid_block_only_cross_attention": null,
|
| 42 |
+
"mid_block_scale_factor": 1,
|
| 43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 44 |
+
"norm_eps": 1e-05,
|
| 45 |
+
"norm_num_groups": 32,
|
| 46 |
+
"num_attention_heads": null,
|
| 47 |
+
"num_class_embeds": null,
|
| 48 |
+
"only_cross_attention": false,
|
| 49 |
+
"out_channels": 4,
|
| 50 |
+
"projection_class_embeddings_input_dim": 2816,
|
| 51 |
+
"resnet_out_scale_factor": 1.0,
|
| 52 |
+
"resnet_skip_time_act": false,
|
| 53 |
+
"resnet_time_scale_shift": "default",
|
| 54 |
+
"reverse_transformer_layers_per_block": null,
|
| 55 |
+
"sample_size": 128,
|
| 56 |
+
"time_cond_proj_dim": null,
|
| 57 |
+
"time_embedding_act_fn": null,
|
| 58 |
+
"time_embedding_dim": null,
|
| 59 |
+
"time_embedding_type": "positional",
|
| 60 |
+
"timestep_post_act": null,
|
| 61 |
+
"transformer_layers_per_block": [
|
| 62 |
+
1,
|
| 63 |
+
2,
|
| 64 |
+
10
|
| 65 |
+
],
|
| 66 |
+
"up_block_types": [
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"UpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": false,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56913b74b493462516ce770d525cca996feef7acd44cf0cba65de667a6c1d58c
|
| 3 |
+
size 5135669022
|
unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9715fb3c6d0d81f46fbe6be46ddce05d91806aaf041504a52a44e1ec9e4f660f
|
| 3 |
+
size 5135149760
|
vae/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.29.0",
|
| 4 |
+
"_name_or_path": "model/vae",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
128,
|
| 8 |
+
256,
|
| 9 |
+
512,
|
| 10 |
+
512
|
| 11 |
+
],
|
| 12 |
+
"down_block_types": [
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D",
|
| 16 |
+
"DownEncoderBlock2D"
|
| 17 |
+
],
|
| 18 |
+
"force_upcast": true,
|
| 19 |
+
"in_channels": 3,
|
| 20 |
+
"latent_channels": 4,
|
| 21 |
+
"latents_mean": null,
|
| 22 |
+
"latents_std": null,
|
| 23 |
+
"layers_per_block": 2,
|
| 24 |
+
"norm_num_groups": 32,
|
| 25 |
+
"out_channels": 3,
|
| 26 |
+
"sample_size": 1024,
|
| 27 |
+
"scaling_factor": 0.13025,
|
| 28 |
+
"shift_factor": null,
|
| 29 |
+
"up_block_types": [
|
| 30 |
+
"UpDecoderBlock2D",
|
| 31 |
+
"UpDecoderBlock2D",
|
| 32 |
+
"UpDecoderBlock2D",
|
| 33 |
+
"UpDecoderBlock2D"
|
| 34 |
+
],
|
| 35 |
+
"use_post_quant_conv": true,
|
| 36 |
+
"use_quant_conv": true
|
| 37 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33c40ff3dc7adeb21dce76cd411d65828037efa0aa54432e3592418401cf8467
|
| 3 |
+
size 167404866
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:915b909d0eeef5985462226b2c9950ca9da42b5a6ec8c296c2e73f6419ae465c
|
| 3 |
+
size 167335342
|