Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
crossroads_v10AlphaNoVae.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<crossroads>
About This Model
STABLE DIFFUSION 1.5 · Base Models
Created by
soul3142
on Civitai
Crossroads model by Soul3142. Creator recommends: VAE : vae-ft-mse-840000-ema-pruned Clip Skip : 2 Min Resolution : 512x768 Hires-Fix : 1.5-2x Upscaler : 4xUltraSharp Denoising : 0.3-0.5 ENSD : 31337 Sampler : Upto you, but i use Euler a mostly For Better Faces/Eyes : install & use After Detailer Min Steps : 20 CFG : 5-9 Sample Negative Prompt : verybadimagenegative_v1.3, bad_prompt_version2, easynegative, bad-hands-5,
Creator notes
Usually my LoRA testing ground, someone asked for it so i'll just post it here. Not the easiest or best model to work with but hey its here if you want to try it. More examples are in images section using wildcards, randomized prompts and my own LoRA's. RECOMMENDATIONS : - VAE : - Clip Skip : 2 - Min Resolution : 512x768 - Hires-Fix : 1.5-2x - Upscaler : - Denoising : 0.3-0.5 - ENSD : 31337 - Sampler : Upto you, but i use Euler a mostly - For Better Faces/Eyes : install & use - Min Steps : 20 - CFG : 5-9 - Sample Negative Prompt : , , , , - For Higher Res Image generation on weaker hardware : enable xFormers, lowvram, use set token merging ratio to 0.2-0.3. Also for better details - My general upscaling method : 512x768 txt2img, 2x hires-fix with 4xUltrashap, 0.4 Denoising -> send to img2img -> with Tiled Diffusion & VAE.
2,274 downloads · 310 likes on Civitai
SHA256
8BE8A4378F09F9026A282249DD94B5711A0F62E2130515005DBB0C70EF9091F7
ModelTrends.ai Model ID
#8749
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 3M SDE
Steps
35
Guidance
6
Seed
1146825990
Size
512x768
Clip skip
2
Prompt
ciriW3_soul3142, 1girl, white hair, scar across eye, green eyes, freckles, detailed skin, masterpiece, best quality, intricate details, <lora:ciriW3-08b:0.6>, <lora:detail_slider_v4:0.7>
Negative prompt
(bad quality, worst quality:1.3), verybadimagenegative_v1.3, bad_prompt_version2, easynegative, ng_deepnegative_v1_75t
Settings
Sampler
Euler a
Steps
25
Guidance
8
Seed
1551373075
Size
512x768
Clip skip
2
Prompt
ship, sea, gwentCB01_soul3142,<lora:gwentCB01-10:0.9>,
Negative prompt
(easynegative:1.1), ng_deepnegative_v1_75t
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
6
Seed
2237190759
Size
1280x1920
Prompt
absurdres, highres, best quality, masterpiece, <lora:Breast Press V2-000011:0.7> breast press, multiple girls, 2girls, classroom, blackboard, (bokeh:1.1), evil smile, <lora:thickline_fp16:0.4> <lora:videl_v3:0.8> blue eyes, black hair, white t-shirt, black gloves, bike shorts, videl2, low twintails, <lora:erasa_dragonball:0.7> erasa db, blonde hair, short hair, blue eyes, large breasts, earrings, strapless tanktop, green tanktop, striped tanktop, horizontal stripes, purple pants, long pants, belt,
Negative prompt
(worst quality, low quality, blurry:1.4), generic, boring, sketch, easynegative, verybadimagenegative_v1.3, bad-picture-chill-75v, bad-artist, badhandv4, Unspeakable-Horrors-Composition-4v, (text, signature, watermark:1.2), (animal ears:1.4), (solo:1.4)
Settings
Sampler
DPM++ 3M SDE
Steps
35
Guidance
6
Seed
686497218
Size
512x768
Clip skip
2
Prompt
ciriW3_soul3142, 1girl, green eyes, white hair, (scar across eye), chainmail, shoulder armor, fingerless gloves, midriff, looking up, full body, hand on hip, night sky, masterpiece, best quality, intricate details, <lora:ciriW3-08b:0.65>, <lora:detail_slider_v4:0.7>
Negative prompt
(bad quality, worst quality:1.3), verybadimagenegative_v1.3, bad_prompt_version2, easynegative, ng_deepnegative_v1_75t
Settings
Sampler
Euler a
Steps
25
Guidance
7
Size
512x768
Clip skip
2
Prompt
(masterpiece, best quality:1.2), <lora:triss-15:0.6>, trissW3_soul3142, 1girl, solo, looking at viewer, red hair, green eyes, closed mouth, mole, portrait, mole under mouth, freckles, realistic, <lora:add_detail:0.6>,
Negative prompt
(easynegative), ng_deepnegative_v1_75t, (bad-hands-5), (worst quality, low quality:1.4)
Settings
Sampler
Euler a
Steps
25
Guidance
8
Seed
1501454741
Size
512x768
Clip skip
2
Prompt
christmas, frame, gwentCB01_soul3142,<lora:gwentCB01-10:0.9>,
Negative prompt
easynegative, ng_deepnegative_v1_75t
Settings
Sampler
DPM++ 3M SDE
Steps
35
Guidance
6
Seed
4190165262
Size
512x768
Clip skip
2
Prompt
ciriW3_soul3142, 1girl, white hair, scar across eye, green eyes, celebration, champagne, elegant, dress, jewelry, cowboy shot, masterpiece, best quality, intricate details, <lora:ciriW3-08b:0.6>, <lora:detail_slider_v4:0.7>
Negative prompt
(bad quality, worst quality:1.3), verybadimagenegative_v1.3, bad_prompt_version2, easynegative, ng_deepnegative_v1_75t
Settings
Sampler
Euler a
Steps
25
Guidance
7
Size
512x768
Clip skip
2
Prompt
lamborghini, dynamic angle, smoke, city, cyberpunk, rain, night, street, fog, reflections, <lora:LowRA:0.5> <lora:add_detail:0.5>
Negative prompt
(bad quality, worst quality:1.3), (bad-hands-5), verybadimagenegative_v1.3, bad_prompt_version2, easynegative,
AI Models for Image, Video & Text Generation
crossroads is a base model for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models