sr alpha3
Vergleichen
7615°
Lokal ausführen
srAlpha_v3.safetensors
2.24 GB · SafeTensor · fp16 · pruned
blessed2.vae.safetensors
160 MB · SafeTensor
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<sr-alpha3>
Über dieses Modell
STABLE DIFFUSION 1.5 · Basismodelle
Notizen des Erstellers
SR-Alpha aims to combine comic art style with semi-realistic textures.
I highly recommend inpainting for best results and to unlock the full potential of the merge. Separate inpainting model not required.
To help with inpainting human features, I have also been tinkering with this extension called , which automatically detects and "fixes" the portion of the image being generated via txt2img depending on the "ADetailer" model used, notably the models for the hands and face which I use most often.
PS:
I no longer remember the exact models used for versions 1-1.2. I believe that with the new update, the old versions would be rendered obsolete.
V2 and V3 Mix Recipe:
-
-
-
-
(used in V3)
Recommended Settings:
V 1.0:
-
Sampling Method: DPM++ SDE Karras
-
Sampling Steps: 50
V1.1 and above:
-
Sampling Method: DPM++ 2M Karras, Euler A (Inpainting)
-
Sampling Steps: 20-30
CFG = 7-10
Denoising Strength = 0.4-0.5 (general), 0.2-0.3 (inpainting hands)
Workflow (used in V3 samples):
-
txt2img
>Initial dimensions 512x615 (WxH)
>Hi-res fix by 1.25x to get 640x768 dimensions
>Adetailer enabled using either 'face_yolov8n' or 'mediapipe_face_mesh'
-
inpainting
>Inpaint areas to improve quality. Do it part by part so that focused area will be altered with best results.
-
Upscaling (optional): Upscale images by 2.25x
Method A.:
Upscaler 1 (U1) = Lanczos
U2 = R-ESRGAN General WDN 4xV3
U2 Visibility = 0.5
GFPGAN visibility = 0.3
Method B.:
U1 = 4xNMKDSuperscale_4xNMKDSuperscale
Suggested Embeddings:
-
-
-
-
-
-
-
VAE:
-
-
Credits to the respective original creators of the resources used.
SHA256
80B617DCF645657FB1083F037C1D47EEF37E280313EDCBBE98FB5085E540C2D1
ModelTrends.ai-Modell-ID
#1881
Inhalt melden
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Einstellungen
Sampler
UniPC
Schritte
35
Guidance
7
Seed
3131190891
Größe
384x576
Clip skip
2
Prompt
1girl, barbarian queen, majectic, toned body, giant axe, full body, pale skin, snow, dynamic pose, perspective, axe swing, fur cape, iron gauntlet, iron tunic, long blonde flowing hair,, mature woman, <lora:UnlimitedBladeWorks1.6:0.5> Axe <lora:LnF:0.15> LnF <lora:Painted_poster_V1-000035_1_pp:0.25> Painted poster, 1girl <lora:EF-LowRA:0.15> dark theme <lora:Ladies Armor - Life Like Diffusion:0.15> <lora:EF-add_detail:0.5>, snowy battlefield <lora:DarkSpheraStyle:0.25> DarkSpheraStyle <lora:cool girl_20230913102000:0.5> cool girl <lora:ww:0.25> <lora:aki:0.15> alphonse mucha<lora:EF-GoodHands-beta2:0.5><lora:EF-GoodHands-beta2:0.5>
Negativer Prompt
(worst quality, low quality:1.4) aid210 bad-artist-anime bad-hands-5 BadDream, city negative_hand-neg ng_deepnegative_v1_75t verybadimagenegative_v1.3
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
20
Guidance
7
Seed
3457260380
Größe
640x768
Clip skip
2
Prompt
woman, (bodybuilder), (dark skin:1.3), (perfect face), defined jawline, beautiful dark purple lips, (beautiful bright pink eyes), (purple cornrows, braided, hip-hop style hair:1.2), (perfect anatomy), (athletic body), (muscular), (sexy), (large breasts:1.2), (large beefy arms:1.2), (black sports bra:1.2), (orange sweatpants:1.2), (standing, hands behind head), (looking at viewer), (medium shot photograph), (gym background), realistic
Negativer Prompt
ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-artist, bad-hands-5, wrinkles, (out of frame, off-centered:1.2), (close-up shot photograph:1.2), (multiple people in frame:1.2), against the light, (watermark, text, signature:1.2), jewelry
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
20
Guidance
7
Seed
1140974499
Größe
640x768
Clip skip
2
Prompt
woman, (dark skin:1.2), (perfect face), defined jawline, beautiful lips, (beautiful bright red eyes), (voluptuous), (long braided undercut hairstyle, fade, white blonde hair:1.2), (fitted black formal suit:1.2), (black necktie), (looking at viewer), (cowboy shot photograph), (modeling studio background), realistic
Negativer Prompt
ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-artist, bad-hands-5, wrinkles, (big anime eyes), (out of frame, off-centered:1.2), (close-up shot photograph:1.2), (multiple people in frame:1.2), against the light, (watermark, text, signature:1.2), (makeup, lipstick:1.2), jewelry
Einstellungen
Sampler
Euler a
Schritte
20
Guidance
7
Seed
562998769
Größe
640x768
Clip skip
2
Prompt
woman, (perfect face), defined jawline, beautiful lips, (beautiful bright pink eyes), (long wavy flowing blonde hair), (perfect anatomy), (athletic body), (sexy), (vibrant red intricate elegant maxi dress:1.2), (gold jewelry) (standing, hand on waist, model pose), (looking at viewer), (luxurious hall background), (medium shot photograph, vibrant fashion magazine cover style photography), realistic
Negativer Prompt
ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-artist, bad-hands-5, wrinkles, (out of frame, off-centered:1.2), (close-up shot photograph:1.2), (multiple people in frame:1.2), against the light, (watermark, text, signature:1.2), (belly button)
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
20
Guidance
7
Seed
3656803062
Größe
768x512
Clip skip
2
Prompt
BlackworkStyleManityro, <lora:BlackworkStyle_V1-Manityro-AdamW:1.0>, monochrome, greyscale, outdoors landscape of a tundra with mountains in the distance
Negativer Prompt
(worst quality:1.4), (low quality:1.2), detailed
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
20
Guidance
7
Seed
1297767
Größe
640x768
Clip skip
2
Prompt
lizard girl hybrid, yellow eyes, (long flowing silver hair), (sexy), goat horns, (detailed red scaly skin), (intricate red scaly dragon armor), looking at viewer, (medium shot photograph), (dark flaming background), realistic
Negativer Prompt
ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-artist, bad-hands-5, wrinkles, (out of frame, off-centered:1.2), (close-up shot photograph:1.2), (multiple people in frame:1.2), against the light, (watermark, text, signature:1.2), (makeup, lipstick:1.2), jewelry, (metal), (steel)
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
20
Guidance
7
Seed
1924938894
Größe
640x768
Clip skip
2
Prompt
woman, (dark skin:1.3), (perfect face), defined jawline, beautiful lips, (beautiful bright yellow eyes), (black eyeliner), (short black bob haircut, straight bangs), (black wolf ears on top of head), (perfect hands), (intricate white bandeau top), (exposed midriff), (white long dress), (ancient Egyptian jewelry), sitting on a stone ledge, looking at viewer, (medium shot photograph), (river oasis background), realistic
Negativer Prompt
ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-artist, bad-hands-5, wrinkles, (out of frame, off-centered:1.2), (close-up shot photograph:1.2), (multiple people in frame:1.2), against the light, (watermark, text, signature:1.2), (lipstick:1.2), (human ears:1.2)
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
20
Guidance
7
Seed
3954582973
Größe
640x768
Clip skip
2
Prompt
woman, (detailed skin), (perfect face), defined jawline, beautiful lips, (beautiful smile, cute cheerful facial expression), (beautiful bright blue eyes), (blonde hair, dutch braids), (perfect anatomy), (athletic body), (sexy), (cleavage), (German Oktoberfest barmaid outfit:1.2), (checkered plaid pleated skirt), (standing), (holding a large beer mug on each hand), (looking at viewer), (medium shot photograph), (medieval tavern interior background), realistic
Negativer Prompt
ng_deepnegative_v1_75t, bad-picture-chill-75v, bad-artist, bad-hands-5, wrinkles, (out of frame, off-centered:1.2), (close-up shot photograph:1.2), (multiple people in frame:1.2), against the light, (watermark, text, signature:1.2), (makeup, lipstick:1.2), (jewelry), (hands:1.2)
Ähnliche Modelle
KI-Modelle für Bild-, Video- und Texterzeugung
sr alpha3 ist ein Basismodell für die Familie Stable Diffusion 1.5 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Stable Diffusion 1.5-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Weitere Stable Diffusion 1.5-ModelleWeitere Stable Diffusion 1.5 Basismodelleanimecomicsdrawingsbasecharactervideo gamefantasy25d
Nach Modellfamilie stöbern
Text / LLM-Modelle
411
Anima-Modelle
509
Chroma-Modelle
14
Flux-Modelle
1,071
Flux 2 / Klein-Modelle
1,237
MiniMax H3-Modelle
331
Hunyuan-Modelle
197
Ideogram-Modelle
20
Krea2-Modelle
674
Qwen-Modelle
17
Qwen2-Modelle
36
Ltx2-Modelle
150
Stable Diffusion 1.5-Modelle
6,465
Stable Diffusion XL 1.0-Modelle
15,432
Zimage-Modelle
804
Wan-Modelle
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
