Kör lokalt
nextphoto_v30.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Nedladdningar sköts av Civitai. Vissa skapare kräver att du först loggar in på Civitai.
Om denna modell
STABLE DIFFUSION 1.5 · Basmodeller
NextPhoto v3.0 model by bigbeanboiler
Skaparens anteckningar
NOTE: This model has it's own VAE, which is baked into the model. For best results, please ensure that the selected VAE in automatic1111 is set to "Automatic". If you've never poked around in the VAE settings, this will be the default.
NextPhoto is the result of a whole lot of training, data curation, and block merging. The model is designed exclusively for the generation of photo-realistic photos, and as such it cannot generate non-photo images (even if prompted to do so). For more details about version 3.0, check out the "About this version".
All sample images were generated using ESRGAN_4x upscaling model at 2x upscaling, with 0.45 denoising strength. I'm not gonna upload a 32 bit model, as the v3 model was trained using 16bit precision, so it would literally just be a waste of space.
Usage Guide
-
(highly recommended) The negative prompt is quite important for the photorealism, but you don't really have to change it ever to get great results. I'd recommend the following negative prompt as a base: (worst quality:0.8), cartoon, halftone print, burlap,(cinematic:1.2), (verybadimagenegative_v1.3:0.3), (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
-
This prompt uses the verybadimagenegative_v1.3 textual embedding. You'll need
-
-
Place the downloaded file into the "embeddings" folder of the SD WebUI root directory, then restart stable diffusion.
-
Positive Prompts: You don't need to think about the positive a whole ton - the model works quite well with simple positive prompts.
-
Examples:
-
A well-lit photograph of woman at the train station
-
A perfect well-lit medium photograph of an old married couple sitting on their porch
-
A poorly lit photograph of a man walking on the trail at night
-
For more examples of positive prompts you can look at the sample photos for the model.
-
Upscaling: This model works will still generate photorealistic images without upscaling, but upscaling is strongly recommended for photorealism. You'll need to use the ESRGAN_4x upscaling model (not R-ESRGAN) in the hires fix section for decent results. Set the weight anywhere from 0.3 to 0.5 for best results, and the upscale amount to 2. I normally set my weight to 0.5 or 0.45.
-
Sampler: I use DPM++ 2M Karas, and generally don't stray from it. While the other samplers can still produce good results, DPM++ 2M Karas is the most consistent in my experience with this model.
-
For further improvements:
-
Reduce your CFG scale: The default classifier free guidance scale scale of 7 works good, but occasionally this can be too high. Reduce the CFG scale until you like the results - I generally bottom out at 4.0, as anything lower than that and the negative prompt starts getting ignored. Increasing the CFG scale past 7 or 8 will result in more "dramatized" photos (not in a good way), but will also result in the model listening more to the prompts, so balance as needed. High CFG scales can work well for specific situations, but lower CFG scales work great quite consistently.
-
Avoid excess LORA and Textual Inversion use: As v2 and v3 of this model are custom trained and not purely block merged, any LORAs or Textual Inversions may not work as well as they do in other models. Based on my experience, you can still get good results with them, but I'd recommend treading lightly - I'd recommend an additive approach where you add LORAs or inversions selectively when needed.
Triggerord
photo
photograph
SHA256
1C1F913F3B87D9FE5161C005CB12AA429193DA241D1C624AA20E749CD5A95A17
ModelTrends.ai modell-ID
#8095
Rapportera innehåll
Exempelrenderingar
Prompter och inställningar delade av personerna som gjorde dessa renderingar på Civitai. Välj en rendering för att se hur den gjordes.
Inställningar
Sampler
DPM++ 2M SDE Karras
Steg
20
Guidance
7
Seed
150371218
Storlek
512x768
Prompt
Blacked out fallen open true refuge issueless towards which so many false time out of mind. Never but silence such that in imagination this wild laughter these cries. Head through calm eye all light white calm all gone from mind. Figment dawn dispeller of figments and the other called dusk. <lora:DestroyedPortrait-000150:0.3> <lora:psychedelic_noir-10:0.6> <lora:Watercolor-000012:0.4>, hologram floating in space, a vibrant digital illustration, dribbble, quantum wavetracing, black background, behance hd
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
5
Seed
4257299988
Storlek
512x640
Prompt
A well lit candid closeup street photograph of a normal, yet beautiful woman posing in the club
Negativ prompt
(worst quality:0.8), cartoon, halftone print, burlap, candle, (verybadimagenegative_v1.3:0.3), (cinematic:1.2), (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
4
Seed
3082189737
Storlek
512x768
Prompt
a perfect well-lit (closeup:1.15) (medium shot portrait:0.6) photograph of a beautiful woman standing on the hiking trail, wearing an intriguing outfit, looking at me, coy slight smile
Negativ prompt
(worst quality:0.8), cartoon, halftone print, burlap, floral, (verybadimagenegative_v1.3:0.3), (cinematic:1.2), (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
Inställningar
Sampler
Euler a
Steg
30
Guidance
9
Seed
1272657414
Storlek
584x1024
Prompt
photo, photograph cinematic photo a car with big_tires, reflective, hyper detailed, ultra sharp, film, ultra realistic, ((best quality, symmetry)), ((masterpiece)), ((realistic)), silicone, metal, (highly detailed, fine details, intricate), (lens flare:0.5), (bloom:0.5), raytracing, specular lighting, (((depth of field, cinematic film still))), (no_humans) . 35mm photograph, film, bokeh, professional, 4k, highly detailed
Negativ prompt
drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, EasyNegativeV2,wrong_hands,(low quality:2),(normal quality:2),(( text, wire, logo)), humans
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
6
Seed
1724033189
Storlek
512x640
Prompt
a perfect well-lit closeup full body photograph of a pretty woman with a cute smile wearing (a casual outfit:0.5) while hiking in the wild
Negativ prompt
(worst quality:0.8), cartoon, halftone print, burlap, candle, (verybadimagenegative_v1.3:0.3), (cinematic:1.2), (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
Inställningar
Sampler
DPM++ 2M SDE Karras
Steg
40
Guidance
7
Seed
1627466517
Storlek
512x768
Prompt
(masterpiece, best quality, high resolution:1.2), (cowboy shot:1.2), (seductive pose:1.2)
professional photo, HDR, natural light, (anti-aliasing:1.2), elegant, soft scattered light, realistic proportions, limited palette, backlit, accent lighting, (neutral colors:1.3), cross process, cinematic lighting, coherent light, coherent shadows, depth of field, 35mm photograph, film grain, film stock photograph ,kodak portra 400 ,camera f1.6 lens ,lifelike texture,
detailed face, detailed eyes, detailed skin, extremely detailed, intricate details,
<lora:YoM_HWMichelle:1>, (1girl, 38 years old), yom_hwmichelle, solo, realistic, blonde hair, blue eyes, seductive smile, dress, sitting, from side,
Negativ prompt
(worst quality:2), (low quality:2), (normal quality:2), lowres, (monochrome:1.21), (grayscale:1.21), signature, watermark, ((bad-hands-5)), epiCNegative
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
5
Seed
679923601
Storlek
512x640
Prompt
A well lit photograph of a man having a great time dancing at the [party|club]
Negativ prompt
(worst quality:0.8), cartoon, halftone print, burlap, (verybadimagenegative_v1.3:0.3), (cinematic:1.2), (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
Inställningar
Sampler
DPM++ 2M Karras
Steg
20
Guidance
5
Seed
704337207
Storlek
512x640
Prompt
A well lit candid closeup street portrait photograph of a normal, yet beautiful woman walking down the street
Negativ prompt
(worst quality:0.8), cartoon, halftone print, burlap, candle, (verybadimagenegative_v1.3:0.3), (cinematic:1.2), (surreal:0.8), (modernism:0.8), (art deco:0.8), (art nouveau:0.8)
Liknande modeller
AI-modeller för bild-, video- och textgenerering
nextphoto3 är en basmodell för familjen Stable Diffusion 1.5, listad på ModelTrends.ai, en skrivskyddad katalog över AI-modeller med öppen källkod för bild, video och text. Jämför den med andra Stable Diffusion 1.5-modeller, se dess hettapoäng och prova den på PirateDiffusion eller BitVector.
Fler Stable Diffusion 1.5-modellerFler Stable Diffusion 1.5 Basmodellerrealisticbasephotostyleeasyphotorealistic
Bläddra efter modellfamilj
Text / LLM-modeller
411
Anima-modeller
509
Chroma-modeller
14
Flux-modeller
1,071
Flux 2 / Klein-modeller
1,237
MiniMax H3-modeller
331
Hunyuan-modeller
197
Ideogram-modeller
20
Krea2-modeller
674
Qwen-modeller
17
Qwen2-modeller
36
Ltx2-modeller
150
Stable Diffusion 1.5-modeller
6,465
Stable Diffusion XL 1.0-modeller
15,432
Zimage-modeller
804
Wan-modeller
919

Model
Trends
.ai
© ModelTrends.ai
|
Tillverkad i Japan
|
© 2026
