Добавлены .ipynb_checkpoints и __pycache__ в .gitignore

.ipynb_checkpoints/README-checkpoint.md

@@ -1,116 +0,0 @@
----
-license: apache-2.0
-pipeline_tag: text-to-image
----
-# Work / train in progress!
-![image](./promo.png)
-
-⚡️Waifu: efficient high-resolution waifu synthesis
-
-
-waifu is a free text-to-image model that can efficiently generate images in 80 languages. Our goal is to create a small model without compromising on quality.
-
-## Core designs include:
-
-(1) [**AuraDiffusion/16ch-vae**](https://huggingface.co/AuraDiffusion/16ch-vae): A fully open source 16ch VAE. Natively trained in fp16. \
-(2) [**Linear DiT**](https://github.com/NVlabs/Sana): we use 1.6b DiT transformer with linear attention. \
-(3) [**MEXMA-SigLIP**](https://huggingface.co/visheratin/mexma-siglip): MEXMA-SigLIP is a model that combines the [MEXMA](https://huggingface.co/facebook/MEXMA) multilingual text encoder and an image encoder from the [SigLIP](https://huggingface.co/timm/ViT-SO400M-14-SigLIP-384) model. This allows us to get a high-performance CLIP model for 80 languages.. \
-(4) Other: we use Flow-Euler sampler, Adafactor-Fused optimizer and bf16 precision for training, and combine efficient caption labeling (MoonDream, CogVlM, Human, Gpt's) and danbooru tags to accelerate convergence.
-
-
-## Example
-
-```py
-import torch
-from diffusers import DiffusionPipeline
-
-from transformers import XLMRobertaTokenizerFast,XLMRobertaModel
-from diffusers import FlowMatchEulerDiscreteScheduler
-from diffusers.models import AutoencoderKL
-from diffusers import SanaTransformer2DModel
-
-pipe_id = "AiArtLab/waifu-2b"
-variant = "fp16"
-# tokenizer
-tokenizer = XLMRobertaTokenizerFast.from_pretrained(
-    pipe_id,
-    subfolder="tokenizer"
-)
-
-# text_encoder
-text_encoder = XLMRobertaModel.from_pretrained(
-    pipe_id,
-    variant=variant,
-    subfolder="text_encoder",
-    add_pooling_layer=False
-).to("cuda")
-
-# scheduler
-scheduler = FlowMatchEulerDiscreteScheduler(shift=1.0)
-
-# VAE
-vae = AutoencoderKL.from_pretrained(
-    pipe_id,
-    variant=variant,
-    subfolder="vae"
-).to("cuda")
-
-# Transformer
-transformer = SanaTransformer2DModel.from_pretrained(
-    pipe_id,
-    variant=variant,
-    subfolder="transformer"
-).to("cuda")
-
-# Pipeline
-pipeline = DiffusionPipeline.from_pretrained(
-    pipe_id,
-    tokenizer=tokenizer,
-    text_encoder=text_encoder,
-    vae=vae,
-    transformer=transformer,
-    trust_remote_code=True,
-).to("cuda")
-print(pipeline)
-
-prompt = 'аниме девушка, waifu, يبتسم جنسيا , sur le fond de la tour Eiffel'
-generator = torch.Generator(device="cuda").manual_seed(42)
-
-image = pipeline(
-    prompt = prompt,
-    negative_prompt = "",
-    generator=generator,
-)[0]
-
-for img in image:
-    img.show()
-    img.save('waifu.png')
-
-```
-
-![image](./waifu.png)
-
-## Donations
-
-We are a small GPU poor group of enthusiasts (current train budget ~$2k)
-
-Please contact with us if you may provide some GPU's on training
-
-DOGE: DEw2DR8C7BnF8GgcrfTzUjSnGkuMeJhg83
-
-![image](./1.png)
-A fluffy domestic cat with piercing green eyes sits attentively in a sunlit room filled natural light streaming through large windows, its soft fur reflecting warm hues of orange from the golden glow casting across its sleek body and delicate features
-
-## Contacts
-
-[recoilme](https://t.me/recoilme)
-
-## How to cite
-
-```bibtex
-@misc{Waifu, 
-    url    = {[https://huggingface.co/AiArtLab/waifu-2b](https://huggingface.co/AiArtLab/waifu-2b)}, 
-    title  = {waifu-2b}, 
-    author = {recoilme, muinez, femboysLover}
-}
-```

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -1,99 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "dca3239c-17d6-4284-a2cf-83237a55a7df",
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "AttributeError",
-     "evalue": "module 'diffusers_modules.local.pipeline_waifu' has no attribute 'WaifuPipeline'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[13], line 6\u001b[0m\n\u001b[1;32m      4\u001b[0m pipe_id \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m/home/recoilme/models/waifu-2b\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m      5\u001b[0m variant \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfp16\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 6\u001b[0m pipe \u001b[38;5;241m=\u001b[39m \u001b[43mDiffusionPipeline\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpipe_id\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m      8\u001b[0m \u001b[43m    \u001b[49m\u001b[43mvariant\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvariant\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m      9\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtrust_remote_code\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\n\u001b[1;32m     10\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m     11\u001b[0m \u001b[38;5;28mprint\u001b[39m(pipe)\n\u001b[1;32m     12\u001b[0m \u001b[38;5;66;03m#pipe_sd.to(\"cuda\")\u001b[39;00m\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m    112\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py:785\u001b[0m, in \u001b[0;36mDiffusionPipeline.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    780\u001b[0m \u001b[38;5;66;03m# 3. Load the pipeline class, if using custom module then load it from the hub\u001b[39;00m\n\u001b[1;32m    781\u001b[0m \u001b[38;5;66;03m# if we load from explicit class, let's use it\u001b[39;00m\n\u001b[1;32m    782\u001b[0m custom_pipeline, custom_class_name \u001b[38;5;241m=\u001b[39m _resolve_custom_pipeline_and_cls(\n\u001b[1;32m    783\u001b[0m     folder\u001b[38;5;241m=\u001b[39mcached_folder, config\u001b[38;5;241m=\u001b[39mconfig_dict, custom_pipeline\u001b[38;5;241m=\u001b[39mcustom_pipeline\n\u001b[1;32m    784\u001b[0m )\n\u001b[0;32m--> 785\u001b[0m pipeline_class \u001b[38;5;241m=\u001b[39m \u001b[43m_get_pipeline_class\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    786\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    787\u001b[0m \u001b[43m    \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    788\u001b[0m \u001b[43m    \u001b[49m\u001b[43mload_connected_pipeline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mload_connected_pipeline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    789\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcustom_pipeline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcustom_pipeline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    790\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclass_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcustom_class_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    791\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    792\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcustom_revision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    793\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    795\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m device_map \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m pipeline_class\u001b[38;5;241m.\u001b[39m_load_connected_pipes:\n\u001b[1;32m    796\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`device_map` is not yet supported for connected pipelines.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/diffusers/pipelines/pipeline_loading_utils.py:370\u001b[0m, in \u001b[0;36m_get_pipeline_class\u001b[0;34m(class_obj, config, load_connected_pipeline, custom_pipeline, repo_id, hub_revision, class_name, cache_dir, revision)\u001b[0m\n\u001b[1;32m    358\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_get_pipeline_class\u001b[39m(\n\u001b[1;32m    359\u001b[0m     class_obj,\n\u001b[1;32m    360\u001b[0m     config\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    367\u001b[0m     revision\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    368\u001b[0m ):\n\u001b[1;32m    369\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m custom_pipeline \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 370\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_get_custom_pipeline_class\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    371\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcustom_pipeline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    372\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    373\u001b[0m \u001b[43m            \u001b[49m\u001b[43mhub_revision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhub_revision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    374\u001b[0m \u001b[43m            \u001b[49m\u001b[43mclass_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclass_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    375\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    376\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    377\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    379\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m class_obj\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDiffusionPipeline\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m    380\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m class_obj\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/diffusers/pipelines/pipeline_loading_utils.py:349\u001b[0m, in \u001b[0;36m_get_custom_pipeline_class\u001b[0;34m(custom_pipeline, repo_id, hub_revision, class_name, cache_dir, revision)\u001b[0m\n\u001b[1;32m    344\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m repo_id \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m hub_revision \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    345\u001b[0m     \u001b[38;5;66;03m# if we load the pipeline code from the Hub\u001b[39;00m\n\u001b[1;32m    346\u001b[0m     \u001b[38;5;66;03m# make sure to overwrite the `revision`\u001b[39;00m\n\u001b[1;32m    347\u001b[0m     revision \u001b[38;5;241m=\u001b[39m hub_revision\n\u001b[0;32m--> 349\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mget_class_from_dynamic_module\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    350\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcustom_pipeline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    351\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmodule_file\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfile_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    352\u001b[0m \u001b[43m    \u001b[49m\u001b[43mclass_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mclass_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    353\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    354\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    355\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m    112\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/diffusers/utils/dynamic_modules_utils.py:457\u001b[0m, in \u001b[0;36mget_class_from_dynamic_module\u001b[0;34m(pretrained_model_name_or_path, module_file, class_name, cache_dir, force_download, proxies, token, revision, local_files_only, **kwargs)\u001b[0m\n\u001b[1;32m    446\u001b[0m \u001b[38;5;66;03m# And lastly we get the class inside our newly created module\u001b[39;00m\n\u001b[1;32m    447\u001b[0m final_module \u001b[38;5;241m=\u001b[39m get_cached_module_file(\n\u001b[1;32m    448\u001b[0m     pretrained_model_name_or_path,\n\u001b[1;32m    449\u001b[0m     module_file,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    455\u001b[0m     local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[1;32m    456\u001b[0m )\n\u001b[0;32m--> 457\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mget_class_in_module\u001b[49m\u001b[43m(\u001b[49m\u001b[43mclass_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfinal_module\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreplace\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.py\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.local/lib/python3.11/site-packages/diffusers/utils/dynamic_modules_utils.py:166\u001b[0m, in \u001b[0;36mget_class_in_module\u001b[0;34m(class_name, module_path)\u001b[0m\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m class_name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    165\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m find_pipeline_class(module)\n\u001b[0;32m--> 166\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mclass_name\u001b[49m\u001b[43m)\u001b[49m\n",
-      "\u001b[0;31mAttributeError\u001b[0m: module 'diffusers_modules.local.pipeline_waifu' has no attribute 'WaifuPipeline'"
-     ]
-    }
-   ],
-   "source": [
-    "import torch\n",
-    "from diffusers import DiffusionPipeline\n",
-    "\n",
-    "pipe_id = \"/home/recoilme/models/waifu-2b\"\n",
-    "variant = \"fp16\"\n",
-    "pipe = DiffusionPipeline.from_pretrained(\n",
-    "    pipe_id, \n",
-    "    variant=variant,\n",
-    "    trust_remote_code=True\n",
-    ")\n",
-    "print(pipe)\n",
-    "#pipe_sd.to(\"cuda\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b6ebc579-0eb2-4828-89d5-b40f6d5e758e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "SanaPipeline {\n",
-    "  \"_class_name\": \"SanaPipeline\",\n",
-    "  \"_diffusers_version\": \"0.32.0.dev0\",\n",
-    "  \"_name_or_path\": \"AiArtLab/waifu-2b\",\n",
-    "  \"scheduler\": [\n",
-    "    \"diffusers\",\n",
-    "    \"FlowMatchEulerDiscreteScheduler\"\n",
-    "  ],\n",
-    "  \"text_encoder\": [\n",
-    "    \"transformers\",\n",
-    "    \"XLMRobertaModel\"\n",
-    "  ],\n",
-    "  \"tokenizer\": [\n",
-    "    \"transformers\",\n",
-    "    \"XLMRobertaTokenizerFast\"\n",
-    "  ],\n",
-    "  \"transformer\": [\n",
-    "    \"diffusers\",\n",
-    "    \"SanaTransformer2DModel\"\n",
-    "  ],\n",
-    "  \"vae\": [\n",
-    "    \"diffusers\",\n",
-    "    \"AutoencoderKL\"\n",
-    "  ]\n",
-    "}\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

.ipynb_checkpoints/model_index-checkpoint.json

@@ -1,25 +0,0 @@
-{
-  "_class_name": ["pipeline_waifu", "WaifuPipeline"],
-  "_diffusers_version": "0.32.0.dev0",
-  "_name_or_path": "AiArtLab/waifu-2b",
-  "scheduler": [
-    "diffusers",
-    "FlowMatchEulerDiscreteScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "XLMRobertaModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "XLMRobertaTokenizerFast"
-  ],
-  "transformer": [
-    "diffusers",
-    "SanaTransformer2DModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}

.ipynb_checkpoints/pipeline_waifu-checkpoint.py

@@ -1,641 +0,0 @@
-# Copyright 2024 PixArt-Sigma Authors and The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import inspect
-from typing import Callable, Dict, List, Optional, Union
-
-import torch
-from diffusers.image_processor import PixArtImageProcessor
-from diffusers.utils.torch_utils import randn_tensor
-from diffusers import DiffusionPipeline
-from transformers import XLMRobertaTokenizerFast,XLMRobertaModel
-from diffusers import SanaTransformer2DModel
-from diffusers.models import AutoencoderKL
-from diffusers import FlowMatchEulerDiscreteScheduler
-from typing import List, Union
-import numpy as np
-import PIL.Image
-
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from diffusers import WaifuPipeline
-
-        >>> pipe = WaifuPipeline.from_pretrained(
-        ...     "AiArtLab/waifu-2b"
-        ... )
-        >>> pipe.to("cuda")
-
-        >>> image = pipe(prompt='a cyberpunk cat with a neon sign that says "Sana"')[0]
-        >>> image[0].save("output.png")
-        ```
-"""
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
-def retrieve_timesteps(
-    scheduler,
-    num_inference_steps: Optional[int] = None,
-    device: Optional[Union[str, torch.device]] = None,
-    timesteps: Optional[List[int]] = None,
-    sigmas: Optional[List[float]] = None,
-    **kwargs,
-):
-    r"""
-    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
-    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
-
-    Args:
-        scheduler (`SchedulerMixin`):
-            The scheduler to get timesteps from.
-        num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
-            must be `None`.
-        device (`str` or `torch.device`, *optional*):
-            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
-            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
-            `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
-            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
-            `num_inference_steps` and `timesteps` must be `None`.
-
-    Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
-        second element is the number of inference steps.
-    """
-    if timesteps is not None and sigmas is not None:
-        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
-    if timesteps is not None:
-        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accepts_timesteps:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" timestep schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    elif sigmas is not None:
-        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accept_sigmas:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" sigmas schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    else:
-        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-    return timesteps, num_inference_steps
-
-
-class WaifuPipeline(DiffusionPipeline):
-    r"""
-    Pipeline for text-to-image generation using [Sana](https://huggingface.co/papers/2410.10629).
-    """
-
-    model_cpu_offload_seq = "text_encoder->transformer->vae"
-    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]
-
-    def __init__(
-        self,
-        tokenizer: XLMRobertaTokenizerFast,
-        text_encoder: XLMRobertaModel,
-        vae: AutoencoderKL,
-        transformer: SanaTransformer2DModel,
-        scheduler: FlowMatchEulerDiscreteScheduler,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler
-        )
-
-        self.vae_scale_factor = (
-            8
-        )
-        self.image_processor = PixArtImageProcessor(vae_scale_factor=self.vae_scale_factor)
-
-    def encode_prompt(
-        self,
-        prompt: Union[str, List[str]],
-        do_classifier_free_guidance: bool = True,
-        negative_prompt: str = "",
-        num_images_per_prompt: int = 1,
-        device: Optional[torch.device] = None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        prompt_attention_mask: Optional[torch.Tensor] = None,
-        negative_prompt_attention_mask: Optional[torch.Tensor] = None,
-        max_sequence_length: int = 512,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt not to guide the image generation. If not defined, one has to pass `negative_prompt_embeds`
-                instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). For
-                PixArt-Alpha, this should be "".
-            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
-                whether to use classifier free guidance or not
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                number of images that should be generated per prompt
-            device: (`torch.device`, *optional*):
-                torch device to place the resulting embeddings on
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. For Sana, it's should be the embeddings of the "" string.
-            max_sequence_length (`int`, defaults to 512): Maximum sequence length to use for the prompt.
-        """
-
-        if device is None:
-            device = self._execution_device
-
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        if self.tokenizer is not None:
-            self.tokenizer.padding_side = "right"
-
-        max_length = max_sequence_length
-        select_index = [0] + list(range(-max_length + 1, 0))
-
-        if prompt_embeds is None:
-            prompt = self._text_preprocessing(prompt)
-
-            max_length_all = max_length
-
-            text_inputs = self.tokenizer(
-                prompt,
-                padding="max_length",
-                max_length=max_length_all,
-                truncation=True,
-                add_special_tokens=True,
-                return_tensors="pt",
-            )
-            text_input_ids = text_inputs.input_ids
-
-            prompt_attention_mask = text_inputs.attention_mask
-            prompt_attention_mask = prompt_attention_mask.to(device)
-
-            prompt_embeds = self.text_encoder(text_input_ids.to(device), attention_mask=prompt_attention_mask)
-            prompt_embeds = prompt_embeds[0][:, select_index]
-            prompt_attention_mask = prompt_attention_mask[:, select_index]
-
-        if self.transformer is not None:
-            dtype = self.transformer.dtype
-        elif self.text_encoder is not None:
-            dtype = self.text_encoder.dtype
-        else:
-            dtype = None
-
-        prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)
-
-        bs_embed, seq_len, _ = prompt_embeds.shape
-        # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
-        prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
-        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-        prompt_attention_mask = prompt_attention_mask.view(bs_embed, -1)
-        prompt_attention_mask = prompt_attention_mask.repeat(num_images_per_prompt, 1)
-
-        # get unconditional embeddings for classifier free guidance
-        if do_classifier_free_guidance and negative_prompt_embeds is None:
-            #print("do_classifier_free_guidance and negative_prompt_embeds is None")
-            uncond_tokens = [negative_prompt] * batch_size if isinstance(negative_prompt, str) else negative_prompt
-            uncond_tokens = self._text_preprocessing(uncond_tokens)
-            max_length = prompt_embeds.shape[1]
-            uncond_input = self.tokenizer(
-                uncond_tokens,
-                padding="max_length",
-                max_length=max_length,
-                truncation=True,
-                return_attention_mask=True,
-                add_special_tokens=True,
-                return_tensors="pt",
-            )
-            negative_prompt_attention_mask = uncond_input.attention_mask
-            negative_prompt_attention_mask = negative_prompt_attention_mask.to(device)
-
-            negative_prompt_embeds = self.text_encoder(
-                uncond_input.input_ids.to(device), attention_mask=negative_prompt_attention_mask
-            )
-            negative_prompt_embeds = negative_prompt_embeds[0]
-
-        if do_classifier_free_guidance:
-            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-            seq_len = negative_prompt_embeds.shape[1]
-
-            negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype, device=device)
-
-            negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
-
-            negative_prompt_attention_mask = negative_prompt_attention_mask.view(bs_embed, -1)
-            negative_prompt_attention_mask = negative_prompt_attention_mask.repeat(num_images_per_prompt, 1)
-        else:
-            negative_prompt_embeds = None
-            negative_prompt_attention_mask = None
-
-        return prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        height,
-        width,
-        callback_on_step_end_tensor_inputs=None,
-        negative_prompt=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        prompt_attention_mask=None,
-        negative_prompt_attention_mask=None,
-    ):
-        if height % 64 != 0 or width % 64 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 64 but are {height} and {width}.")
-
-        if callback_on_step_end_tensor_inputs is not None and not all(
-            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
-        ):
-            raise ValueError(
-                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
-            )
-
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and prompt_attention_mask is None:
-            raise ValueError("Must provide `prompt_attention_mask` when specifying `prompt_embeds`.")
-
-        if negative_prompt_embeds is not None and negative_prompt_attention_mask is None:
-            raise ValueError("Must provide `negative_prompt_attention_mask` when specifying `negative_prompt_embeds`.")
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-            if prompt_attention_mask.shape != negative_prompt_attention_mask.shape:
-                raise ValueError(
-                    "`prompt_attention_mask` and `negative_prompt_attention_mask` must have the same shape when passed directly, but"
-                    f" got: `prompt_attention_mask` {prompt_attention_mask.shape} != `negative_prompt_attention_mask`"
-                    f" {negative_prompt_attention_mask.shape}."
-                )
-
-    def _text_preprocessing(self, text):
-
-        if not isinstance(text, (tuple, list)):
-            text = [text]
-
-        def process(text: str):
-            text = text.lower().strip()
-            return text
-
-        return [process(t) for t in text]
-
-    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        if latents is not None:
-            return latents.to(device=device, dtype=dtype)
-
-        shape = (
-            batch_size,
-            num_channels_latents,
-            int(height) // self.vae_scale_factor,
-            int(width) // self.vae_scale_factor,
-        )
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        return latents
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def do_classifier_free_guidance(self):
-        return self._guidance_scale > 1.0
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @property
-    def interrupt(self):
-        return self._interrupt
-
-    @torch.no_grad()
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        negative_prompt: str = "",
-        num_inference_steps: int = 20,
-        timesteps: List[int] = None,
-        sigmas: List[float] = None,
-        guidance_scale: float = 4.5,
-        num_images_per_prompt: Optional[int] = 1,
-        height: int = 512,
-        width: int = 512,
-        eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.Tensor] = None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        prompt_attention_mask: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_attention_mask: Optional[torch.Tensor] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = False,
-        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        max_sequence_length: int = 512,
-    ) -> Union[List[PIL.Image.Image], np.ndarray]:
-        """
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            num_inference_steps (`int`, *optional*, defaults to 20):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            timesteps (`List[int]`, *optional*):
-                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
-                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
-                passed will be used. Must be in descending order.
-            sigmas (`List[float]`, *optional*):
-                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
-                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
-                will be used.
-            guidance_scale (`float`, *optional*, defaults to 4.5):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            height (`int`, *optional*, defaults to self.unet.config.sample_size):
-                The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size):
-                The width in pixels of the generated image.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.Tensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            prompt_attention_mask (`torch.Tensor`, *optional*): Pre-generated attention mask for text embeddings.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not
-                provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
-            negative_prompt_attention_mask (`torch.Tensor`, *optional*):
-                Pre-generated attention mask for negative text embeddings.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
-            callback_on_step_end (`Callable`, *optional*):
-                A function that calls at the end of each denoising steps during the inference. The function is called
-                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
-                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
-                `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-            max_sequence_length (`int` defaults to `512`):
-                Maximum sequence length to use with the `prompt`.
-
-        Examples:
-
-        Returns:
-            Union[List[PIL.Image.Image], np.ndarray] is returned,
-                otherwise a `tuple` is returned where the first element is a list with the generated images
-        """
-
-#       if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
-#           callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
-
-        # 1. Check inputs. Raise error if not correct
-
-        self.check_inputs(
-            prompt,
-            height,
-            width,
-            callback_on_step_end_tensor_inputs,
-            negative_prompt,
-            prompt_embeds,
-            negative_prompt_embeds,
-            prompt_attention_mask,
-            negative_prompt_attention_mask,
-        )
-
-        self._guidance_scale = guidance_scale
-        self._interrupt = False
-
-        # 2. Default height and width to transformer
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        # 3. Encode input prompt
-        (
-            prompt_embeds,
-            prompt_attention_mask,
-            negative_prompt_embeds,
-            negative_prompt_attention_mask,
-        ) = self.encode_prompt(
-            prompt,
-            self.do_classifier_free_guidance,
-            negative_prompt=negative_prompt,
-            num_images_per_prompt=num_images_per_prompt,
-            device=device,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            prompt_attention_mask=prompt_attention_mask,
-            negative_prompt_attention_mask=negative_prompt_attention_mask,
-            max_sequence_length=max_sequence_length,
-        )
-        if self.do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-            prompt_attention_mask = torch.cat([negative_prompt_attention_mask, prompt_attention_mask], dim=0)
-
-        # 4. Prepare timesteps
-        timesteps, num_inference_steps = retrieve_timesteps(
-            self.scheduler, num_inference_steps, device, timesteps, sigmas
-        )
-
-        # 5. Prepare latents.
-        latent_channels = self.transformer.config.in_channels
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            latent_channels,
-            height,
-            width,
-            torch.float32,
-            device,
-            generator,
-            latents,
-        )
-
-        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 7. Denoising loop
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-        self._num_timesteps = len(timesteps)
-
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-
-                latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
-                latent_model_input = latent_model_input.to(prompt_embeds.dtype)
-
-                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-                timestep = t.expand(latent_model_input.shape[0]).to(latents.dtype)
-
-                # predict noise model_output
-                noise_pred = self.transformer(
-                    latent_model_input,
-                    encoder_hidden_states=prompt_embeds,
-                    encoder_attention_mask=prompt_attention_mask,
-                    timestep=timestep,
-                    return_dict=False,
-                )[0]
-                noise_pred = noise_pred.float()
-
-                # perform guidance
-                if self.do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                # learned sigma
-                if self.transformer.config.out_channels // 2 == latent_channels:
-                    noise_pred = noise_pred.chunk(2, dim=1)[0]
-                else:
-                    noise_pred = noise_pred
-
-                # compute previous image: x_t -> x_t-1
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-
-                if callback_on_step_end is not None:
-                    callback_kwargs = {}
-                    for k in callback_on_step_end_tensor_inputs:
-                        callback_kwargs[k] = locals()[k]
-                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
-
-                    latents = callback_outputs.pop("latents", latents)
-                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
-                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-
-        if output_type == "latent":
-            image = latents
-        else:
-            latents = latents.to(self.vae.dtype)
-            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
-
-        if not output_type == "latent":
-            image = self.image_processor.postprocess(image, output_type=output_type)
-            #image = numpy_to_pil(image)
-
-        # Offload all models
-        #print("Offload all models 4")
-        self.maybe_free_model_hooks()
-
-        if not return_dict:
-            return (image,)
-
-        return Union[List[PIL.Image.Image], np.ndarray]