Tất cả

anima

flux2

FLUX.2 [dev] is Black Forest Labs' second-generation open-weights image model, released in November 2025. It is a much larger flow-matching transformer than FLUX.1 that uses the Mistral Small 3.1 vision-language model as its text encoder,…FLUX.2 [dev] is Black Forest Labs' second-generation open-weights image model, released in November 2025. It is a much larger flow-matching transformer than FLUX.1 that uses the Mistral Small 3.1 vision-language model as its text encoder, which gives it far better understanding of long, descriptive prompts, reliable multi-line typography and real-world knowledge about brands, materials and lighting. It was designed from the start as a unified model: the same weights generate from text, edit an existing picture from instructions, and combine up to ten reference images for character, product or style consistency, with output up to 4 megapixels. The family also includes the smaller FLUX.2 Klein 4B and 9B distillations that most Flux2 LoRAs in this catalog are trained on. This entry is the text-to-image workflow, accelerated with a turbo LoRA so that it finishes in a handful of steps.Hiển thị thêm

flux

qwen

Qwen-Image is the image generation foundation model of Alibaba's Qwen team, released as open weights in August 2025. It is a 20-billion-parameter multimodal diffusion transformer that reads prompts through the Qwen2.5-VL vision-language…Qwen-Image is the image generation foundation model of Alibaba's Qwen team, released as open weights in August 2025. It is a 20-billion-parameter multimodal diffusion transformer that reads prompts through the Qwen2.5-VL vision-language model, and its headline strength is text: it renders long paragraphs, multi-line signs, posters and mixed Chinese and English typography with an accuracy no earlier open model reached. The same team's technical report also shows strong results for layout-heavy prompts, infographics and precise image editing, and the companion Qwen-Image-Edit model is the basis of many editing workflows. It generates natively around 1.3 to 1.6 megapixels in the usual aspect ratios and takes natural-language prompts rather than tag lists; the team recommends appending quality phrases such as 'Ultra HD, 4K, cinematic composition'. This entry is the version 2512 text-to-image workflow (the December 2025 refresh of the weights); the original release is kept as qwen-v1.Hiển thị thêm

sulphur2

by SulphurAI - Sulphur v2 is a custom finetune of LTX 2.3 designed to add in missing NSFW concepts to LTX. This is specifically the LoRA version of the finetune, and should work with both T2V and I2V on workflows that support LTX 2.3…by SulphurAI - Sulphur v2 is a custom finetune of LTX 2.3 designed to add in missing NSFW concepts to LTX. This is specifically the LoRA version of the finetune, and should work with both T2V and I2V on workflows that support LTX 2.3 LoRAs. Be sure to use good quality natural language prompts for the best effects!Hiển thị thêm

WAI illustrious

sdxl

Stable Diffusion XL version 1.0 is here, and the Refiner 1.0 is also installed. This is the official full release, but our software needs adjustment to fully support it. Only the /render command works and SDXL cannot be mixed with old…Stable Diffusion XL version 1.0 is here, and the Refiner 1.0 is also installed. This is the official full release, but our software needs adjustment to fully support it. Only the /render command works and SDXL cannot be mixed with old styles, recipes, loras, inversions, and other commands yet. Keep an eye on the XL news topic in Telegram VIP for more informationHiển thị thêm

WAI ANI PONYXL

WAI-ANI-NSFW-PONYXL by Wai0731 is a stylish anime pony model. Notes from the creator: Brief description of v7: To better suit a wider range of uses, I adjusted the weights and revised some composition logic. I also incorporated some…WAI-ANI-NSFW-PONYXL by Wai0731 is a stylish anime pony model. Notes from the creator: Brief description of v7: To better suit a wider range of uses, I adjusted the weights and revised some composition logic. I also incorporated some effects-related assets into the training. I made sure to retain the original NSFW content as much as possible. If you encounter any issues or feel there are areas that need improvement, please leave me a message. Version 7 released. v6->v7 Fixed the issue where images appeared entirely covered with snowflakes. Revised the composition logic to be more suitable for general scenarios. Added new assets for backgrounds, mature women, and clothing. Ensured consistency with the previous model and further fixed the issue of blurry eyes in medium and long shots. Fixed some minor issues. V7 Recommended Setting Steps: 30 CFG scale: 7 Sampler: Euler a/DPM++ 2M Karras ADetailer to fix eyes. Positive Prompt score_9, score_8_up, score_7_up,source_anime, Negative Prompt score_6, score_5, score_4, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark,Hiển thị thêm

Pony Diffusion V6 XL V6 (start with this one)

FLUX

AlbedoBase XL

Aesthetic Quality Modifiers Masterpiece v5.1 [anima base 1]

CyberRealistic Pony

DeepSeek V4.1 Flash

DeepSeek | 1,048,576 token context | $0.04/M input, $0.68/M output. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B…DeepSeek | 1,048,576 token context | $0.04/M input, $0.68/M output. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision ExpOpens in new tab. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 ProOpens in new tab on performance, speed, and task completion time.Hiển thị thêm

sdv15

Stable Diffusion 1.5 by Stability / RunwayML, the OG model. Someone said it was weird that we didn't have this in the concepts collection, and they were correct, so here you go! Of course, this model is over a year old, but it's still…Stable Diffusion 1.5 by Stability / RunwayML, the OG model. Someone said it was weird that we didn't have this in the concepts collection, and they were correct, so here you go! Of course, this model is over a year old, but it's still fantastic in its own right.Hiển thị thêm

Animagine XL V3.1

Nova Anime XL IL v19.0

Juggernaut XL Ragnarok

zimage turbo

ReV Animated

Hassaku XL (Illustrious)

Counterfeit V3.0

CounterfeitV3.0 by rqdwdw. The 3.0 version of Counterfeit has much brighter colors and more focus on the subject, whereas the previous model was more muted and pastel-like. The backgrounds look totally different in particular, so we're…CounterfeitV3.0 by rqdwdw. The 3.0 version of Counterfeit has much brighter colors and more focus on the subject, whereas the previous model was more muted and pastel-like. The backgrounds look totally different in particular, so we're going to keep both. It should be noted that there are 10 upvotes and 3 comments about green spots from users on Civitai.Hiển thị thêm

AutismMix SDXL AutismMix_pony

Hands XL + SD 1.5 + F1D + Pony + Illustrious + zit + ZIB Hand F1D v2.0

by EauDeNoire - Update: Please if you see any of my models somewhere else report or let me know! Thnx Please read version info (about version) Update: Added perfection style model (Hands + Feet + all in one) Update: Added Detailed style…by EauDeNoire - Update: Please if you see any of my models somewhere else report or let me know! Thnx Please read version info (about version) Update: Added perfection style model (Hands + Feet + all in one) Update: Added Detailed style (Hand focus + all in one) Update: Added SD 1.5 Model Trained on base model xl 1.0 + FLUX.1-dev Feel free to check feet model as well. Feedback and ratings are much appreciated. Other models to check: Skin Tone (Cinematic Photography) Style XL (Human skin color) Realistic Skin Texture style XL (Detailed Skin) Facial Expressions (detailed emotions) style XL Perfect Eyes (Variaty of sclera) XLHiển thị thêm

DreamShaper

Wan 2.1

Wan 2.1 is the February 2025 generation of Alibaba's open Wan video models: 1.3B and 14B weights for text-to-video and image-to-video. It has been superseded by Wan 2.2 (July 2025), which gives clearly better motion, detail and prompt…Wan 2.1 is the February 2025 generation of Alibaba's open Wan video models: 1.3B and 14B weights for text-to-video and image-to-video. It has been superseded by Wan 2.2 (July 2025), which gives clearly better motion, detail and prompt following with the same kind of workflows, so there is no reason to start with Wan 2.1 in 2026 or later. This page stays as a reference for the older LoRAs and workflows that were made for it.Hiển thị thêm

Beautiful Realistic Asians

GLM 5.3 Flash

Z.ai | 1,048,576 token context | $0.02/M input, $0.72/M output. GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture…Z.ai | 1,048,576 token context | $0.02/M input, $0.72/M output. GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead. Yes, the stealth model Ox Alpha was revealed to be ZAI's new model, GLM-5.3 Flash.Hiển thị thêm

NTR MIX | illustrious XL | Noob XL XIII

Hy4 preview

Tencent | 1,048,576 token context | $0.83/M input, $2.50/M output. Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows,…Tencent | 1,048,576 token context | $0.83/M input, $2.50/M output. Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.Hiển thị thêm

MiMo V2.6 Flash

Xiaomi | ngữ cảnh 1.050.000 token | $0.14/M đầu vào, $0.28/M đầu ra. MiMo-V2.6-Flash là một mô hình nền tảng mã nguồn mở do Xiaomi phát triển. Xây dựng trên kiến trúc Mixture-of-Experts với tổng số 309 tỷ tham số và 15 tỷ tham số kích hoạt…Xiaomi | ngữ cảnh 1.050.000 token | $0.14/M đầu vào, $0.28/M đầu ra. MiMo-V2.6-Flash là một mô hình nền tảng mã nguồn mở do Xiaomi phát triển. Xây dựng trên kiến trúc Mixture-of-Experts với tổng số 309 tỷ tham số và 15 tỷ tham số kích hoạt mỗi token, nó sử dụng cơ chế chú ý kết hợp để tăng hiệu quả tính toán. Mô hình có cửa sổ ngữ cảnh 1 triệu token và khả năng đa phương thức gốc. Tối ưu cho các quy trình agentic, nó mang lại hiệu suất mạnh mẽ trong các kịch bản lập trình, hình ảnh, tổng quát và nghiên cứu, xuất sắc trong các nhiệm vụ phức tạp, dài hạn với khả năng tổng quát hóa vững chắc trên nhiều dạng agent khác nhau.Hiển thị thêm

chilloutmix

Pony Realism 🌐 v2.2

by ZyloO -- Pony Realism v2.2 Main + VAE tips: use sampler dpm2m, Settings: Steps: >=30 Guidance: 6-9 Clip Skip: 2 Resolution: >1024 Terminology: Recommended the use of "female/male" instead of "woman/man" Additional Information: Use…by ZyloO -- Pony Realism v2.2 Main + VAE tips: use sampler dpm2m, Settings: Steps: >=30 Guidance: 6-9 Clip Skip: 2 Resolution: >1024 Terminology: Recommended the use of "female/male" instead of "woman/man" Additional Information: Use Danbooru tags. Example positive: score_9, score_8_up, score_7_up, asian girl, makeup, goth, emo, portrait, close-up, messy bedroom, supported on bedside table, clutter tattoos, solo, sexy curves, revealing outfit, a latex minidress, depth of field, highly detailed, high contrast, film grain, Rim Lighting — example negative — score_6, score_5, score_4, text, censored, deformed, bad hand — parameters — /guidance:6 /steps:30 /parser:new /clipskip:2 /sampler:dpm2m /karrasHiển thị thêm

ICBINP "I Can't Believe It's Not Photography" SECO

DeepSeek V4 Flash 0731

DeepSeek | 1,048,576 token context | $0.01/M input, $1.28/M output. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for…DeepSeek | 1,048,576 token context | $0.01/M input, $1.28/M output. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.Hiển thị thêm

Unholy Desire Mix Sinister Aesthetic (Illustrious)

majicMIX realistic 麦橘写实

lightning

Detail Tweaker XL

Nemotron 3 Ultra

NVIDIA | ngữ cảnh 262.144 token | $0.60/M đầu vào, $2.40/M đầu ra. NVIDIA Nemotron 3 Ultra là một mô hình tiên phong về suy luận và điều phối từ NVIDIA, với 55 tỷ tham số kích hoạt trên tổng số 550 tỷ tham số (MoE). Xây dựng trên kiến trúc…NVIDIA | ngữ cảnh 262.144 token | $0.60/M đầu vào, $2.40/M đầu ra. NVIDIA Nemotron 3 Ultra là một mô hình tiên phong về suy luận và điều phối từ NVIDIA, với 55 tỷ tham số kích hoạt trên tổng số 550 tỷ tham số (MoE). Xây dựng trên kiến trúc hỗn hợp Transformer-Mamba mixture-of-experts, nó hỗ trợ đầu vào và đầu ra văn bản với cửa sổ ngữ cảnh lên đến 1 triệu token. Mô hình phù hợp cho các quy trình agentic chạy dài, bao gồm điều phối agent, agent lập trình, nghiên cứu sâu và các nhiệm vụ doanh nghiệp phức tạp. Nó đặc biệt mạnh về suy luận và lập kế hoạch nhiều bước, với khả năng suy luận thông lượng cao thiết kế cho các pipeline agent khối lượng lớn. Đây là một phần của dòng mô hình mở NVIDIA Nemotron dành cho AI agentic.Hiển thị thêm

Step 5 Preview

StepFun | 1,048,576 token context | $1.00/M input, $2.70/M output. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in…StepFun | 1,048,576 token context | $1.00/M input, $2.70/M output. Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance. It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.Hiển thị thêm

ZUKI anime ILL

by Zu_Ki - Hentai capable illustrious model. Prompt： masterpiece,best quality,amazing quality,very aesthetic,absurdres, Negative prompt： lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn,…by Zu_Ki - Hentai capable illustrious model. Prompt： masterpiece,best quality,amazing quality,very aesthetic,absurdres, Negative prompt： lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, censor,blurry, watermark,simple background, transparent background, CFG:3~12 STEPS:30Hiển thị thêm

AbyssOrangeMix3 (AOM3)

One obsession

CyberRealistic Final

Add More Details Detail Enhancer / Tweaker (细节调整) LoRA

Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA by Lykon writes: his between 0.5 and 1 weight, depending on your preference. You can go lower than 0.5 for a more subtle effect, of course. I also found out that this gives some…Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA by Lykon writes: his between 0.5 and 1 weight, depending on your preference. You can go lower than 0.5 for a more subtle effect, of course. I also found out that this gives some interesting results at negative weight, sometimesHiển thị thêm

[MMH3] Mystic XXX v4.0 (FL2VA & REF2VA)

By alcaitiff - (v4) MiniMax H3 general NSFW motion and anatomy helper LoRA, improves on mystic3-h3 and mystic-v2-h3 with higher resolution during the training process. Author notes it has better motion quality, temporal stability, and fine…By alcaitiff - (v4) MiniMax H3 general NSFW motion and anatomy helper LoRA, improves on mystic3-h3 and mystic-v2-h3 with higher resolution during the training process. Author notes it has better motion quality, temporal stability, and fine detail. No specific trigger needed in prompt, just be specific about what you want to see in your prompts.Hiển thị thêm

waifu

waifu-diffusion by hakurei. A long running base model trained on crisp-looking anime. Compared to your other anime base model options, this one is fairly well-rounded, which unfortunately has been detrimental in making it a clear winner in…waifu-diffusion by hakurei. A long running base model trained on crisp-looking anime. Compared to your other anime base model options, this one is fairly well-rounded, which unfortunately has been detrimental in making it a clear winner in any category.Hiển thị thêm

Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious + ZiT + Anima + Krea2 Flux Original

hyper