Meta tags:

Headings (most frequently used words):

lucataco, flux, video, sdxl, lora, 8b, 7b, v1, vision, ollama, instruct, 70b, audio, 1b, diffusion, controlnet, llama, lcm, realistic, llama3, qwen1, ssd, image, stable, hunyuan, v2, 3b, large, chat, animate, img2img, v5, vl, img, caption, dev, qwen2, base, xl, adapter, realvisxl, wan, multi, qwen, kontext, merge, heygen, tuner, hunyuanvideo, 72b, alpha, pro, anything, dolphin, hermes, clip, diff, depth, openpose, realvisxl2, ip_, face, ocr, filter, gpt, oss, safeguard, deepseek, qwen3, nemotron, nano, featured, prompt, boost, txt2img, frame, avatar, img2vid, i2v, ltx, to, wan2, split, step, 6b, qwq, vid2vid, r1, dotted, woman, musubi, trainer, modernbert, apollo, 5b, turbo, diffusers, dreambooth, vlta, text, pixart, florence, idefics, embed, lightning, dreamshaper, wizardcoder, upscaler, demofusion, magic, style, real, esrgan, inference, training, mistral, inpainting, interrogator, glaive, 13b, vicuna, luis, catacora, motif, glm, sensenova, u1, mot, gemma, 31b, it, anime, vibevoice, asr, privacy, sam3, next, scene, interactiveomni, emu3, 120b, longcat, 20b, triblend, internvl3_, 30b, vid, consensus, ugc, ad, neutts, air, indextts, transition, banana, first, last, edit, davinci, compare, models, talking, minicpm, extract, seed, ppo, higgs, distilled, slideshow, meta, cars, realearth, embedding, veo, fast, vertical, iclora, seedance, lite, trim, vid2webp, 4step, screen, content, omnigen2, vectorized, dot, grid, jennai, 3d, emojis, game, assets, ace, omni, extractor, orpheus, ft, csm, magma, cogview4, 32b, olmocr, in, context, 1776, tts, videollama3, waveform, visualizer, steamboat, willie, joshua, converter, community, rf, inversion, dalgona, qvq, preview, 90b, 11b, bulk, moondream, smolvlm, sd3, fine, cogvideox, interpolation, x2, rplctcpl, layer, lineart, promeai, joy, pre, nsfw_, video_, detection, time100, reflection, union, syd, mead, watercolor, queso, schnell, ai, toolkit, simpletuner, dis, background, removal, segment, train, aura, flow, v0, guard, 86m, sigma, 900m, numinamath, tir, internlm2_, 57b, a14b, theta, mobius, paligemma, pt, 224, yi, blip3, phi3, mini, 110b, snowflake, arctic, sdxs, 512, mvsep, mdx23, music, separation, rembg, vit, patch32, moondream2, zeta, editing, sbs, rgb2grayscale, cuda, deep3d, glpn, nyu, nomic, phixtral, 2x2_, bge, m3, 4b, diffusionlight, and, audio2video, watermark_, detector, moondream1, siglip, 33b, gguf, whisperspeech, small, magnet, pheme, pasd, magnify, deepcache, tinyllama, open, dalle, motion, transfer, singing_, voice_, conversion, ip, faceid, dpo, seamless_, communication, x4, phi, segmind, vega, enhance, vid2openpose, vid2densepose, aligned, blend, interpany, clearer, tile, seine, dreamshaper7, vseq2vseq, modelscope, facefusion, inpaint, niji, se, zeke, loras, xtts, txt2img_, batch, thinkdiffusionxl, kosmos, mistrallite, bakllava, fuyu, crafter, comfyui, sadtalker, hotshot, illusion, hq, remove, bg, panoramic, codeformer, blueprint, ms, python, 34b, 9b, spider, gwen, upstage, function, calling, gfpgan, freewilly2, speaker, diarization, rivers, wsrglow, v4, v3, sandbox, xgen, 8k, codegen2, tiny, starcoder, py, shiba,

Text of the page (most frequently used words):
#lucataco (299), public (297), runs (296), model (78), and (72), video (69), image (58), the (55), with (51), text (50), flux (50), for (47), lora (47), sdxl (44), diffusion (31), #vision (29), audio (28), large (26), that (23), language (23), models (22), trained (22), based (19), from (19), images (18), ollama (18), realistic (17), fine (17), generation (16), version (16), stable (15), instruct (15), chat (15), open (15), controlnet (15), multimodal (15), using (15), lcm (15), dev (15), llama (14), qwen2 (14), face (13), 70b (13), transformer (13), prompt (13), only (13), qwen (12), diffusers (12), quality (12), ssd (12), speech (12), qwen1 (12), hunyuanvideo (12), base (11), inference (11), implementation (11), high (11), tuned (11), data (10), img2img (10), training (10), tool (10), finetune (10), style (9), into (9), generate (9), step (9), wan (9), clip (8), dataset (8), designed (8), pretrained (8), frame (8), simple (8), first (8), llama3 (8), animate (7), source (7), depth (7), openpose (7), multi (7), adapter (7), replicate (7), videos (7), embedding (7), anything (7), tasks (7), has (7), series (7), trainer (7), caption (7), merge (7), avatar (7), real (6), your (6), photos (6), function (6), inpainting (6), which (6), mistral (6), distilled (6), dolphin (6), microsoft (6), poc (6), loras (6), via (6), convert (6), file (6), beta (6), decoder (6), amount (6), end (6), hermes (6), unified (6), wrapper (6), reasoning (6), heygen (6), hunyuan (6), kontext (6), code (5), upscaler (5), meta (5), prompts (5), tune (5), realvisxl (5), background (5), segmind (5), long (5), context (5), variety (5), realvisxl2 (5), dreamshaper (5), pixart (5), research (5), understanding (5), 72b (5), two (5), lightning (5), pro (5), pre (5), experimental (5), tuner (5), gpt (5), qwq (5), foundation (5), powerful (5), fast (5), content (5), vicuna (4), 13b (4), glaive (4), interrogator (4), esrgan (4), calling (4), llm (4), supports (4), capabilities (4), labs (4), work (4), single (4), run (4), while (4), tokens (4), world (4), mode (4), steps (4), multilingual (4), time (4), length (4), interpolation (4), img (4), demofusion (4), alpha (4), use (4), input (4), size (4), anime (4), this (4), 224 (4), create (4), embed (4), openai (4), performance (4), developed (4), florence (4), are (4), explorer (4), split (4), apollo (4), modernbert (4), deepseek (4), dotted (4), tts (4), native (4), extract (4), filter (4), seedance (4), safety (4), salesforce (3), xgen (3), vae (3), faster (3), personalized (3), diff (3), gptq (3), idefics (3), wizardcoder (3), any (3), driven (3), talking (3), comfyui (3), txt2img (3), architecture (3), maintaining (3), processing (3), train (3), versatile (3), across (3), sdv1 (3), ip_ (3), voice (3), original (3), short (3), transition (3), clearer (3), resolution (3), magicanimate (3), human (3), phi (3), well (3), art (3), can (3), conversion (3), tinyllama (3), conversational (3), small (3), siglip (3), vit (3), detection (3), multiple (3), retrieval (3), encoder (3), removal (3), music (3), suite (3), sequences (3), inputs (3), json (3), foundational (3), diverse (3), representation (3), released (3), parameter (3), cog (3), sigma (3), huggingface (3), progress (3), black (3), ostris (3), toolkit (3), 299 (3), nemotron (3), bidirectional (3), preview (3), visual (3), community (3), musubi (3), provide (3), information (3), olmocr (3), wan2 (3), i2v (3), last (3), omni (3), natural (3), lite (3), ltx (3), veo (3), qwen3 (3), seed (3), boost (3), edit (3), nano (3), ocr (3), shiba (2), lmsys (2), codegen2 (2), 115 (2), sandbox (2), wsrglow (2), larger (2), segments (2), speaker (2), freewilly2 (2), practical (2), restoration (2), algorithm (2), old (2), generated (2), faces (2), generative (2), synthetic (2), upstage (2), match (2), spider (2), gwen (2), empowering (2), evol (2), img2vid (2), such (2), question (2), creative (2), realvisxl_v1 (2), remove (2), top (2), hotshot (2), animation (2), workflow (2), team (2), fuyu (2), modal (2), bakllava (2), offering (2), speedup (2), enhanced (2), orca (2), realvisxl_v2 (2), 264 (2), thinkdiffusionxl (2), capable (2), also (2), without (2), batch (2), enable (2), latent (2), consistency (2), xtts (2), cloning (2), requires (2), fewer (2), instead (2), zeke (2), combination (2), inpaint (2), user (2), 293 (2), infinite (2), seine (2), tile (2), interpany (2), system (2), magic (2), aligned (2), vega (2), 100 (2), translation (2), dpo (2), directly (2), turbo (2), faceid (2), 185 (2), zero (2), shot (2), motion (2), transfer (2), dalle (2), deepcache (2), non (2), super (2), pheme (2), generates (2), applications (2), magnet (2), loss (2), moondream1 (2), 439 (2), 888 (2), diffusionlight (2), bge (2), phixtral (2), full (2), nomic (2), glpn (2), deep3d (2), 128 (2), cuda (2), rgb2grayscale (2), sbs (2), vid2vid (2), been (2), editing (2), inversion (2), moondream2 (2), patch32 (2), demixing (2), sdxs (2), 512 (2), snowflake (2), arctic (2), updated (2), cleaned (2), openhermes (2), newly (2), introduced (2), house (2), blip3 (2), mini (2), paligemma (2), vlm (2), google (2), token (2), output (2), mobius (2), advancing (2), theta (2), instruction (2), billion (2), alibaba (2), a14b (2), sourced (2), numinamath (2), tir (2), 900m (2), flow (2), segment (2), simpletuner (2), deprecated (2), please (2), forest (2), schnell (2), queso (2), watercolor (2), dreambooth (2), syd (2), mead (2), character (2), violeta (2), vlta (2), reflection (2), people (2), lineart (2), specific (2), layer (2), cogvideox (2), stablediffusion3 (2), hugging (2), smolvlm (2), 193 (2), snippets (2), moondream (2), 183 (2), exploration (2), 32b (2), 11b (2), 90b (2), family (2), modernized (2), bert (2), trillion (2), english (2), qvq (2), dalgona (2), tencent (2), pipeline (2), format (2), steamboat (2), willie (2), 141 (2), woman (2), together (2), waveform (2), post (2), chinese (2), magma (2), 14b (2), 480p (2), csm (2), orpheus (2), simultaneously (2), was (2), jennai (2), vectorized (2), dot (2), grid (2), omnigen2 (2), efficient (2), weight (2), screen (2), trim (2), vertical (2), car (2), slideshow (2), form (2), higgs (2), expressive (2), ppo (2), bytedance (2), minicpm (2), compare (2), support (2), banana (2), ugc (2), three (2), consensus (2), down (2), web (2), friendly (2), featured (2), classify (2), policies (2), you (2), perform (2), oss (2), safeguard (2), privacy (2), recognition (2), vibevoice (2), asr (2), gemma (2), 31b (2), sensenova (2), mot (2), motif (2), apps (2), github (2), 701, bigcode, tiny_starcoder_py, tiny, starcoder, 639, environment, 361, sahil2801, replit, 123, 324, working, 460, rivershavewings, rivers, optional, correction, adjustable, upscale, 339, recording, who, speaking, a100, diarization, 317, stability, 408k, gfpgan, 487, creates, beautiful, 250, param, platform, canny, 848, optimizes, given, 187, 223, quantized, 882, python, 34b, turn, 826, assistant, alignment, techniques, more, flexible, interaction, round, answering, 358, blueprints, blueprint, robust, codeformer, 360, panorama, inpainted, wrapping, seam, panoramic, 428, monster, qrcode, illusion, 938, gif, alongside, stylized, sadtalker, 457, text2img, crafter, adept, augmented, llava, smaller, 665, mistrallitea, 32k, mistrallite, 290, grounding, kosmos, cheaper, amazing, photorealism, enough, styles, subjects, needing, prompting, genius, txt2img_, 491, reduces, number, needed, coqui, 376, combined, second, 398, distills, 612, sdxl_niji_special, edition, niji, ip_adapter, mediapipe, auto, fuse, onto, template, similar, appearance, modelscope, facefusion, 437, variable, conditioning, vseq2vseq, dreamshaper7, 366, prediction, 335, anytime, manipulated, blending, blend, democratising, 1024px, embeddings, temporally, consistent, googleai, shared, attention, densepose, vid2densepose, vid2openpose, enhancer, enhance, reduction, facebookresearch, seamlessm4t, massively, machine, seamless_, communication, direct, preference, optimization, method, align, preferences, optimizing, comparison, 232, general, purpose, aims, doing, everything, manga, midjourney, dall, various, conditioned, amphion, singing, diffwavenetsvc, singing_, voice_, space, features, 132, unique, fusion, showcases, exceptional, adherence, semantic, seems, above, closer, terms, comprehension, 653, finetuned, intermediate, 1431k, academic, commercial, pixel, aware, stylization, pasd, magnify, 586, voices, khz, phone, call, masked, autoregressive, built, inverting, whisper, whisperspeech, 33b, gguf, proposes, replace, used, pairwise, sigmoid, performs, par, twice, its, amrul, hzz, patch16, in21k, watermark, watermark_, detector, take, audio2video, light, probes, painting, chrome, ball, 754, granularity, 2x2_8, mixure, experts, moe, made, inspired, mistralai, mixtral, 8x7b, 2x2_, 801, files, 8192, surpasses, ada, 002, global, local, path, networks, nyuv2, monocular, estimation, nyu, 570, deep, learning, 221, produce, animatediff, 144, mult, ddpm, zeta, efficiently, edge, devices, rembg, sound, challenge, 2023, track, mdx, mvsep, mdx23, separation, texts, score, distillation, feature, matching, 399, focuses, creating, optimized, idefics2, accepts, arbitrary, produces, outputs, 110b, projection, module, add, capabilties, 53k, 403, lmms, phi3, continuously, corpus, 500b, tuning, samples, 628, pushes, boundaries, domain, agnostic, debiasing, realignment, 134k, 380, merged, nous, 11k, coding, skills, initial, agentic, abilities, cloud, completions, 57b, internlm2, tailored, scenarios, internlm2_, solve, math, problems, integrated, powered, susceptible, attacks, intentionally, subvert, developer, intended, behavior, guard, 86m, 441, fully, aura, finetuner, sam2, automatic, mask, eccv2022, quick, dis, 105, 322, jake, dog, concept, blade, runner, jointly, instantx, shakker, union, named, 658, times, most, influential, time100, 103, falconais, nsfw, extended, nsfw_, video_, joy, 834, condition, promeai, 465, 620, experiment, one, rplctcpl, 126, gpus, alimama, 328, keyframe, zhengcong, fei, 907, sd3, huggingfacetb, apart, smallest, preprocessing, captioning, claude, gemini, bulk, 162, 125k, 634, latest, chatting, focusing, enhancing, cookies, unofficial, fork, formatted, weights, 222, rfinversion, finetunes, finetrainers, kohya, musibi, compatible, converter, foreground, 101, joshua, 122, walt, disney, 1928, separate, 275, comparable, 340, visualizer, converts, white, effect, videollama, frontier, videollama3, represents, industry, scale, utilizing, paradigm, 287, unbiased, accurate, factual, perplexity, 1776, apply, logo, release, ai2, mix, 0225, tongyi, lab, group, compared, conventional, thinking, 169, cogview, parameters, cogview4, 912, agents, 751, sesame, rvq, codes, emotive, extractor, perceive, modalities, including, generating, responses, streaming, manner, 142, towards, text2music, ace, game, assets, 164, emojis, 31k, brett, designjoy, 972, check, figures, copyright, concerns, combines, layout, causvid, 4step, webp, looping, vid2webp, 210, quickly, 145, icloras, iclora, shorts, specifically, ranking, turns, basic, satellite, drone, shots, realearth, 168, change, cdmx, cars, 565, transform, collection, 127, controllability, excels, 37k, mmaudio, deployment, computational, environments, strong, 789, kling, lipsync, autocaption, avatars, forked, shridharathi, help, decrease, volume, 341, synthesizes, 197, drawings, leonardo, vinci, davinci, 931, text2image, aspect, ratios, 119, between, clips, emotionally, duration, controlled, indextts, 559, enhances, 478, instant, neutts, air, 165, ads, ask, llms, same, find, vid, document, intelligence, vlms, enables, ability, query, summarize, physical, virtual, 102, documents, markdown, raw, locate, advanced, internvl3, specializing, internvl3_, 30b, crop, triblend, 20b, 153, longcat, 120b, learners, emu3, receive, coherent, interactiveomni, 265, lovis93, cinematic, progression, 2509, next, scene, segmentation, sam3, classifier, detecting, masking, personally, identifiable, pii, timestamp, aesthetics, negative, portraits, scenes, characters, 282, out, compact, state, omnidocbench, overall, four, modes, formula, latex, table, parsing, schema, extraction, fits, glm, reve, internal, pixverse, examples, intelligent, utilities, organizations, https, com, staff, luis, catacora,

Text of the page (random words):
lic lucataco bulk video caption video preprocessing tool for captioning multiple videos using gpt claude or gemini 183 runs public lucataco moondream 0 5b moondream 0 5b the world s smallest vision language model 69 runs public lucataco video split simple tool to split apart a video into snippets 193 runs public lucataco smolvlm instruct smolvlm instruct by huggingfacetb 8 3k runs public lucataco sd3 5 large fine tuner ostris ai toolkit for stablediffusion3 5 large lora training 439 runs public lucataco stable diffusion 3 5 large lora trainer fine tune stablediffusion3 5 large with hugging face diffusers 907 runs public lucataco stable diffusion 3 5 large lora stable diffusion 3 5 large lora explorer 2 5k runs public lucataco cogvideox interpolation cogvideox keyframe interpolation by zhengcong fei 328 runs public lucataco ollama nemotron 70b ollama nemotron 70b 8 8k runs public lucataco flux 1 turbo alpha 8 step distilled lora for flux 1 dev model released by the alimama creative team 2k runs public lucataco diffusers dreambooth lora x2 flux 1 dev lora training with 2x gpus by huggingface diffusers 126 runs public lucataco flux rplctcpl flux lora training experiment training two people in one lora with two images 620 runs public lucataco flux vlta layer flux finetune of violeta specific layer training 465 runs public lucataco flux 1 controlnet lineart promeai controlnet trained on black forest labs flux 1 dev with lineart condition 834 runs public lucataco ollama qwen2 5 72b ollama qwen2 5 72b 29 4k runs public lucataco joy caption pre alpha image caption model 3 8k runs public lucataco nsfw_ video_ detection falconais nsfw detection model extended for videos 103 8k runs public lucataco flux time100 flux finetune of the style times 100 most influential people in ai 658 runs public lucataco ollama reflection 70b ollama reflection 70b 1 6k runs public lucataco flux vlta a flux finetune of an ai character named violeta 1 9k runs public lucataco controlnet union pro controlnet for flux 1 dev model jointly released by instantx and shakker labs 2 8k runs public lucataco flux syd mead flux finetune trained on syd mead concept art for blade runner 1 4k runs public lucataco diffusers dreambooth lora flux 1 dev lora training by huggingface diffusers 299 runs public lucataco flux dev multi lora flux 1 dev multi lora explorer 1 8m runs public lucataco flux watercolor a flux lora trained on watercolor style photos 8 3k runs public lucataco flux queso a flux lora trained on photos of jake s dog queso 322 runs public lucataco flux schnell lora flux 1 schnell lora explorer 2 4m runs public lucataco ai toolkit ostris ai toolkit for flux lora training deprecated please use ostris flux dev lora trainer 61 1k runs public lucataco flux dev lora flux 1 dev lora explorer deprecated please use black forest labs flux dev lora 4 2m runs public lucataco flux dev flux dev diffusers implementation 1 1k runs public lucataco simpletuner flux flux 1 dev lora trainer via simpletuner work in progress 105 runs public lucataco dis background removal eccv2022 quick background removal 7 7k runs public lucataco segment anything 2 segment anything 2 sam2 by meta automatic mask generation 42 6k runs public lucataco train text to image lora huggingface diffusers sdv1 4 1 5 2 0 2 1 finetuner 34 runs public lucataco aura flow v0 2 a fully open sourced large flow based text to image generation model 441 runs public lucataco prompt guard 86m llm powered applications are susceptible to prompt attacks which are prompts intentionally designed to subvert the developer s intended behavior of the llm 50 runs public lucataco pixart sigma 900m pixart sigma 900m is a text to image generation model based on the pixart sigma architecture 2 2k runs public lucataco numinamath 7b tir numinamath is a series of language models that are trained to solve math problems using tool integrated reasoning tir 40 runs public lucataco ollama llama3 70b cog wrapper for ollama llama3 70b 6 6k runs public lucataco ollama llama3 8b cog wrapper for ollama llama3 8b 21 runs public lucataco internlm2_ 5 7b chat internlm2 5 has open sourced a 7 billion parameter base model and a chat model tailored for practical scenarios 63 runs public lucataco qwen2 57b a14b instruct qwen2 57 billion parameter language model from alibaba cloud fine tuned for chat completions 1 4k runs public lucataco dolphin 2 9 llama3 8b dolphin 2 9 has a variety of instruction conversational and coding skills it also has initial agentic abilities and supports function calling 11k runs public lucataco hermes 2 theta llama 3 8b hermes 2 θ theta is the first experimental merged model released by nous research 29 runs public lucataco hermes 2 pro llama 3 70b hermes 2 pro is an updated and cleaned version of the openhermes 2 5 dataset as well as a newly introduced function calling and json mode dataset developed in house 380 runs public lucataco florence 2 large florence 2 advancing a unified representation for a variety of vision tasks 2m runs public lucataco florence 2 base florence 2 advancing a unified representation for a variety of vision tasks 134k runs public lucataco mobius mobius a diffusion model that pushes the boundaries of domain agnostic debiasing and representation realignment 628 runs public lucataco paligemma 3b pt 224 paligemma 3b an open vlm by google pre trained with 224 224 input images and 128 token input output text sequences 4 1k runs public lucataco yi 1 5 6b yi 1 5 is continuously pre trained on yi with a high quality corpus of 500b tokens and fine tuned on 3m diverse fine tuning samples 69 runs public lucataco blip3 phi3 mini instruct r v1 blip3 xgen mm is a series of foundational large multimodal models lmms developed by salesforce ai research 403 runs public lucataco hermes 2 pro llama 3 8b hermes 2 pro is an updated and cleaned version of the openhermes 2 5 dataset as well as a newly introduced function calling and json mode dataset developed in house 53k runs public lucataco llama 3 vision alpha projection module trained to add vision capabilties to llama 3 using siglip 6 8k runs public lucataco qwen1 5 110b qwen1 5 is the beta version of qwen2 a transformer based decoder only language model pretrained on a large amount of data 2 7k runs public lucataco idefics 8b idefics2 is an open multimodal model that accepts arbitrary sequences of image and text inputs and produces text outputs 1 2k runs public lucataco snowflake arctic embed l snowflake arctic embed is a suite of text embedding models that focuses on creating high quality retrieval models optimized for performance 399 2k runs public lucataco sdxs 512 0 9 sdxs 512 0 9 can generate high resolution images in real time based on prompt texts trained using score distillation and feature matching 18 9k runs public lucataco mvsep mdx23 music separation model for sound demixing challenge 2023 music demixing track mdx 23 35 8k runs public lucataco rembg video video background removal 16 7k runs public lucataco clip vit base patch32 openai clip vit large patch32 1 3k runs public lucataco moondream2 moondream2 is a small vision language model designed to run efficiently on edge devices 14 9m runs public lucataco zeta editing zero shot text based audio editing using ddpm inversion 2k runs public lucataco sdxl lightning multi controlnet sdxl lightning mult controlnet img2img inpainting 10 6k runs public lucataco dreamshaper xl lightning dreamshaper xl lightning is a stable diffusion model that has been fine tuned on sdxl 144 3k runs public lucataco animate diff vid2vid animatediff video to video 888 runs public lucataco depth anything video sbs poc implementation of depth anything to produce a 3d sbs video 221 runs public lucataco rgb2grayscale cuda cuda implementation of an rgb2grayscale function 128 runs public lucataco deep3d deep3d real time end to end 2d to 3d video conversion based on deep learning 570 runs public lucataco glpn nyu global local path networks glpn model trained on nyuv2 for monocular depth estimation 62 runs public lucataco nomic embed text v1 nomic embed text v1 is 8192 context length text encoder that surpasses openai text embedding ada 002 and text embedding 3 small performance on short and long context tasks 46 9k runs public lucataco depth anything video depth anything on full video files 801 runs public lucataco phixtral 2x2_ 8 phixtral 2x2_8 is the first mixure of experts moe made with two microsoft phi 2 models inspired by the mistralai mixtral 8x7b v0 1 architecture 1 5k runs public lucataco bge m3 bge m3 the first embedding model which supports multiple retrieval mode multilingual and multi granularity retrieval 293 runs public lucataco qwen1 5 72b qwen1 5 is the beta version of qwen2 a transformer based decoder only language model pretrained on a large amount of data 4 4k runs public lucataco qwen1 5 7b qwen1 5 is the beta version of qwen2 a transformer based decoder only language model pretrained on a large amount of data 3 5k runs public lucataco qwen1 5 4b qwen1 5 is the beta version of qwen2 a transformer based decoder only language model pretrained on a large amount of data 1 4k runs public lucataco qwen1 5 1 8b qwen1 5 is the beta version of qwen2 a transformer based decoder only language model pretrained on a large amount of data 754 runs public lucataco qwen1 5 0 5b qwen1 5 is the beta version of qwen2 a transformer based decoder only language model pretrained on a large amount of data 63 runs public lucataco diffusionlight diffusionlight light probes by painting a chrome ball 888 runs public lucataco img and audio2video take an image and an audio file and create a video clip 17 2k runs public lucataco watermark_ detector amrul hzz s fine tuned version of vit base patch16 224 in21k for watermark image detection 439 runs public lucataco moondream1 research only moondream1 is a vision language model that performs on par with models twice its size 11 5k runs public lucataco siglip siglip proposes to replace the loss function used in clip by a simple pairwise sigmoid loss 2 1k runs public lucataco wizardcoder 33b v1 1 gguf wizardcoder empowering code large language models with evol instruct 17 9k runs public lucataco whisperspeech small an open source text to speech system built by inverting whisper 1 6k runs public lucataco magnet magnet masked audio generation using a single non autoregressive transformer 3 2k runs public lucataco pheme pheme generates a variety of conversational voices in 16 khz for phone call applications 586 runs public lucataco pasd magnify academic and non commercial use only pixel aware stable diffusion for realistic image super resolution and personalized stylization 49 2k runs public lucataco sdxl deepcache sdxl using deepcache 3 9k runs public lucataco tinyllama 1 1b chat v1 0 this is the chat model finetuned on top of tinyllama tinyllama 1 1b intermediate step 1431k 3t 653 runs public lucataco open dalle v1 1 a unique fusion that showcases exceptional prompt adherence and semantic understanding it seems to be a step above base sdxl and a step closer to dalle 3 in terms of prompt comprehension 132 9k runs public lucataco diffusion motion transfer space time diffusion features for zero shot text driven motion transfer 185 runs public lucataco singing_ voice_ conversion amphion singing voice conversion diffwavenetsvc 1 2k runs public lucataco ip adapter faceid research only ip adapter faceid can generate various style images conditioned on a face with only text prompts 33 9k runs public lucataco dreamshaper xl turbo dreamshaper is a general purpose sd model that aims at doing everything well photos art anime manga it s designed to match midjourney and dall e 232 7k runs public lucataco dpo sdxl direct preference optimization dpo is a method to align diffusion models to text human preferences by directly optimizing on human comparison data 2 2k runs public lucataco seamless_ communication facebookresearch seamlessm4t v2 massively multilingual multimodal machine translation 1 1k runs public lucataco stable diffusion x4 upscaler stable diffusion x4 upscaler model 8 3k runs public lucataco phi 2 phi 2 by microsoft 3 7k runs public lucataco segmind vega segmind vega model is a distilled version of sdxl offering a 70 reduction in size and an 100 speedup 2 7k runs public lucataco demofusion enhance image to image enhancer using demofusion 11 2k runs public lucataco vid2openpose video to openpose 2k runs public lucataco magic animate openpose magicanimate using an openpose input video 2 2k runs public lucataco vid2densepose convert your videos to densepose and use it with magicanimate 6 6k runs public lucataco style aligned googleai style aligned image generation via shared attention 1 3k runs public lucataco magic animate magicanimate temporally consistent human image animation using diffusion model 56 9k runs public lucataco pixart xl 2 pixart alpha 1024px is a transformer based text to image diffusion system trained on text embeddings from t5 78 9k runs public lucataco demofusion demofusion democratising high resolution image generation with no 9 3k runs public lucataco sdxl img blend sdxl image blending 42 6k runs public lucataco interpany clearer interpany clearer clearer anytime frame interpolation manipulated interpolation 13 3k runs public lucataco controlnet tile controlnet v1 1 tile version 4 3k runs public lucataco real esrgan video real esrgan video upscaler 335 5k runs public lucataco seine image to video seine short to long video diffusion model for generative transition and prediction 15 2k runs public lucataco animate diff sdxl lcm animate your personalized text to image diffusion models with sdxl and lcm 366 runs public lucataco dreamshaper7 img2img lcm dreamshaper 7 img2img with lcm lora for faster inference 55 3k runs public lucataco vseq2vseq text to video diffusion model with variable length frame conditioning for infinite length video 437 runs public lucataco realvisxl2 lcm realvisxl v2 0 with lcm lora requires fewer steps 4 to 8 instead of the original 40 to 50 293 2k runs public lucataco modelscope facefusion auto fuse a user s face onto the template image with a similar appearance to the user 15 3k runs public lucataco ip_ adapter face inpaint a combination of ip_adapter sdv1 5 and mediapipe face to inpaint a face 4 4k runs public lucataco sdxl niji se sdxl_niji_special edition 90 6k runs public lucataco sdxl lcm zeke a fine tuned sdxl lcm lora based on the photos of zeke 612 runs public lucataco sdxl lcm latent consistency model lcm sdxl distills the original model into a version that requires fewer steps 4 to 8 instead of the original 25 to 50 398 4k runs public lucataco sdxl lcm loras poc of sdxl lcm lora combined with a replicate lora for 4 second inference time 376 runs public lucataco xtts v2 coqui xtts v2 multilingual text to speech voice cloning 7 1m runs public lucataco lcm ssd 1b latent consistency model lcm ssd 1b is a lcm distilled version that reduces the nu...