all-the-public-replicate-models 1.505.0 → 1.506.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. package/.github/workflows/claude-code-review.yml +75 -0
  2. package/.github/workflows/claude.yml +59 -0
  3. package/models-lite.json +1124 -1097
  4. package/models.json +3470 -2385
  5. package/package.json +1 -1
  6. package/stats.json +26053 -25167
  7. package/stats.md +0 -287
package/stats.md DELETED
@@ -1,287 +0,0 @@
1
- # Model Stats
2
- ## New Models
3
- - https://replicate.com/meta/meta-llama-guard-2-8b
4
-
5
- ## Removed Models
6
- - https://replicate.com/lucataco/meta-llama-guard-2-8b
7
-
8
- ## Rising Stars
9
- | Model | Description | Runs Today | Runs Total | % of Total |
10
- |-------|-------------|------------|------------|------------|
11
- | [meta/meta-llama-guard-2-8b](https://replicate.com/meta/meta-llama-guard-2-8b) | Meta Llama Guard 2 is an 8B parameter Llama 3-based LLM safeguard model | 23 | 23 | 100.00% |
12
- | [lucataco/deepseek-67b-base](https://replicate.com/lucataco/deepseek-67b-base) | DeepSeek LLM, an advanced language model comprising 67 billion parameters. Trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese | 4 | 7 | 57.14% |
13
- | [remodela-ai/style-materials-transfer](https://replicate.com/remodela-ai/style-materials-transfer) | null | 1 | 4 | 25.00% |
14
- | [lucataco/hermes-2-pro-llama-3-8b](https://replicate.com/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 | 5 | 44 | 11.36% |
15
- | [wolverinn/ecommerce-virtual-try-on](https://replicate.com/wolverinn/ecommerce-virtual-try-on) | Virtual try-on using Stable Diffusion and IP-Adapter | 5 | 73 | 6.85% |
16
- | [zsxkib/talknet-asd](https://replicate.com/zsxkib/talknet-asd) | 🗣️ TalkNet-ASD: Detect who is speaking in a video | 3 | 51 | 5.88% |
17
- | [hvision-nku/storydiffusion](https://replicate.com/hvision-nku/storydiffusion) | Consistent Self-Attention for Long-Range Image and Video Generation | 101 | 1896 | 5.33% |
18
- | [bhavnicksm/sdxl-hiroshinagai](https://replicate.com/bhavnicksm/sdxl-hiroshinagai) | A SDXL Model trained from another SDXL-hiroshinagai model images | 4 | 78 | 5.13% |
19
- | [kitaef/mytestmodel](https://replicate.com/kitaef/mytestmodel) | The img2img pipeline that makes an anime-style image of a person. It uses one of sd1.5 models as a base, depth-estimation as a ControleNet and IPadapter model for face consistency. | 2 | 45 | 4.44% |
20
- | [tomasmcm/llamaguard-7b](https://replicate.com/tomasmcm/llamaguard-7b) | Source: llamas-community/LlamaGuard-7b ✦ Quant: TheBloke/LlamaGuard-7B-AWQ ✦ Llama-Guard is a 7B parameter Llama 2-based input-output safeguard model | 2985 | 71136 | 4.20% |
21
- | [jd7h/texify](https://replicate.com/jd7h/texify) | Converts images or pdfs containing math into markdown and LaTeX that can be rendered by MathJax | 1 | 28 | 3.57% |
22
- | [lucataco/qwen-vl-chat](https://replicate.com/lucataco/qwen-vl-chat) | A multimodal LLM-based AI assistant, which is trained with alignment techniques. Qwen-VL-Chat supports more flexible interaction, such as multi-round question answering, and creative capabilities. | 12088 | 343776 | 3.52% |
23
- | [zsxkib/pulid](https://replicate.com/zsxkib/pulid) | 📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment | 266 | 7658 | 3.47% |
24
- | [wolverinn/webui-api](https://replicate.com/wolverinn/webui-api) | sd-webui API full support with extensions | 145 | 4243 | 3.42% |
25
- | [jd7h/luciddreamer](https://replicate.com/jd7h/luciddreamer) | High-Fidelity Text-to-3D Generation via Interval Score Matching | 2 | 61 | 3.28% |
26
- | [lucataco/rembg-video](https://replicate.com/lucataco/rembg-video) | Remove video background | 4 | 125 | 3.20% |
27
- | [nateraw/autotune](https://replicate.com/nateraw/autotune) | pitch correction on your voice | 2 | 79 | 2.53% |
28
- | [myaiteam2/album-video-maker](https://replicate.com/myaiteam2/album-video-maker) | null | 1 | 41 | 2.44% |
29
- | [chamuditha4/cartoonizer](https://replicate.com/chamuditha4/cartoonizer) | null | 1 | 43 | 2.33% |
30
- | [iordcalin/material-transfer](https://replicate.com/iordcalin/material-transfer) | Transfer a material from an image to a subject | 53 | 2465 | 2.15% |
31
- | [smoosh-sh/baby-mystic](https://replicate.com/smoosh-sh/baby-mystic) | Implementation of Realistic Vision v5.1 to conjure up images of the potential baby using a single photo from each parent | 60 | 2849 | 2.11% |
32
- | [cjwbw/openvoice](https://replicate.com/cjwbw/openvoice) | Updated to OpenVoice v2: Versatile Instant Voice Cloning | 87 | 4727 | 1.84% |
33
- | [cjwbw/hyper-sdxl-1step-t2i](https://replicate.com/cjwbw/hyper-sdxl-1step-t2i) | Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis | 10 | 587 | 1.70% |
34
- | [visoar/cat-xiaobai](https://replicate.com/visoar/cat-xiaobai) | My Cat Xiaobai | 4 | 247 | 1.62% |
35
- | [mdzor/weapons-items](https://replicate.com/mdzor/weapons-items) | null | 1 | 66 | 1.52% |
36
- | [philz1337x/style-transfer](https://replicate.com/philz1337x/style-transfer) | Apply the style of an image to your image. Upscaling with Clarity is recommended. Twitter/X: @philz1337x | 65 | 4327 | 1.50% |
37
- | [lucataco/watermark_detector](https://replicate.com/lucataco/watermark_detector) | amrul-hzz's fine-tuned version of vit-base-patch16-224-in21k for watermark image detection | 2 | 142 | 1.41% |
38
- | [spuuntries/borealis-10.7b-dpo-gguf](https://replicate.com/spuuntries/borealis-10.7b-dpo-gguf) | Undi95's Borealis 10.7B Mistral DPO Finetune, GGUF Q5_K_M quantized by Undi95. | 1 | 71 | 1.41% |
39
- | [asiryan/absolutereality-v1.8.1](https://replicate.com/asiryan/absolutereality-v1.8.1) | AbsoluteReality V1.8.1 Model (Text2Img, Img2Img and Inpainting) | 224 | 16711 | 1.34% |
40
- | [austinxu123/test-sdxl-finetune-canva-5](https://replicate.com/austinxu123/test-sdxl-finetune-canva-5) | null | 3 | 226 | 1.33% |
41
- | [sunfjun/stable-video-diffusion](https://replicate.com/sunfjun/stable-video-diffusion) | null | 144 | 10906 | 1.32% |
42
- | [lucataco/singing_voice_conversion](https://replicate.com/lucataco/singing_voice_conversion) | Amphion Singing Voice Conversion: DiffWaveNetSVC | 7 | 550 | 1.27% |
43
- | [cjwbw/dreamtalk](https://replicate.com/cjwbw/dreamtalk) | RESEARCH/NON-COMMERCIAL USE ONLY: diffusion-based audio-driven expressive talking head generation | 8 | 657 | 1.22% |
44
- | [simbrams/ri](https://replicate.com/simbrams/ri) | Realistic Inpainting with ControlNET (M-LSD + SEG) | 67 | 5899 | 1.14% |
45
- | [shanginn/supir](https://replicate.com/shanginn/supir) | null | 167 | 14737 | 1.13% |
46
- | [cjwbw/pixart-sigma](https://replicate.com/cjwbw/pixart-sigma) | Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation | 7 | 625 | 1.12% |
47
- | [cjwbw/animagine-xl-3.1](https://replicate.com/cjwbw/animagine-xl-3.1) | Anime-themed text-to-image stable diffusion model | 130 | 12228 | 1.06% |
48
- | [bytedance/sdxl-lightning-4step](https://replicate.com/bytedance/sdxl-lightning-4step) | SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps | 323955 | 31403526 | 1.03% |
49
- | [cswry/seesr](https://replicate.com/cswry/seesr) | SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution | 171 | 16713 | 1.02% |
50
- | [lorenzomarines/astra](https://replicate.com/lorenzomarines/astra) | a powerful and competitive model like Midjourney v6 and DALL-E 3 but Open and Decentralized | 9 | 964 | 0.93% |
51
- | [snowflake/snowflake-arctic-instruct](https://replicate.com/snowflake/snowflake-arctic-instruct) | An efficient, intelligent, and truly open-source language model | 1972 | 215568 | 0.91% |
52
- | [lucataco/minicpm-v-2](https://replicate.com/lucataco/minicpm-v-2) | OpenBMB MiniCPM-V 2.8B is a strong multimodal large language model for efficient end-side deployment | 1 | 111 | 0.90% |
53
- | [suminhthanh/vixtts](https://replicate.com/suminhthanh/vixtts) | viⓍTTS vixTTS là mô hình tạo sinh giọng nói cho phép bạn sao chép giọng nói sang các ngôn ngữ khác nhau chỉ bằng cách sử dụng một đoạn âm thanh nhanh dài 6 giây | 1 | 111 | 0.90% |
54
- | [mercurio005/whisperx-spanish](https://replicate.com/mercurio005/whisperx-spanish) | WhisperX model for spanish language. | 245 | 27762 | 0.88% |
55
- | [styleof/fast-face-to-many](https://replicate.com/styleof/fast-face-to-many) | null | 15 | 1720 | 0.87% |
56
- | [cuuupid/idm-vton](https://replicate.com/cuuupid/idm-vton) | Best-in-class clothing virtual try on in the wild (non-commercial use only) | 343 | 39741 | 0.86% |
57
- | [cjwbw/voicecraft](https://replicate.com/cjwbw/voicecraft) | Zero-Shot Speech Editing and Text-to-Speech in the Wild | 14 | 1631 | 0.86% |
58
- | [135arvin/my_comfyui](https://replicate.com/135arvin/my_comfyui) | Run comfyui with api | 375 | 45599 | 0.82% |
59
- | [cjwbw/aniportrait-audio2vid](https://replicate.com/cjwbw/aniportrait-audio2vid) | Audio-Driven Synthesis of Photorealistic Portrait Animations | 12 | 1478 | 0.81% |
60
- | [jd7h/dreamcraft3d](https://replicate.com/jd7h/dreamcraft3d) | DreamCraft3D is a text and image to 3D model. Dreamcraft3D uses DeepFloyd IF and Stable Zero123, non-commercial research-only models. Please make sure you read and abide to the relevant licenses before using it. | 1 | 127 | 0.79% |
61
-
62
- ## Active Models
63
- | Model | Description | Runs in the last day |
64
- |-------|-------------|---------------------|
65
- | [bytedance/sdxl-lightning-4step](https://replicate.com/bytedance/sdxl-lightning-4step) | SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps | 323955 |
66
- | [meta/meta-llama-3-70b-instruct](https://replicate.com/meta/meta-llama-3-70b-instruct) | A 70 billion parameter language model from Meta, fine tuned for chat completions | 58277 |
67
- | [salesforce/blip](https://replicate.com/salesforce/blip) | Bootstrapping Language-Image Pre-training | 37319 |
68
- | [nightmareai/real-esrgan](https://replicate.com/nightmareai/real-esrgan) | Real-ESRGAN with optional face correction and adjustable upscale | 37015 |
69
- | [tencentarc/gfpgan](https://replicate.com/tencentarc/gfpgan) | Practical face restoration algorithm for *old photos* or *AI-generated faces* | 21712 |
70
- | [stability-ai/sdxl](https://replicate.com/stability-ai/sdxl) | A text-to-image generative AI model that creates beautiful images | 21205 |
71
- | [openai/whisper](https://replicate.com/openai/whisper) | Convert speech in audio to text | 15102 |
72
- | [yorickvp/llava-13b](https://replicate.com/yorickvp/llava-13b) | Visual instruction tuning towards large language and vision models with GPT-4 level capabilities | 14386 |
73
- | [meta/meta-llama-3-8b](https://replicate.com/meta/meta-llama-3-8b) | Base version of Llama 3, an 8 billion parameter language model from Meta. | 14337 |
74
- | [lucataco/qwen-vl-chat](https://replicate.com/lucataco/qwen-vl-chat) | A multimodal LLM-based AI assistant, which is trained with alignment techniques. Qwen-VL-Chat supports more flexible interaction, such as multi-round question answering, and creative capabilities. | 12088 |
75
- | [meta/llama-2-7b-chat](https://replicate.com/meta/llama-2-7b-chat) | A 7 billion parameter language model from Meta, fine tuned for chat completions | 11292 |
76
- | [xinntao/gfpgan](https://replicate.com/xinntao/gfpgan) | Practical face restoration algorithm for *old photos* or *AI-generated faces* | 8686 |
77
- | [philz1337x/clarity-upscaler](https://replicate.com/philz1337x/clarity-upscaler) | High resolution image Upscaler and Enhancer. Use at ClarityAI.cc. A free Magnific alternative. Twitter/X: @philz1337x | 8341 |
78
- | [andreasjansson/clip-features](https://replicate.com/andreasjansson/clip-features) | Return CLIP features for the clip-vit-large-patch14 model | 8273 |
79
- | [mistralai/mixtral-8x7b-instruct-v0.1](https://replicate.com/mistralai/mixtral-8x7b-instruct-v0.1) | The Mixtral-8x7B-instruct-v0.1 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts tuned to be a helpful assistant. | 7625 |
80
- | [lucataco/proteus-v0.2](https://replicate.com/lucataco/proteus-v0.2) | Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities. | 5300 |
81
- | [m1guelpf/nsfw-filter](https://replicate.com/m1guelpf/nsfw-filter) | Run any image through the Stable Diffusion content filter | 5197 |
82
- | [andreasjansson/blip-2](https://replicate.com/andreasjansson/blip-2) | Answers questions about images | 4635 |
83
- | [mistralai/mistral-7b-v0.1](https://replicate.com/mistralai/mistral-7b-v0.1) | A 7 billion parameter language model from Mistral. | 3814 |
84
- | [daanelson/real-esrgan-a100](https://replicate.com/daanelson/real-esrgan-a100) | Real-ESRGAN for image upscaling on an A100 | 3715 |
85
- | [tencentarc/photomaker](https://replicate.com/tencentarc/photomaker) | Create photos, paintings and avatars for anyone in any style within seconds. | 3588 |
86
- | [omniedgeio/face-swap](https://replicate.com/omniedgeio/face-swap) | Face Swap | 3467 |
87
- | [tomasmcm/llamaguard-7b](https://replicate.com/tomasmcm/llamaguard-7b) | Source: llamas-community/LlamaGuard-7b ✦ Quant: TheBloke/LlamaGuard-7B-AWQ ✦ Llama-Guard is a 7B parameter Llama 2-based input-output safeguard model | 2985 |
88
- | [sczhou/codeformer](https://replicate.com/sczhou/codeformer) | Robust face restoration algorithm for old photos / AI-generated faces | 2918 |
89
- | [meta/meta-llama-3-8b-instruct](https://replicate.com/meta/meta-llama-3-8b-instruct) | An 8 billion parameter language model from Meta, fine tuned for chat completions | 2914 |
90
- | [cjwbw/clip-vit-large-patch14](https://replicate.com/cjwbw/clip-vit-large-patch14) | openai/clip-vit-large-patch14 with Transformers | 2795 |
91
- | [ai-forever/kandinsky-2.2](https://replicate.com/ai-forever/kandinsky-2.2) | multilingual text2image latent diffusion model | 2665 |
92
- | [fofr/sdxl-emoji](https://replicate.com/fofr/sdxl-emoji) | An SDXL fine-tune based on Apple Emojis | 2480 |
93
- | [stability-ai/stable-diffusion-inpainting](https://replicate.com/stability-ai/stable-diffusion-inpainting) | Fill in masked parts of images with Stable Diffusion | 2465 |
94
- | [playgroundai/playground-v2.5-1024px-aesthetic](https://replicate.com/playgroundai/playground-v2.5-1024px-aesthetic) | Playground v2.5 is the state-of-the-art open-source model in aesthetic quality | 2030 |
95
- | [snowflake/snowflake-arctic-instruct](https://replicate.com/snowflake/snowflake-arctic-instruct) | An efficient, intelligent, and truly open-source language model | 1972 |
96
- | [fofr/face-to-many](https://replicate.com/fofr/face-to-many) | Turn a face into 3D, emoji, pixel art, video game, claymation or toy | 1971 |
97
- | [lucataco/juggernaut-xl-v9](https://replicate.com/lucataco/juggernaut-xl-v9) | Juggernaut XL v9 | 1853 |
98
- | [pharmapsychotic/clip-interrogator](https://replicate.com/pharmapsychotic/clip-interrogator) | The CLIP Interrogator is a prompt engineering tool that combines OpenAI's CLIP and Salesforce's BLIP to optimize text prompts to match a given image. Use the resulting prompts with text-to-image models like Stable Diffusion to create cool art! | 1801 |
99
- | [cjwbw/rembg](https://replicate.com/cjwbw/rembg) | Remove images background | 1773 |
100
- | [tencentarc/photomaker-style](https://replicate.com/tencentarc/photomaker-style) | Create photos, paintings and avatars for anyone in any style within seconds. (Stylization version) | 1623 |
101
- | [allenhooo/lama](https://replicate.com/allenhooo/lama) | 🦙 LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions | 1462 |
102
- | [yorickvp/llava-v1.6-34b](https://replicate.com/yorickvp/llava-v1.6-34b) | LLaVA v1.6: Large Language and Vision Assistant (Nous-Hermes-2-34B) | 1457 |
103
- | [lucataco/remove-bg](https://replicate.com/lucataco/remove-bg) | Remove background from an image | 1439 |
104
- | [lucataco/sdxl-controlnet](https://replicate.com/lucataco/sdxl-controlnet) | SDXL ControlNet - Canny | 1391 |
105
- | [replicate/all-mpnet-base-v2](https://replicate.com/replicate/all-mpnet-base-v2) | This is a language model that can be used to obtain document embeddings suitable for downstream tasks like semantic search and clustering. | 1308 |
106
- | [batouresearch/magic-image-refiner](https://replicate.com/batouresearch/magic-image-refiner) | A better alternative to SDXL refiners, providing a lot of quality and detail. Can also be used for inpainting or upscaling. | 1281 |
107
- | [xinntao/realesrgan](https://replicate.com/xinntao/realesrgan) | Practical Image Restoration Algorithms for General/Anime Images | 1228 |
108
- | [stability-ai/stable-diffusion](https://replicate.com/stability-ai/stable-diffusion) | A latent text-to-image diffusion model capable of generating photo-realistic images given any text input | 1114 |
109
- | [usamaehsan/controlnet-1.1-x-realistic-vision-v2.0](https://replicate.com/usamaehsan/controlnet-1.1-x-realistic-vision-v2.0) | controlnet 1.1 lineart x realistic-vision-v2.0 (updated to v5) | 1096 |
110
- | [fofr/face-to-sticker](https://replicate.com/fofr/face-to-sticker) | Turn a face into a sticker | 1005 |
111
- | [mejiabrayan/logoai](https://replicate.com/mejiabrayan/logoai) | null | 989 |
112
- | [konieshadow/fooocus-api](https://replicate.com/konieshadow/fooocus-api) | Third party Fooocus replicate model | 956 |
113
- | [shefa/turbo-enigma](https://replicate.com/shefa/turbo-enigma) | SDXL based text-to-image model applying Distribution Matching Distillation, supporting zero-shot identity generation in 2-5s. https://ai-visionboard.com | 938 |
114
- | [tomasmcm/llama2-13b-tiefighter](https://replicate.com/tomasmcm/llama2-13b-tiefighter) | Source: KoboldAI/LLaMA2-13B-Tiefighter ✦ Quant: TheBloke/LLaMA2-13B-Tiefighter-AWQ ✦ A merged model achieved trough merging two different lora's on top of a well established existing merge | 868 |
115
- | [meta/musicgen](https://replicate.com/meta/musicgen) | Generate music from a prompt or melody | 827 |
116
- | [vaibhavs10/incredibly-fast-whisper](https://replicate.com/vaibhavs10/incredibly-fast-whisper) | whisper-large-v3, incredibly fast, powered by Hugging Face Transformers! 🤗 | 766 |
117
- | [cjwbw/anything-v3-better-vae](https://replicate.com/cjwbw/anything-v3-better-vae) | high-quality, highly detailed anime style stable-diffusion with better VAE | 693 |
118
- | [fofr/audio-to-waveform](https://replicate.com/fofr/audio-to-waveform) | Create a waveform video from audio | 685 |
119
- | [fofr/any-comfyui-workflow](https://replicate.com/fofr/any-comfyui-workflow) | Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui | 681 |
120
- | [hnesk/whisper-wordtimestamps](https://replicate.com/hnesk/whisper-wordtimestamps) | openai/whisper with exposed settings for word_timestamps | 669 |
121
- | [lucataco/nsfw_image_detection](https://replicate.com/lucataco/nsfw_image_detection) | Falcons.ai Fine-Tuned Vision Transformer (ViT) for NSFW Image Classification | 665 |
122
- | [bfirsh/segformer-b0-finetuned-ade-512-512](https://replicate.com/bfirsh/segformer-b0-finetuned-ade-512-512) | null | 609 |
123
- | [usamaehsan/controlnet-x-ip-adapter-realistic-vision-v5](https://replicate.com/usamaehsan/controlnet-x-ip-adapter-realistic-vision-v5) | Inpainting || multi-controlnet || single-controlnet || ip-adapter || ip adapter face || ip adapter plus || No ip adapter | 599 |
124
- | [jingyunliang/swinir](https://replicate.com/jingyunliang/swinir) | Image Restoration Using Swin Transformer | 593 |
125
- | [mistralai/mistral-7b-instruct-v0.2](https://replicate.com/mistralai/mistral-7b-instruct-v0.2) | The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1. | 587 |
126
- | [cjwbw/anything-v4.0](https://replicate.com/cjwbw/anything-v4.0) | high-quality, highly detailed anime-style Stable Diffusion models | 581 |
127
- | [yuval-alaluf/sam](https://replicate.com/yuval-alaluf/sam) | Only a Matter of Style: Age Transformation Using a Style-Based Regression Model | 560 |
128
- | [meta/llama-2-70b-chat](https://replicate.com/meta/llama-2-70b-chat) | A 70 billion parameter language model from Meta, fine tuned for chat completions | 556 |
129
- | [spuuntries/flatdolphinmaid-8x7b-gguf](https://replicate.com/spuuntries/flatdolphinmaid-8x7b-gguf) | Undi95's FlatDolphinMaid 8x7B Mixtral Merge, GGUF Q5_K_M quantized by TheBloke. | 534 |
130
- | [aussielabs/musicgen](https://replicate.com/aussielabs/musicgen) | Deployment of Meta's MusicGen | 533 |
131
- | [lucataco/sdxl-inpainting](https://replicate.com/lucataco/sdxl-inpainting) | SDXL Inpainting developed by the HF Diffusers team | 523 |
132
- | [heedster/realistic-vision-v5](https://replicate.com/heedster/realistic-vision-v5) | Deployment of Realistic vision v5.0 with xformers for fast inference | 516 |
133
- | [meta/llama-2-13b-chat](https://replicate.com/meta/llama-2-13b-chat) | A 13 billion parameter language model from Meta, fine tuned for chat completions | 512 |
134
- | [fofr/realvisxl-v3-multi-controlnet-lora](https://replicate.com/fofr/realvisxl-v3-multi-controlnet-lora) | RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting | 510 |
135
- | [nateraw/goliath-120b](https://replicate.com/nateraw/goliath-120b) | An auto-regressive causal LM created by combining 2x finetuned Llama-2 70B into one. | 506 |
136
- | [mcai/babes-v2.0-img2img](https://replicate.com/mcai/babes-v2.0-img2img) | Generate a new image from an input image with Babes 2.0 | 498 |
137
- | [mark3labs/embeddings-gte-base](https://replicate.com/mark3labs/embeddings-gte-base) | General Text Embeddings (GTE) model. | 485 |
138
- | [jagilley/controlnet-scribble](https://replicate.com/jagilley/controlnet-scribble) | Generate detailed images from scribbled drawings | 478 |
139
- | [fofr/realvisxl-v3](https://replicate.com/fofr/realvisxl-v3) | Amazing photorealism with RealVisXL_V3.0, based on SDXL, trainable | 476 |
140
- | [antoinelyset/openhermes-2-mistral-7b-awq](https://replicate.com/antoinelyset/openhermes-2-mistral-7b-awq) | null | 416 |
141
- | [cjwbw/zoedepth](https://replicate.com/cjwbw/zoedepth) | ZoeDepth: Combining relative and metric depth | 412 |
142
- | [zsxkib/clip-age-predictor](https://replicate.com/zsxkib/clip-age-predictor) | Age prediction using CLIP - Patched version of `https://replicate.com/andreasjansson/clip-age-predictor` that works with the new version of cog! | 405 |
143
- | [fofr/become-image](https://replicate.com/fofr/become-image) | Adapt any picture of a face into another image | 394 |
144
- | [fofr/sticker-maker](https://replicate.com/fofr/sticker-maker) | Make stickers with AI. Generates graphics with transparent backgrounds. | 380 |
145
- | [135arvin/my_comfyui](https://replicate.com/135arvin/my_comfyui) | Run comfyui with api | 375 |
146
- | [lucataco/ms-img2vid](https://replicate.com/lucataco/ms-img2vid) | Turn any image into a video | 351 |
147
- | [cuuupid/idm-vton](https://replicate.com/cuuupid/idm-vton) | Best-in-class clothing virtual try on in the wild (non-commercial use only) | 343 |
148
- | [cjwbw/real-esrgan](https://replicate.com/cjwbw/real-esrgan) | Real-ESRGAN: Real-World Blind Super-Resolution | 342 |
149
- | [andreasjansson/sheep-duck-llama-2-70b-v1-1-gguf](https://replicate.com/andreasjansson/sheep-duck-llama-2-70b-v1-1-gguf) | null | 339 |
150
- | [lucataco/codeformer](https://replicate.com/lucataco/codeformer) | Robust face restoration algorithm for old photos/AI-generated faces - (A40 GPU) | 338 |
151
- | [asiryan/reliberate-v3](https://replicate.com/asiryan/reliberate-v3) | Reliberate v3 Model (Text2Img, Img2Img and Inpainting) | 337 |
152
- | [zsxkib/realistic-voice-cloning](https://replicate.com/zsxkib/realistic-voice-cloning) | Create song covers with any RVC v2 trained AI voice from audio files. | 337 |
153
- | [batouresearch/high-resolution-controlnet-tile](https://replicate.com/batouresearch/high-resolution-controlnet-tile) | Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination. | 334 |
154
- | [fofr/prompt-classifier](https://replicate.com/fofr/prompt-classifier) | Determines the toxicity of text to image prompts, llama-13b fine-tune. [SAFETY_RANKING] between 0 (safe) and 10 (toxic) | 334 |
155
- | [mistralai/mistral-7b-instruct-v0.1](https://replicate.com/mistralai/mistral-7b-instruct-v0.1) | An instruction-tuned 7 billion parameter language model from Mistral | 327 |
156
- | [orpatashnik/styleclip](https://replicate.com/orpatashnik/styleclip) | Text-Driven Manipulation of StyleGAN Imagery | 311 |
157
- | [pvitoria/chromagan](https://replicate.com/pvitoria/chromagan) | An Adversarial Approach for Picture Colorization | 307 |
158
- | [catacolabs/sdxl-ad-inpaint](https://replicate.com/catacolabs/sdxl-ad-inpaint) | Product advertising image generator using SDXL | 306 |
159
- | [zsxkib/instant-id](https://replicate.com/zsxkib/instant-id) | Make realistic images of real people instantly | 293 |
160
- | [mv-lab/swin2sr](https://replicate.com/mv-lab/swin2sr) | 3 Million Runs! AI Photorealistic Image Super-Resolution and Restoration | 286 |
161
- | [lucataco/xtts-v2](https://replicate.com/lucataco/xtts-v2) | Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning | 281 |
162
- | [zsxkib/pulid](https://replicate.com/zsxkib/pulid) | 📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment | 266 |
163
- | [catacolabs/cartoonify](https://replicate.com/catacolabs/cartoonify) | Turn your image into a cartoon | 261 |
164
- | [lambdal/text-to-pokemon](https://replicate.com/lambdal/text-to-pokemon) | Generate Pokémon from a text description | 253 |
165
- | [asiryan/blue-pencil-xl-v2](https://replicate.com/asiryan/blue-pencil-xl-v2) | Blue Pencil XL v2 Model (Text2Img, Img2Img and Inpainting) | 247 |
166
- | [lucataco/realvisxl2-lcm](https://replicate.com/lucataco/realvisxl2-lcm) | RealvisXL-v2.0 with LCM LoRA - requires fewer steps (4 to 8 instead of the original 40 to 50) | 246 |
167
- | [mercurio005/whisperx-spanish](https://replicate.com/mercurio005/whisperx-spanish) | WhisperX model for spanish language. | 245 |
168
- | [mcai/absolutebeauty-v1.0](https://replicate.com/mcai/absolutebeauty-v1.0) | Generate a new image given any input text with AbsoluteReality v1.0 | 245 |
169
- | [jagilley/controlnet-hough](https://replicate.com/jagilley/controlnet-hough) | Modify images using M-LSD line detection | 240 |
170
- | [lucataco/ssd-1b](https://replicate.com/lucataco/ssd-1b) | Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities | 234 |
171
- | [mcai/absolutebeauty-v1.0-img2img](https://replicate.com/mcai/absolutebeauty-v1.0-img2img) | Generate a new image from an input image with AbsoluteReality v1.0 | 234 |
172
- | [philz1337x/controlnet-deliberate](https://replicate.com/philz1337x/controlnet-deliberate) | Modify images with canny edge detection and Deliberate model twitter: @philz1337x | 233 |
173
- | [mcai/realistic-vision-v2.0](https://replicate.com/mcai/realistic-vision-v2.0) | Generate a new image given any input text with Realistic Vision V2.0 | 230 |
174
- | [prompthero/openjourney](https://replicate.com/prompthero/openjourney) | Stable Diffusion fine tuned on Midjourney v4 images. | 228 |
175
- | [01-ai/yi-34b-chat](https://replicate.com/01-ai/yi-34b-chat) | The Yi series models are large language models trained from scratch by developers at 01.AI. | 225 |
176
- | [asiryan/absolutereality-v1.8.1](https://replicate.com/asiryan/absolutereality-v1.8.1) | AbsoluteReality V1.8.1 Model (Text2Img, Img2Img and Inpainting) | 224 |
177
- | [lucataco/sdxl](https://replicate.com/lucataco/sdxl) | SDXL v1.0 - A text-to-image generative AI model that creates beautiful images | 216 |
178
- | [nateraw/openchat_3.5-awq](https://replicate.com/nateraw/openchat_3.5-awq) | OpenChat: Advancing Open-source Language Models with Mixed-Quality Data | 214 |
179
- | [zylim0702/qr_code_controlnet](https://replicate.com/zylim0702/qr_code_controlnet) | ControlNet QR Code Generator: Simplify QR code creation for various needs using ControlNet's user-friendly neural interface, making integration a breeze. Just key in the url ! | 213 |
180
- | [lucataco/dreamshaper-xl-lightning](https://replicate.com/lucataco/dreamshaper-xl-lightning) | dreamshaper-xl-lightning is a Stable Diffusion model that has been fine-tuned on SDXL | 210 |
181
- | [methexis-inc/img2prompt](https://replicate.com/methexis-inc/img2prompt) | Get an approximate text prompt, with style, matching an image. (Optimized for stable-diffusion (clip ViT-L/14)) | 205 |
182
- | [megvii-research/nafnet](https://replicate.com/megvii-research/nafnet) | Nonlinear Activation Free Network for Image Restoration | 196 |
183
- | [pengdaqian2020/image-tagger](https://replicate.com/pengdaqian2020/image-tagger) | image tagger | 189 |
184
- | [batouresearch/sdxl-controlnet-lora](https://replicate.com/batouresearch/sdxl-controlnet-lora) | '''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support. | 179 |
185
- | [lucataco/moondream2](https://replicate.com/lucataco/moondream2) | moondream2 is a small vision language model designed to run efficiently on edge devices | 172 |
186
- | [cswry/seesr](https://replicate.com/cswry/seesr) | SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution | 171 |
187
- | [shanginn/supir](https://replicate.com/shanginn/supir) | null | 167 |
188
- | [ai-forever/kandinsky-2](https://replicate.com/ai-forever/kandinsky-2) | text2img model trained on LAION HighRes and fine-tuned on internal datasets | 161 |
189
- | [piddnad/ddcolor](https://replicate.com/piddnad/ddcolor) | Towards Photo-Realistic Image Colorization via Dual Decoders | 160 |
190
- | [wolverinn/webui-api](https://replicate.com/wolverinn/webui-api) | sd-webui API full support with extensions | 145 |
191
- | [sunfjun/stable-video-diffusion](https://replicate.com/sunfjun/stable-video-diffusion) | null | 144 |
192
- | [fofr/latent-consistency-model](https://replicate.com/fofr/latent-consistency-model) | Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet | 144 |
193
- | [lucataco/hotshot-xl](https://replicate.com/lucataco/hotshot-xl) | 😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL | 141 |
194
- | [tgohblio/instant-id-multicontrolnet](https://replicate.com/tgohblio/instant-id-multicontrolnet) | InstantID. ControlNets. More base SDXL models. And the latest ByteDance's ⚡️SDXL-Lightning !⚡️ | 140 |
195
- | [daanelson/imagebind](https://replicate.com/daanelson/imagebind) | A model for text, audio, and image embeddings in one space | 139 |
196
- | [fofr/style-transfer](https://replicate.com/fofr/style-transfer) | Transfer the style of one image to another | 138 |
197
- | [meta/meta-llama-3-70b](https://replicate.com/meta/meta-llama-3-70b) | Base version of Llama 3, a 70 billion parameter language model from Meta. | 134 |
198
- | [swartype/sdxl-pixar](https://replicate.com/swartype/sdxl-pixar) | Create Pixar poster easily with SDXL Pixar. | 134 |
199
- | [cjwbw/dreamshaper](https://replicate.com/cjwbw/dreamshaper) | Dream Shaper stable diffusion | 134 |
200
- | [cjwbw/animagine-xl-3.1](https://replicate.com/cjwbw/animagine-xl-3.1) | Anime-themed text-to-image stable diffusion model | 130 |
201
- | [cjwbw/bigcolor](https://replicate.com/cjwbw/bigcolor) | Colorization using a Generative Color Prior for Natural Images | 130 |
202
- | [alaradirik/t2i-adapter-sdxl-openpose](https://replicate.com/alaradirik/t2i-adapter-sdxl-openpose) | Modify images using human pose | 124 |
203
- | [lucataco/animate-diff](https://replicate.com/lucataco/animate-diff) | Animate Your Personalized Text-to-Image Diffusion Models | 124 |
204
- | [mixinmax1990/realisitic-vision-v3-inpainting](https://replicate.com/mixinmax1990/realisitic-vision-v3-inpainting) | Realistic Vision V3.0 Inpainting | 124 |
205
- | [rossjillian/controlnet](https://replicate.com/rossjillian/controlnet) | Control diffusion models | 124 |
206
- | [usamaehsan/instant-id-x-juggernaut](https://replicate.com/usamaehsan/instant-id-x-juggernaut) | null | 120 |
207
- | [playgroundai/playground-v2-1024px-aesthetic](https://replicate.com/playgroundai/playground-v2-1024px-aesthetic) | Playground v2 is a diffusion-based text-to-image generative model trained from scratch by the research team at Playground | 120 |
208
- | [lucataco/realvisxl-v2.0](https://replicate.com/lucataco/realvisxl-v2.0) | Implementation of SDXL RealVisXL_V2.0 | 120 |
209
- | [tstramer/midjourney-diffusion](https://replicate.com/tstramer/midjourney-diffusion) | null | 120 |
210
- | [simbrams/segformer-b5-finetuned-ade-640-640](https://replicate.com/simbrams/segformer-b5-finetuned-ade-640-640) | Semantic Segmentation | 119 |
211
- | [jagilley/controlnet-depth2img](https://replicate.com/jagilley/controlnet-depth2img) | Modify images using depth maps | 118 |
212
- | [logerzhu/ad-inpaint](https://replicate.com/logerzhu/ad-inpaint) | Product advertising image generator | 115 |
213
- | [jyoung105/playground-v2.5](https://replicate.com/jyoung105/playground-v2.5) | State-of-the-art text to image "with turbo speed" | 113 |
214
- | [lucataco/proteus-v0.4](https://replicate.com/lucataco/proteus-v0.4) | ProteusV0.4: The Style Update | 111 |
215
- | [alaradirik/t2i-adapter-sdxl-depth-midas](https://replicate.com/alaradirik/t2i-adapter-sdxl-depth-midas) | Modify images using depth maps | 109 |
216
- | [konieshadow/fooocus-api-anime](https://replicate.com/konieshadow/fooocus-api-anime) | Third party Fooocus replicate model with preset 'anime' | 104 |
217
- | [nandycc/sdxl-app-icons](https://replicate.com/nandycc/sdxl-app-icons) | Fine tuned to generate awesome app icons, by aistartupkit.com | 104 |
218
- | [hvision-nku/storydiffusion](https://replicate.com/hvision-nku/storydiffusion) | Consistent Self-Attention for Long-Range Image and Video Generation | 101 |
219
- | [google-research/maxim](https://replicate.com/google-research/maxim) | Multi-Axis MLP for Image Processing | 101 |
220
-
221
- ## Top Model Authors by Run Count
222
- | Author | Models | Total Runs |
223
- |--------|--------|------------|
224
- | [stability-ai](https://replicate.com/stability-ai) | 6 | 175534497 |
225
- | [andreasjansson](https://replicate.com/andreasjansson) | 39 | 81395444 |
226
- | [salesforce](https://replicate.com/salesforce) | 2 | 79774559 |
227
- | [tencentarc](https://replicate.com/tencentarc) | 5 | 75090705 |
228
- | [jagilley](https://replicate.com/jagilley) | 12 | 49418838 |
229
- | [nightmareai](https://replicate.com/nightmareai) | 8 | 43999623 |
230
- | [meta](https://replicate.com/meta) | 29 | 37071124 |
231
- | [pengdaqian2020](https://replicate.com/pengdaqian2020) | 4 | 35884977 |
232
- | [sczhou](https://replicate.com/sczhou) | 2 | 32778622 |
233
- | [bytedance](https://replicate.com/bytedance) | 3 | 31408629 |
234
- | [cjwbw](https://replicate.com/cjwbw) | 135 | 27588556 |
235
- | [fofr](https://replicate.com/fofr) | 89 | 20178172 |
236
- | [abiruyt](https://replicate.com/abiruyt) | 2 | 17248203 |
237
- | [ai-forever](https://replicate.com/ai-forever) | 3 | 15097124 |
238
- | [prompthero](https://replicate.com/prompthero) | 8 | 12334978 |
239
- | [xinntao](https://replicate.com/xinntao) | 3 | 11857937 |
240
- | [lucataco](https://replicate.com/lucataco) | 160 | 11584031 |
241
- | [mistralai](https://replicate.com/mistralai) | 4 | 11103944 |
242
- | [daanelson](https://replicate.com/daanelson) | 15 | 10638403 |
243
- | [yorickvp](https://replicate.com/yorickvp) | 8 | 9660835 |
244
- | [lambdal](https://replicate.com/lambdal) | 4 | 8044342 |
245
- | [rossjillian](https://replicate.com/rossjillian) | 4 | 7250533 |
246
- | [openai](https://replicate.com/openai) | 1 | 6845542 |
247
- | [jingyunliang](https://replicate.com/jingyunliang) | 2 | 5833828 |
248
- | [tstramer](https://replicate.com/tstramer) | 16 | 4841130 |
249
- | [beautyyuyanli](https://replicate.com/beautyyuyanli) | 3 | 4088057 |
250
- | [mcai](https://replicate.com/mcai) | 16 | 3897757 |
251
- | [usamaehsan](https://replicate.com/usamaehsan) | 10 | 3698826 |
252
- | [mv-lab](https://replicate.com/mv-lab) | 2 | 3493456 |
253
- | [m1guelpf](https://replicate.com/m1guelpf) | 7 | 2809422 |
254
-
255
- ## Top Model Authors by Model Count
256
- | Author | Model Count |
257
- |--------|-------------|
258
- | [lucataco](https://replicate.com/lucataco) | 160 |
259
- | [cjwbw](https://replicate.com/cjwbw) | 135 |
260
- | [fofr](https://replicate.com/fofr) | 89 |
261
- | [adirik](https://replicate.com/adirik) | 47 |
262
- | [camenduru](https://replicate.com/camenduru) | 43 |
263
- | [nateraw](https://replicate.com/nateraw) | 42 |
264
- | [tomasmcm](https://replicate.com/tomasmcm) | 41 |
265
- | [andreasjansson](https://replicate.com/andreasjansson) | 39 |
266
- | [meta](https://replicate.com/meta) | 29 |
267
- | [zsxkib](https://replicate.com/zsxkib) | 25 |
268
- | [asiryan](https://replicate.com/asiryan) | 22 |
269
- | [anotherjesse](https://replicate.com/anotherjesse) | 22 |
270
- | [zeke](https://replicate.com/zeke) | 18 |
271
- | [sakemin](https://replicate.com/sakemin) | 18 |
272
- | [pagebrain](https://replicate.com/pagebrain) | 18 |
273
- | [arielreplicate](https://replicate.com/arielreplicate) | 17 |
274
- | [cbh123](https://replicate.com/cbh123) | 16 |
275
- | [mcai](https://replicate.com/mcai) | 16 |
276
- | [tstramer](https://replicate.com/tstramer) | 16 |
277
- | [batouresearch](https://replicate.com/batouresearch) | 15 |
278
- | [jbilcke](https://replicate.com/jbilcke) | 15 |
279
- | [daanelson](https://replicate.com/daanelson) | 15 |
280
- | [cloneofsimo](https://replicate.com/cloneofsimo) | 14 |
281
- | [dribnet](https://replicate.com/dribnet) | 14 |
282
- | [pollinations](https://replicate.com/pollinations) | 13 |
283
- | [chigozienri](https://replicate.com/chigozienri) | 12 |
284
- | [jagilley](https://replicate.com/jagilley) | 12 |
285
- | [hilongjw](https://replicate.com/hilongjw) | 11 |
286
- | [stphtan94117](https://replicate.com/stphtan94117) | 11 |
287
- | [usamaehsan](https://replicate.com/usamaehsan) | 10 |