ldm_cc3m_random_noise_30

README.md

@@ -0,0 +1,101 @@
+---
+tags:
+- DiffusionNoise
+license: "apache-2.0"
+datasets:
+- CC3M
+metrics:
+- FID
+- IS 
+base_model: "DiffusionNoise/ldm_cc3m_random_noise_30"
+---
+
+# ldm_cc3m_random_noise_30 Model Card
+
+This repository contains diffusion models (DMs) developed for exploring the impact of slight corruption in pre-training data on generative performance. 
+By introducing controlled condition corruption, we observed significant improvements in the quality, diversity, and fidelity of generated outputs across various DM architectures. 
+This **ldm_cc3m_random_noise_30** is trained on CC3M.
+
+The models and resources provided here aim to advance research in robust generative modeling and inspire new approaches to data-centric AI development.
+Explore the models at https://huggingface.co/DiffusionNoise.
+
+**Note**: Since the models are trained on CC3M, which is a relatively small dataset, they might be incapable of follow complex prompts.
+
+## Usage  
+
+Currently, we only support a custon diffusers version. 
+You need to install the diffusers from here: https://github.com/Hhhhhhao/diffusers.
+
+Install
+```
+git clone https://github.com/Hhhhhhao/diffusers.git
+cd diffusers
+pip install -e ./
+
+or 
+
+pip install git+https://github.com/Hhhhhhao/diffusers.git
+```
+
+Use with (Custom) Diffusers
+```
+from diffusers.pipelines.latent_diffusion.pipeline_latent_diffusion import LDMTextToImagePipeline
+from diffusers DPMSolverMultistepScheduler
+
+# load model
+pipeline = LDMTextToImagePipeline.from_pretrained('DiffusionNoise/ldm_cc3m_random_noise_30')    
+# use DPM scheduler for faster inference
+pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
+# use float 16
+pipeline = pipeline.to('cuda')
+pipeline = pipeline.to(torch.float16)
+
+# inference 
+prompt = 'A photograph of a modern kitchen with appliances'
+batch_size = 1
+num_inference_steps=25
+guidance_scale=2.5
+images = pipeline([prompt] * batch_size, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale).images
+
+images[0].save("img.png")
+```
+
+More comprehensive usage scripts can be found here: https://github.com/Hhhhhhao/DiffusionNoise
+
+
+### Direct Use 
+
+The model is intended for research purposes only. Possible research areas and tasks include:
+* Safe deployment of models which have the potential to generate harmful content.
+* Probing and understanding the limitations and biases of generative models.
+* Generation of artworks and use in design and other artistic processes.
+* Applications in educational or creative tools.
+* Research on generative models.
+* Excluded uses are described below.
+
+### Misuse, Malicious Use, and Out-of-Scope Use
+
+The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
+
+The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
+
+Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
+* Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
+* Intentionally promoting or propagating discriminatory content or harmful stereotypes.
+* Impersonating individuals without their consent.
+* Sexual content without consent of the people who might see it.
+* Mis- and disinformation
+* Representations of egregious violence and gore
+* Sharing of copyrighted or licensed material in violation of its terms of use.
+* Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
+
+##  Citation
+```
+@article{chen2024slight,
+  title={Slight Corruption in Pre-training Data Makes Better Diffusion Models},
+  author={Chen, Hao and Han, Yujin and Misra, Diganta and Li, Xiang and Hu, Kai and Zou, Difan and Sugiyama, Masashi and Wang, Jindong and Raj, Bhiksha},
+  booktitle={Neural Information Processing Systems (NeurIPS)},
+  year={2024}
+}
+```
+

bert/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

bert/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3d803e47c9e598e14a230a4149dde79f48db19f96f9bbbe105333da944837a
+size 437951328

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "LDMTextToImagePipeline",
+  "_diffusers_version": "0.27.0.dev0",
+  "bert": [
+    "transformers",
+    "BertModel"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "tokenizer": [
+    "transformers",
+    "BertTokenizerFast"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vqvae": [
+    "diffusers",
+    "VQModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,1020 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.27.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": [
+    0.0008500000112690032,
+    0.0008546986500732601,
+    0.0008594102691859007,
+    0.0008641348103992641,
+    0.0008688723319210112,
+    0.0008736227755434811,
+    0.0008783861994743347,
+    0.0008831625455059111,
+    0.0008879518718458712,
+    0.0008927541202865541,
+    0.0008975693490356207,
+    0.0009023974998854101,
+    0.0009072386310435832,
+    0.000912092684302479,
+    0.0009169597178697586,
+    0.000921839673537761,
+    0.000926732609514147,
+    0.0009316384675912559,
+    0.0009365573059767485,
+    0.0009414890664629638,
+    0.0009464338072575629,
+    0.0009513914701528847,
+    0.0009563620551489294,
+    0.0009613456786610186,
+    0.0009663421660661697,
+    0.0009713516337797046,
+    0.0009763740818016231,
+    0.0009814094519242644,
+    0.0009864578023552895,
+    0.0009915190748870373,
+    0.0009965932695195079,
+    0.0010016805026680231,
+    0.0010067806579172611,
+    0.001011893735267222,
+    0.0010170197347179055,
+    0.0010221587726846337,
+    0.001027310616336763,
+    0.0010324756149202585,
+    0.001037653419189155,
+    0.0010428441455587745,
+    0.0010480479104444385,
+    0.0010532645974308252,
+    0.0010584942065179348,
+    0.001063736854121089,
+    0.001068992423824966,
+    0.0010742609156295657,
+    0.0010795423295348883,
+    0.0010848367819562554,
+    0.0010901440400630236,
+    0.0010954643366858363,
+    0.0011007976718246937,
+    0.001106143812648952,
+    0.001111502991989255,
+    0.0011168750934302807,
+    0.0011222601169720292,
+    0.0011276581790298223,
+    0.0011330691631883383,
+    0.001138493069447577,
+    0.0011439298978075385,
+    0.0011493796482682228,
+    0.0011548424372449517,
+    0.0011603181483224034,
+    0.001165806781500578,
+    0.001171308453194797,
+    0.0011768229305744171,
+    0.0011823504464700818,
+    0.0011878910008817911,
+    0.0011934443609789014,
+    0.0011990107595920563,
+    0.001204590080305934,
+    0.0012101823231205344,
+    0.0012157876044511795,
+    0.0012214056914672256,
+    0.0012270368169993162,
+    0.0012326808646321297,
+    0.0012383379507809877,
+    0.0012440079590305686,
+    0.0012496908893808722,
+    0.0012553867418318987,
+    0.001261095516383648,
+    0.0012668173294514418,
+    0.0012725520646199584,
+    0.0012782997218891978,
+    0.00128406030125916,
+    0.0012898339191451669,
+    0.0012956204591318965,
+    0.001301419921219349,
+    0.001307232421822846,
+    0.001313057728111744,
+    0.0013188960729166865,
+    0.001324747339822352,
+    0.001330611645244062,
+    0.0013364888727664948,
+    0.0013423789059743285,
+    0.0013482820941135287,
+    0.00135419808793813,
+    0.0013601271202787757,
+    0.0013660690747201443,
+    0.0013720239512622356,
+    0.0013779917499050498,
+    0.0013839725870639086,
+    0.0013899663463234901,
+    0.0013959730276837945,
+    0.0014019926311448216,
+    0.0014080252731218934,
+    0.001414070837199688,
+    0.0014201293233782053,
+    0.0014262007316574454,
+    0.0014322851784527302,
+    0.0014383825473487377,
+    0.001444492838345468,
+    0.0014506160514429212,
+    0.001456752303056419,
+    0.0014629014767706394,
+    0.0014690635725855827,
+    0.0014752385905012488,
+    0.0014814266469329596,
+    0.001487627625465393,
+    0.0014938415260985494,
+    0.0015000683488324285,
+    0.0015063082100823522,
+    0.0015125608770176768,
+    0.001518826698884368,
+    0.00152510532643646,
+    0.0015313969925045967,
+    0.0015377014642581344,
+    0.0015440189745277166,
+    0.0015503495233133435,
+    0.0015566928777843714,
+    0.0015630492707714438,
+    0.001569418585859239,
+    0.001575800939463079,
+    0.0015821960987523198,
+    0.0015886042965576053,
+    0.0015950254164636135,
+    0.0016014594584703445,
+    0.0016079065389931202,
+    0.0016143665416166186,
+    0.0016208394663408399,
+    0.0016273253131657839,
+    0.0016338241985067725,
+    0.0016403358895331621,
+    0.0016468606190755963,
+    0.0016533983871340752,
+    0.001659948960877955,
+    0.0016665125731378794,
+    0.0016730891074985266,
+    0.0016796785639598966,
+    0.0016862810589373112,
+    0.0016928964760154486,
+    0.0016995248151943088,
+    0.0017061660764738917,
+    0.0017128202598541975,
+    0.0017194874817505479,
+    0.001726167625747621,
+    0.001732860691845417,
+    0.0017395667964592576,
+    0.001746285823173821,
+    0.0017530177719891071,
+    0.001759762642905116,
+    0.0017665204359218478,
+    0.0017732912674546242,
+    0.0017800750210881233,
+    0.0017868716968223453,
+    0.0017936814110726118,
+    0.0018005040474236012,
+    0.0018073396058753133,
+    0.0018141880864277482,
+    0.001821049489080906,
+    0.0018279239302501082,
+    0.0018348112935200334,
+    0.0018417115788906813,
+    0.0018486249027773738,
+    0.0018555510323494673,
+    0.0018624902004376054,
+    0.001869442407041788,
+    0.0018764074193313718,
+    0.001883385470137,
+    0.0018903764430433512,
+    0.001897380338050425,
+    0.0019043971551582217,
+    0.001911427010782063,
+    0.001918469788506627,
+    0.001925525488331914,
+    0.0019325942266732454,
+    0.0019396757706999779,
+    0.001946770353242755,
+    0.0019538779743015766,
+    0.0019609984010457993,
+    0.0019681318663060665,
+    0.0019752781372517347,
+    0.0019824374467134476,
+    0.001989609794691205,
+    0.0019967949483543634,
+    0.0020039931405335665,
+    0.002011204371228814,
+    0.0020184284076094627,
+    0.002025665482506156,
+    0.00203291536308825,
+    0.002040178282186389,
+    0.0020474542398005724,
+    0.002054743003100157,
+    0.002062044804915786,
+    0.0020693596452474594,
+    0.002076687291264534,
+    0.002084027975797653,
+    0.0020913814660161734,
+    0.002098747994750738,
+    0.0021061275620013475,
+    0.002113519934937358,
+    0.002120925346389413,
+    0.0021283437963575125,
+    0.002135775052011013,
+    0.002143219346180558,
+    0.0021506764460355043,
+    0.002158146584406495,
+    0.0021656297612935305,
+    0.002173125743865967,
+    0.0021806347649544477,
+    0.0021881568245589733,
+    0.0021956916898489,
+    0.002203239593654871,
+    0.002210800303146243,
+    0.00221837405115366,
+    0.002225960837677121,
+    0.0022335604298859835,
+    0.0022411730606108904,
+    0.002248798729851842,
+    0.0022564372047781944,
+    0.0022640887182205915,
+    0.0022717530373483896,
+    0.0022794303949922323,
+    0.0022871207911521196,
+    0.002294823992997408,
+    0.002302540233358741,
+    0.0023102692794054747,
+    0.002318011596798897,
+    0.0023257664870470762,
+    0.002333534648641944,
+    0.0023413156159222126,
+    0.0023491093888878822,
+    0.00235691643320024,
+    0.002364736283197999,
+    0.002372568938881159,
+    0.0023804146330803633,
+    0.0023882733657956123,
+    0.0023961449041962624,
+    0.002404029481112957,
+    0.0024119270965456963,
+    0.0024198375176638365,
+    0.0024277609772980213,
+    0.0024356974754482508,
+    0.002443646779283881,
+    0.0024516091216355562,
+    0.0024595842696726322,
+    0.002467572456225753,
+    0.002475573681294918,
+    0.0024835877120494843,
+    0.002491614781320095,
+    0.002499654656276107,
+    0.0025077075697481632,
+    0.0025157735217362642,
+    0.002523852279409766,
+    0.0025319440755993128,
+    0.002540048910304904,
+    0.002548166550695896,
+    0.002556297229602933,
+    0.0025644409470260143,
+    0.0025725974701344967,
+    0.0025807670317590237,
+    0.0025889493990689516,
+    0.002597144804894924,
+    0.0026053530164062977,
+    0.0026135744992643595,
+    0.0026218087878078222,
+    0.002630055882036686,
+    0.0026383160147815943,
+    0.0026465891860425472,
+    0.002654875162988901,
+    0.0026631741784512997,
+    0.002671486232429743,
+    0.002679811092093587,
+    0.0026881489902734756,
+    0.0026964996941387653,
+    0.0027048634365200996,
+    0.0027132402174174786,
+    0.0027216298040002584,
+    0.002730032429099083,
+    0.002738448092713952,
+    0.002746876562014222,
+    0.002755318069830537,
+    0.002763772616162896,
+    0.0027722399681806564,
+    0.0027807201258838177,
+    0.002789213554933667,
+    0.0027977197896689177,
+    0.002806238830089569,
+    0.002814770909026265,
+    0.002823316026479006,
+    0.002831874182447791,
+    0.0028404451441019773,
+    0.0028490289114415646,
+    0.00285762595012784,
+    0.0028662357944995165,
+    0.002874858444556594,
+    0.002883494133129716,
+    0.0028921428602188826,
+    0.002900804625824094,
+    0.002909479197114706,
+    0.0029181665740907192,
+    0.0029268672224134207,
+    0.002935580676421523,
+    0.0029443069361150265,
+    0.0029530462343245745,
+    0.002961798571050167,
+    0.0029705639462918043,
+    0.0029793421272188425,
+    0.0029881331138312817,
+    0.002996937371790409,
+    0.0030057544354349375,
+    0.003014584304764867,
+    0.003023427212610841,
+    0.0030322831589728594,
+    0.0030411521438509226,
+    0.0030500339344143867,
+    0.003058928530663252,
+    0.0030678363982588053,
+    0.003076756838709116,
+    0.003085690550506115,
+    0.003094637067988515,
+    0.0031035966239869595,
+    0.003112568985670805,
+    0.003121554385870695,
+    0.00313055282458663,
+    0.0031395640689879656,
+    0.003148588351905346,
+    0.003157625673338771,
+    0.0031666758004575968,
+    0.0031757389660924673,
+    0.003184814937412739,
+    0.003193903947249055,
+    0.0032030059956014156,
+    0.0032121208496391773,
+    0.0032212487421929836,
+    0.003230389440432191,
+    0.0032395434100180864,
+    0.0032487099524587393,
+    0.0032578897662460804,
+    0.0032670823857188225,
+    0.0032762878108769655,
+    0.003285506507381797,
+    0.003294738009572029,
+    0.0033039823174476624,
+    0.00331323966383934,
+    0.0033225100487470627,
+    0.003331793239340186,
+    0.003341089468449354,
+    0.003350398736074567,
+    0.0033597208093851805,
+    0.0033690559212118387,
+    0.0033784040715545416,
+    0.0033877650275826454,
+    0.00339713878929615,
+    0.0034065258223563433,
+    0.0034159256611019373,
+    0.0034253383055329323,
+    0.0034347642213106155,
+    0.003444202709943056,
+    0.003453654469922185,
+    0.0034631190355867147,
+    0.003472596639767289,
+    0.0034820870496332645,
+    0.0034915904980152845,
+    0.003501106984913349,
+    0.0035106362774968147,
+    0.003520178608596325,
+    0.003529733745381236,
+    0.003539301920682192,
+    0.0035488831344991922,
+    0.0035584773868322372,
+    0.0035680842120200396,
+    0.00357770430855453,
+    0.0035873372107744217,
+    0.003596983151510358,
+    0.0036066421307623386,
+    0.0036163139156997204,
+    0.003625998506322503,
+    0.003635696368291974,
+    0.003645407035946846,
+    0.003655130509287119,
+    0.00366486725397408,
+    0.0036746165715157986,
+    0.0036843791604042053,
+    0.003694154554978013,
+    0.0037039429880678654,
+    0.0037137442268431187,
+    0.0037235585041344166,
+    0.0037333855871111155,
+    0.0037432259414345026,
+    0.003753078868612647,
+    0.0037629450671374798,
+    0.0037728240713477135,
+    0.0037827161140739918,
+    0.003792620962485671,
+    0.003802538849413395,
+    0.0038124697748571634,
+    0.003822413505986333,
+    0.003832370275631547,
+    0.003842339850962162,
+    0.0038523224648088217,
+    0.003862318117171526,
+    0.003872326575219631,
+    0.003882348071783781,
+    0.003892382374033332,
+    0.003902429947629571,
+    0.003912490326911211,
+    0.003922563511878252,
+    0.003932649735361338,
+    0.003942748997360468,
+    0.0039528608322143555,
+    0.003962986171245575,
+    0.003973124083131552,
+    0.003983275033533573,
+    0.003993439022451639,
+    0.00400361604988575,
+    0.004013805650174618,
+    0.004024008754640818,
+    0.004034224431961775,
+    0.004044453147798777,
+    0.004054694902151823,
+    0.004064949229359627,
+    0.004075217060744762,
+    0.004085497464984655,
+    0.004095790907740593,
+    0.004106097389012575,
+    0.004116416443139315,
+    0.004126749001443386,
+    0.004137094132602215,
+    0.004147452302277088,
+    0.004157823510468006,
+    0.004168207757174969,
+    0.004178604576736689,
+    0.004189014434814453,
+    0.0041994377970695496,
+    0.004209873732179403,
+    0.004220322240144014,
+    0.004230784252285957,
+    0.004241258837282658,
+    0.0042517464607954025,
+    0.004262247122824192,
+    0.004272760823369026,
+    0.004283287562429905,
+    0.004293826874345541,
+    0.004304379690438509,
+    0.004314945079386234,
+    0.004325523506850004,
+    0.004336114507168531,
+    0.0043467190116643906,
+    0.004357336089015007,
+    0.004367966204881668,
+    0.004378609359264374,
+    0.004389265552163124,
+    0.004399934317916632,
+    0.004410616587847471,
+    0.004421311430633068,
+    0.0044320193119347095,
+    0.004442740231752396,
+    0.004453473724424839,
+    0.004464220721274614,
+    0.004474980290979147,
+    0.004485752899199724,
+    0.004496538545936346,
+    0.0045073372311890125,
+    0.004518148489296436,
+    0.004528972785919905,
+    0.004539810586720705,
+    0.004550660494714975,
+    0.004561523906886578,
+    0.0045724003575742245,
+    0.004583289381116629,
+    0.0045941914431750774,
+    0.004605106543749571,
+    0.004616034682840109,
+    0.0046269758604466915,
+    0.0046379296109080315,
+    0.004648896399885416,
+    0.004659876227378845,
+    0.004670869093388319,
+    0.004681874997913837,
+    0.004692893475294113,
+    0.004703925456851721,
+    0.004714970011264086,
+    0.004726027604192495,
+    0.004737097769975662,
+    0.004748181439936161,
+    0.004759277682751417,
+    0.004770387429744005,
+    0.004781509283930063,
+    0.004792644642293453,
+    0.004803793039172888,
+    0.00481495400890708,
+    0.0048261284828186035,
+    0.004837315529584885,
+    0.004848515149205923,
+    0.0048597282730042934,
+    0.004870954435318708,
+    0.004882193170487881,
+    0.004893444944173098,
+    0.004904709756374359,
+    0.004915987607091665,
+    0.004927278030663729,
+    0.004938581492751837,
+    0.004949898459017277,
+    0.004961227998137474,
+    0.004972570110112429,
+    0.004983925726264715,
+    0.004995293915271759,
+    0.0050066751427948475,
+    0.005018069874495268,
+    0.005029476713389158,
+    0.0050408970564603806,
+    0.00505232997238636,
+    0.005063776392489672,
+    0.0050752353854477406,
+    0.005086707416921854,
+    0.005098192021250725,
+    0.0051096901297569275,
+    0.0051212008111178875,
+    0.005132724530994892,
+    0.005144261289387941,
+    0.005155811086297035,
+    0.005167373921722174,
+    0.0051789493300020695,
+    0.00519053777679801,
+    0.005202139262109995,
+    0.0052137537859380245,
+    0.005225381348282099,
+    0.00523702148348093,
+    0.005248675122857094,
+    0.005260341335088015,
+    0.005272020120173693,
+    0.005283712409436703,
+    0.005295417737215757,
+    0.005307135637849569,
+    0.005318866576999426,
+    0.005330610554665327,
+    0.005342367570847273,
+    0.005354137159883976,
+    0.005365920253098011,
+    0.005377715919166803,
+    0.00538952462375164,
+    0.005401346366852522,
+    0.005413180682808161,
+    0.005425028502941132,
+    0.00543688889592886,
+    0.0054487623274326324,
+    0.00546064879745245,
+    0.005472548305988312,
+    0.005484460387378931,
+    0.005496385972946882,
+    0.005508324131369591,
+    0.005520275328308344,
+    0.005532239098101854,
+    0.005544216372072697,
+    0.005556206218898296,
+    0.005568209104239941,
+    0.0055802250280976295,
+    0.005592253990471363,
+    0.005604295991361141,
+    0.005616350565105677,
+    0.005628418643027544,
+    0.005640499293804169,
+    0.005652592517435551,
+    0.005664699245244265,
+    0.005676819011569023,
+    0.005688951350748539,
+    0.005701096728444099,
+    0.0057132551446557045,
+    0.005725426599383354,
+    0.005737610626965761,
+    0.0057498081587255,
+    0.005762018263339996,
+    0.005774241406470537,
+    0.005786477588117123,
+    0.005798726342618465,
+    0.00581098860129714,
+    0.005823263432830572,
+    0.005835551302880049,
+    0.00584785221144557,
+    0.0058601656928658485,
+    0.005872492678463459,
+    0.005884832236915827,
+    0.005897184833884239,
+    0.005909550469368696,
+    0.005921929143369198,
+    0.005934320390224457,
+    0.005946725141257048,
+    0.005959142465144396,
+    0.005971572827547789,
+    0.005984016228467226,
+    0.005996472202241421,
+    0.006008941680192947,
+    0.006021423730999231,
+    0.00603391882032156,
+    0.006046426948159933,
+    0.006058948114514351,
+    0.006071481853723526,
+    0.006084028631448746,
+    0.00609658844769001,
+    0.006109161302447319,
+    0.006121747195720673,
+    0.006134346127510071,
+    0.006146957632154226,
+    0.006159582175314426,
+    0.006172219756990671,
+    0.0061848703771829605,
+    0.006197533570230007,
+    0.006210210267454386,
+    0.006222899537533522,
+    0.006235601846128702,
+    0.006248317193239927,
+    0.00626104511320591,
+    0.006273786537349224,
+    0.006286540534347296,
+    0.006299307569861412,
+    0.006312087643891573,
+    0.0063248807564377785,
+    0.006337686441838741,
+    0.006350505631417036,
+    0.006363337393850088,
+    0.006376182194799185,
+    0.006389040034264326,
+    0.006401910446584225,
+    0.006414794363081455,
+    0.006427690852433443,
+    0.0064406003803014755,
+    0.006453522946685553,
+    0.006466458085924387,
+    0.006479406729340553,
+    0.006492367945611477,
+    0.006505342200398445,
+    0.006518329493701458,
+    0.0065313298255205154,
+    0.00654434273019433,
+    0.00655736867338419,
+    0.006570408120751381,
+    0.0065834601409733295,
+    0.0065965247340500355,
+    0.006609602831304073,
+    0.0066226935014128685,
+    0.006635797210037708,
+    0.006648913957178593,
+    0.006662043742835522,
+    0.006675186567008495,
+    0.006688341964036226,
+    0.006701510865241289,
+    0.006714692339301109,
+    0.006727886851876974,
+    0.006741093937307596,
+    0.00675431452691555,
+    0.0067675476893782616,
+    0.0067807938903570175,
+    0.006794053129851818,
+    0.006807325407862663,
+    0.006820610258728266,
+    0.0068339086137712,
+    0.006847219541668892,
+    0.006860543508082628,
+    0.006873880513012409,
+    0.0068872300907969475,
+    0.006900593172758818,
+    0.006913968827575445,
+    0.006927357520908117,
+    0.006940759252756834,
+    0.006954174023121595,
+    0.006967601366341114,
+    0.006981041748076677,
+    0.0069944956339895725,
+    0.007007961627095938,
+    0.007021441124379635,
+    0.007034933660179377,
+    0.007048438768833876,
+    0.007061956916004419,
+    0.007075488101691008,
+    0.0070890323258936405,
+    0.007102589588612318,
+    0.007116159424185753,
+    0.007129742298275232,
+    0.007143338210880756,
+    0.007156947162002325,
+    0.007170569151639938,
+    0.007184203714132309,
+    0.0071978517808020115,
+    0.007211512420326471,
+    0.007225186098366976,
+    0.0072388723492622375,
+    0.007252572104334831,
+    0.007266284432262182,
+    0.007280009798705578,
+    0.007293748203665018,
+    0.007307499647140503,
+    0.007321264129132032,
+    0.007335041183978319,
+    0.0073488312773406506,
+    0.0073626344092190266,
+    0.007376450579613447,
+    0.007390279788523912,
+    0.007404121570289135,
+    0.0074179768562316895,
+    0.007431844715029001,
+    0.007445725612342358,
+    0.007459619082510471,
+    0.007473526056855917,
+    0.00748744560405612,
+    0.0075013781897723675,
+    0.00751532381400466,
+    0.0075292824767529964,
+    0.007543254178017378,
+    0.007557238452136517,
+    0.0075712357647717,
+    0.007585246115922928,
+    0.0075992695055902,
+    0.007613305933773518,
+    0.007627354934811592,
+    0.0076414174400269985,
+    0.007655492518097162,
+    0.007669580634683371,
+    0.007683681324124336,
+    0.007697795517742634,
+    0.007711922284215689,
+    0.007726062089204788,
+    0.007740214932709932,
+    0.007754380814731121,
+    0.007768559735268354,
+    0.007782751228660345,
+    0.00779695576056838,
+    0.00781117333099246,
+    0.007825404405593872,
+    0.007839647121727467,
+    0.00785390380769968,
+    0.007868173532187939,
+    0.007882455363869667,
+    0.007896751165390015,
+    0.007911059074103832,
+    0.007925380021333694,
+    0.007939714007079601,
+    0.007954061031341553,
+    0.007968421094119549,
+    0.00798279419541359,
+    0.007997180335223675,
+    0.008011579513549805,
+    0.008025990799069405,
+    0.008040416054427624,
+    0.008054853416979313,
+    0.008069304749369621,
+    0.0080837681889534,
+    0.008098244667053223,
+    0.00811273418366909,
+    0.008127236738801003,
+    0.00814175233244896,
+    0.00815628096461296,
+    0.008170821703970432,
+    0.008185376413166523,
+    0.008199943229556084,
+    0.008214524015784264,
+    0.008229116909205914,
+    0.008243722841143608,
+    0.008258341811597347,
+    0.008272973820567131,
+    0.00828761886805296,
+    0.008302276954054832,
+    0.00831694807857275,
+    0.008331631310284138,
+    0.008346328511834145,
+    0.008361037820577621,
+    0.008375760167837143,
+    0.008390496484935284,
+    0.008405244909226894,
+    0.00842000637203455,
+    0.00843478087335825,
+    0.008449568413197994,
+    0.008464368991553783,
+    0.008479181677103043,
+    0.008494008332490921,
+    0.00850884709507227,
+    0.008523699827492237,
+    0.008538564667105675,
+    0.008553442545235157,
+    0.008568333461880684,
+    0.008583237417042255,
+    0.008598154410719872,
+    0.008613084442913532,
+    0.008628027513623238,
+    0.008642982691526413,
+    0.008657951839268208,
+    0.008672934025526047,
+    0.008687928318977356,
+    0.00870293565094471,
+    0.008717956021428108,
+    0.008732989430427551,
+    0.008748035877943039,
+    0.008763095363974571,
+    0.008778167888522148,
+    0.00879325345158577,
+    0.008808351121842861,
+    0.008823462761938572,
+    0.008838586509227753,
+    0.008853724226355553,
+    0.008868874050676823,
+    0.008884036913514137,
+    0.008899212814867496,
+    0.0089144017547369,
+    0.008929603733122349,
+    0.008944818750023842,
+    0.008960045874118805,
+    0.008975286968052387,
+    0.00899054016917944,
+    0.009005807340145111,
+    0.009021086618304253,
+    0.009036378934979439,
+    0.00905168429017067,
+    0.009067002683877945,
+    0.009082334116101265,
+    0.00909767858684063,
+    0.009113036096096039,
+    0.009128405712544918,
+    0.009143789298832417,
+    0.009159184992313385,
+    0.009174594655632973,
+    0.00919001642614603,
+    0.009205451235175133,
+    0.00922089908272028,
+    0.009236359968781471,
+    0.009251833893358707,
+    0.009267320856451988,
+    0.009282820858061314,
+    0.009298332966864109,
+    0.009313859045505524,
+    0.009329397231340408,
+    0.009344948455691338,
+    0.009360513649880886,
+    0.009376090951263905,
+    0.009391681291162968,
+    0.009407284669578075,
+    0.009422901086509228,
+    0.00943852961063385,
+    0.009454172104597092,
+    0.009469827637076378,
+    0.009485495276749134,
+    0.009501175954937935,
+    0.009516870602965355,
+    0.009532577358186245,
+    0.00954829715192318,
+    0.009564029984176159,
+    0.009579775854945183,
+    0.009595534764230251,
+    0.009611306712031364,
+    0.009627090767025948,
+    0.00964288879185915,
+    0.009658698923885822,
+    0.00967452209442854,
+    0.009690359234809875,
+    0.009706208482384682,
+    0.009722070768475533,
+    0.009737946093082428,
+    0.009753834456205368,
+    0.009769735857844353,
+    0.009785649366676807,
+    0.009801576845347881,
+    0.009817516431212425,
+    0.009833469986915588,
+    0.009849435649812222,
+    0.0098654143512249,
+    0.009881406091153622,
+    0.009897410869598389,
+    0.0099134286865592,
+    0.009929459542036057,
+    0.009945503436028957,
+    0.009961560368537903,
+    0.009977629408240318,
+    0.009993712417781353,
+    0.010009807534515858,
+    0.010025915689766407,
+    0.010042036883533001,
+    0.01005817111581564,
+    0.010074318386614323,
+    0.01009047869592905,
+    0.010106652043759823,
+    0.01012283843010664,
+    0.010139036923646927,
+    0.010155249387025833,
+    0.01017147395759821,
+    0.010187712498009205,
+    0.01020396314561367,
+    0.01022022683173418,
+    0.010236503556370735,
+    0.010252793319523335,
+    0.010269096121191978,
+    0.010285411961376667,
+    0.010301739908754826,
+    0.010318081825971603,
+    0.010334436781704426,
+    0.010350803844630718,
+    0.010367183946073055,
+    0.010383577086031437,
+    0.010399984195828438,
+    0.010416403412818909,
+    0.01043283473700285,
+    0.01044928003102541,
+    0.010465738363564014,
+    0.010482209734618664,
+    0.010498693212866783,
+    0.010515190660953522,
+    0.01053170021623373,
+    0.010548222810029984,
+    0.010564758442342281,
+    0.010581308044493198,
+    0.010597869753837585,
+    0.010614443570375443,
+    0.010631031356751919,
+    0.01064763218164444,
+    0.01066424511373043,
+    0.01068087201565504,
+    0.010697511024773121,
+    0.01071416400372982,
+    0.01073082908987999,
+    0.010747507214546204,
+    0.010764198377728462,
+    0.010780902579426765,
+    0.010797619819641113,
+    0.010814350098371506,
+    0.010831092484295368,
+    0.01084784884005785,
+    0.010864617303013802,
+    0.010881399735808372,
+    0.010898194275796413,
+    0.010915001854300499,
+    0.010931822471320629,
+    0.010948656126856804,
+    0.010965502820909023,
+    0.010982362553477287,
+    0.010999235324561596,
+    0.011016120202839375,
+    0.011033019050955772,
+    0.01104993000626564,
+    0.011066854931414127,
+    0.011083791963756084,
+    0.011100742034614086,
+    0.011117705143988132,
+    0.011134681291878223,
+    0.011151670478284359,
+    0.01116867270320654,
+    0.011185687966644764,
+    0.011202715337276459,
+    0.011219756677746773,
+    0.011236810125410557,
+    0.011253876611590385,
+    0.011270957067608833,
+    0.011288049630820751,
+    0.011305155232548714,
+    0.01132227387279272,
+    0.011339405551552773,
+    0.011356549337506294,
+    0.011373707093298435,
+    0.01139087788760662,
+    0.011408060789108276,
+    0.011425256729125977,
+    0.011442466638982296,
+    0.011459688656032085,
+    0.01147692371159792,
+    0.011494171805679798,
+    0.011511432938277721,
+    0.01152870710939169,
+    0.011545993387699127,
+    0.011563293635845184,
+    0.011580605991184711,
+    0.011597932316362858,
+    0.011615270748734474,
+    0.01163262315094471,
+    0.011649987660348415,
+    0.011667365208268166,
+    0.01168475579470396,
+    0.0117021594196558,
+    0.01171957515180111,
+    0.011737004853785038,
+    0.011754447594285011,
+    0.011771902441978455,
+    0.011789370328187943,
+    0.01180685218423605,
+    0.011824346147477627,
+    0.011841853149235249,
+    0.011859373189508915,
+    0.011876906268298626,
+    0.011894452385604382,
+    0.011912011541426182,
+    0.011929582804441452,
+    0.011947168037295341,
+    0.011964765377342701,
+    0.01198237668722868,
+    0.012000000104308128
+  ]
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    6,
+    12,
+    18,
+    30
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    192,
+    384,
+    576,
+    960
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 3,
+  "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": 3,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "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": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585b29b19df7067708a1ef427e18f556932bec1476ed3090c94aab132a31e598
+size 1625392420

vqvae/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "VQModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": false,
+  "in_channels": 3,
+  "latent_channels": 3,
+  "layers_per_block": 2,
+  "lookup_from_codebook": false,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "norm_type": "group",
+  "num_vq_embeddings": 8192,
+  "out_channels": 3,
+  "sample_size": 64,
+  "scaling_factor": 1.0,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "vq_embed_dim": null
+}

vqvae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178b7f07d6d5665795e45941c23e3248a7b9e1b8155efbcb0e56d4985fc62963
+size 221314016