Model
Trends
.ai
Model
Trends
.ai
nejlepší open source AI modely

Nejlépe hodnocené AI modely podle kategorie a času

Celý katalog v pořadí podle žhavosti, nejžhavější první. Hledejte a filtrujte, abyste viděli, kde model stojí mezi svými protějšky. Je to přes 9000.
Hledat
Filtrovat podle času:
Filtrovat podle štítku:
NSFW
30,815 modelů · strana 1 z 344
  1. #1
    #1
    FLUX 2 / KLEIN
    •
    BASE
    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,…
    9831°
    Zlato · Za celou dobu
  2. #2
    #2
    FLUX
    •
    BASE
    The fastest Flux DEV fp8 workflow, supports up to 5 loras. Built-in upscaler is a factor of 1.4, modify with /slot8
    9821°
    Stříbro · Za celou dobu
  3. #3
    #3
    QWEN
    •
    BASE
    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…
    9730°
    Bronz · Za celou dobu
  4. #4
    #4
    STABLE DIFFUSION XL 1.0
    •
    BASE
    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…
    9658°
  5. AD
    Bez instalace - spouštějte AI modely v cloudu
    BitVector Prism je nejsnazší způsob, jak začít: vyberte model, napište prompt a generujte v přehledné webové aplikaci, bez jakéhokoli nastavování. BitVector je k dispozici také na Discordu a na webu (SpyGlass).
  6. #5
    #5
    STABLE DIFFUSION XL 1.0
    •
    BASE
    9587°
  7. #6
    #6
    STABLE DIFFUSION 1.5
    •
    BASE
    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…
    9546°
  8. #7
    #7
    9493°
  9. #8
    #8
    STABLE DIFFUSION XL 1.0
    •
    BASE
    9457°
  10. #9
    #9
    9422°
  11. #10
    #10
    STABLE DIFFUSION 1.5
    •
    BASE
    Dreamshaper 8 by Lykon is one of the most popular base models for illustrations and art. This update includes better support for character LoRAs, better photorealism, can still handle anime, and better NSFW
    9419°
  12. #11
    #11
    STABLE DIFFUSION XL 1.0
    •
    BASE
    by tkio - NTR MIX | illustrious-XL | Noob-XL
    9314°
  13. #12
    #12
    STABLE DIFFUSION XL 1.0
    •
    LORA
    9300°
  14. #13
    #13
    STABLE DIFFUSION 1.5
    •
    BASE
    ICBINP - "I Can't Believe It's Not Photography" SECO by Residentchiefnz
    9278°
  15. #14
    #14
    9233°
  16. #15
    #15
    STABLE DIFFUSION XL 1.0
    •
    LORA
    The "hyper-xl" model is optimized to significantly increase generation speed.
    9231°
  17. AD
    PirateDiffusion
    Bez instalace - spouštějte AI modely v cloudu
    PirateDiffusion je pouze na Telegramu a je stavěný pro profesionály: tisíce modelů, LoRA a workflow ovládaných chatovými příkazy, s neomezeným generováním za pevnou cenu.
  18. #16
    #16
    STABLE DIFFUSION 1.5
    •
    BASE
    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…
    9223°
  19. #17
    #17
    STABLE DIFFUSION 1.5
    •
    BASE
    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…
    9206°
  20. #18
    #18
    STABLE DIFFUSION 1.5
    •
    BASE
    majicMIX realistic 麦橘写实 model by Merjic
    9205°
  21. #19
    #19
    STABLE DIFFUSION 1.5
    •
    BASE
    BB95 Furry Mix v9.0 by Bumbleblee95 One of the best furry models out there. It's a mix of various models and can generate various anthro ideas. It's doing well in generating photorealistic males and females. SFW and NSFW. Example positive:…
    9151°
  22. #20
    #20
    STABLE DIFFUSION XL 1.0
    •
    BASE
    Prefect (sic) Pony V3 by GoofyAI is a pony diffusion fine tune with better support for loras, and better eyes and faces than the previous versions. Clipskip 2 is recommended.
    9131°
  23. #21
    #21
    STABLE DIFFUSION 1.5
    •
    BASE
    Realistic Vision V6.0 B1 model by SG_161222. This is not yet the full version of the model. Creator's Recommended Generation Parameters Sampler: DPM++ SDE Karras (25+ steps) / DPM++ 2M SDE (50+ steps) Negative Prompt: (deformed iris,…
    9114°
  24. #22
    #22
    9056°
  25. #23
    #23
    STABLE DIFFUSION 1.5
    •
    BASE
    Rev Animated 2.0 is under new management - the project is now maintained by Zovya This is a remaster of the classic popular Revani series for SD15
    9049°
  26. #24
    #24
    STABLE DIFFUSION XL 1.0
    •
    BASE
    by Crody - Recommended settings: Sampler: DPM++ 2M SDE Karras for best results, Euler a for best performance Steps: 20-50 steps, (Illustrious) CFG Scale: 3-5 Prompt: masterpiece, best quality, amazing quality, very aesthetic, high…
    9041°
  27. #25
    #25
    STABLE DIFFUSION 1.5
    •
    BASE
    Deliberate 2 has been called "the NSFW master's toolkit", boasting the best balance of detailed backgrounds, light effects, skin texture, and accurate prompts at the time of its release. Incredibly versatile, though prompts tend to run on…
    9013°
  28. AD
    Bez instalace - spouštějte AI modely v cloudu
    BitVector Prism je nejsnazší způsob, jak začít: vyberte model, napište prompt a generujte v přehledné webové aplikaci, bez jakéhokoli nastavování. BitVector je k dispozici také na Discordu a na webu (SpyGlass).
  29. #26
    #26
    STABLE DIFFUSION XL 1.0
    •
    BASE
    by Ikena - Hassaku XL (Illustrious) V3.4
    8992°
  30. #27
    #27
    STABLE DIFFUSION 1.5
    •
    BASE
    Epic Diffusion by johnslegers. A general purpose model based on Stable Diffusion 1.x intended to replace the official SD releases as your default model. It is focused on providing high quality output in a wide range of different styles,…
    8939°
  31. #28
    #28
    STABLE DIFFUSION XL 1.0
    •
    BASE
    Dreamshaper SDXL Lightning by Lykon is a low steps version of the popular model family. This version slightly trades off quality for speed - and still looks amazing. Experiment with settings like: /guidance:2 /steps:6 /nofix
    8937°
  32. #29
    #29
    STABLE DIFFUSION XL 1.0
    •
    BASE
    This is the 1024 Aesthetic version of the general purpose Playground 2 concept, a rebuild of SDXL. Try it as a second opinion when you don't like what gives you. It can handle realism as well as paintings and ilustrations
    8928°
  33. #30
    #30
    STABLE DIFFUSION XL 1.0
    •
    BASE
    Blender animation model by Guy90. Recommended settings: Sampler: Euler a, DPM++ 2S a, DPM++ 2M Karras Sampling Steps: 20+ CFG Scale: 7
    8924°
  34. #31
    #31
    STABLE DIFFUSION 1.5
    •
    BASE
    Photon by Photographer makes photorealistic images effortlessly. Example prompt from the creator /seed:3883312123 /sampler:dpm2m /size:768x512 /steps:20 /guidance:6 A photo of a young, nerdy woman sitting in a caf, wearing a white shirt…
    8916°
  35. #32
    #32
    FLUX
    •
    BASE
    8905°
  36. #33
    #33
    8903°
  37. #34
    #34
    8901°
  38. #35
    #35
    8891°
  39. #36
    #36
    STABLE DIFFUSION XL 1.0
    •
    BASE
    This is the old version of Illustrious by request, version beta .01. The new full version 1 is also available but works best as a workflow, or partially with render when using euler_a
    8885°
  40. #37
    #37
    STABLE DIFFUSION 1.5
    •
    BASE
    iCoMix v5 by lostdog Easy to use comics model. Version 5 is less 'cutesy' than previous ones and better fulfils its role as a comics model. The colours are also better and less grainy. Negative prompts that work well with it: (worst…
    8882°
  41. #38
    #38
    STABLE DIFFUSION 1.5
    •
    BASE
    Edge of Realism by AreThoseLevel4Plates, from the maker of it's more famous cousin, . Edge Version 2.0 is a photorealistic model. The base is Level 4 but using high quality original photos for a completely different look. Easy to prompt…
    8860°
  42. #39
    #39
    STABLE DIFFUSION 1.5
    •
    BASE
    VAE Natural Sin Final and last of epiCRealism by epinikion, a realistic base model. Notes from the creator: add "asian, chinese" to negative if you're looking for ethnicities other than Asian Light, shadows, and details are excellent…
    8855°
  43. #40
    #40
    KREA2
    •
    LORA
    by alcaitiff - [KREA 2] Detail Slider
    8851°
  44. #41
    #41
    STABLE DIFFUSION XL 1.0
    •
    BASE
    8849°
  45. #42
    #42
    STABLE DIFFUSION 1.5
    •
    BASE
    Ghibli Diffusion by Nitrosocke was a face-melting anime model of its time, one of the first to cement the idea that Stable Diffusion could one day be stable enough to create films in any distinctive art style, such as that by Japanese art…
    8846°
  46. #43
    #43
    STABLE DIFFUSION 1.5
    •
    BASE
    Beautiful Realistic Asians v7 model by pleasebankai
    8841°
  47. #44
    #44
    STABLE DIFFUSION 1.5
    •
    BASE
    NeverEnding Dream version 1.22 (installed May 26th) by Lykon is the model to use when DreamShaper is too fantasy, and AnyLora is too anime. NED fits snuggly between the two. This is a full base model designed for high compatibility with…
    8836°
  48. #45
    #45
    MINIMAX H3
    •
    LORA
    by tsolful - Minimax H3 Turbo Loras larryvrh_4step_pruned
    8835°
  49. #46
    #46
    STABLE DIFFUSION 1.5
    •
    BASE
    Disney Pixar Cartoon Type A v1.0 by PromptSharingSam6319 is a versatile model that can do both disney-like and pixar-like renders. It's more than capable for picking up the work of old and models. Tip: If your results come out blurry and…
    8831°
  50. #47
    #47
    STABLE DIFFUSION 1.5
    •
    BASE
    8829°
  51. #48
    #48
    STABLE DIFFUSION 1.5
    •
    BASE
    Dreamlike Diffusion 1.0 by sviasem is an older but solid illustration and semi-real base model, best for playful colorful images like stock photos and concept art. Dreamlike has an incredible range and is easy to work with, one of the…
    8827°
  52. #49
    #49
    STABLE DIFFUSION 1.5
    •
    BASE
    Lyriel version 1.6 by FIKOsofter is a popular general model but is best known for dramatic portraits and strong results with just short prompts. This might be the last update, as the creator was kicked from Civitai for manipulating…
    8826°
  53. #50
    #50
    8819°
  54. AD
    PirateDiffusion
    Bez instalace - spouštějte AI modely v cloudu
    PirateDiffusion je pouze na Telegramu a je stavěný pro profesionály: tisíce modelů, LoRA a workflow ovládaných chatovými příkazy, s neomezeným generováním za pevnou cenu.
Žhavost je naše interní skóre trendu od chladné po 9999°. Každý den se mění podle signálů využití a popularity z komunit a služeb kolem každého modelu. Žebříček zahrnuje základní modely, LoRA, embeddingy a textové modely napříč všemi rodinami v katalogu.
Procházet podle rodiny modelů