Model
Trends
.ai
Model
Trends
.ai
los mejores modelos de IA de código abierto
Ejecutar en local
realismByStableYogi_xlV3VAE.safetensors
6.46 GB · SafeTensor · fp16 · full
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
AD
<stableyogi-realism3-xl>
Sobre este modelo
STABLE DIFFUSION XL 1.0 · Modelos base
Creado por
Stable_Yogi
en Civitai
REALISM_XL_V3_VAE_BY_STABLE_YOGI Configuration for this Checkpoint CFG 4.5 or upto 9 Steps 27+ Resolutions: 720x1170, 768x1024, 810x1260 and others as required. Adetailer (Required) High res Fix (Required)
Notas del creador
Pro Version of Realism Pony V4-V5-V6 now. Onsite generations are permanently available on these models: 👉 Realism_By_Stable_Yogi V3: Realism by Stable Yogi Pony V6.5 V6.5 is here — and you all helped build it. Real thank-you to everyone who pushed V6 hard, sent feedback, and posted the broken hands. V6.5's fix list literally came from you. Anatomy, hand grips, expressions, twin-tails, full-body proportions, isolated objects, painterly style separation, hair color consistency — all worked on this round. Trigger Word 99rbsy99 — add this to every prompt for the V6.5 realism style. Place it at the END of your tag list for soft activation, or earlier for stronger effect. Compatible with my character LoRAs (which use 99bsy99) — they stack cleanly without conflict. Use both together for a character rendered in V6.5 realism. All Variants in This Release Seven variants ship today, covering everything from 4 GB CPU setups to 24 GB workstations. FP32 (safetensors, around 13 GB) Maximum precision. Research and production work. Best for 24 GB+ cards. FP16 (safetensors, around 6.5 GB) The default. Best quality and speed balance for most users. BF16 (safetensors, around 6.5 GB) Same size as FP16, slightly faster on RTX 3000+ with native BF16 support. FP8 Scaled (safetensors, around 3.2 GB) Near-FP16 quality at half the VRAM. Native in Forge and ComfyUI. Great for 8 GB cards. DMD2 Merge (safetensors, around 6.5 GB) FP16 with DMD2 distillation LoRA pre-merged. 4-step generation. LCM sampler, CFG 1.2. Fastest path for any card. Q8_0 GGUF (around 3.9 GB) 8-bit quantized. Near-FP16 quality. For 12+ GB cards in GGUF workflows. Q4_0 GGUF (around 2.7 GB) 4-bit quantized. Smallest file. Makes SDXL actually run on 6–8 GB entry-level cards. Quick Pick by Your VRAM 24 GB+ (3090, 4090, 5090, A6000) — FP16 or BF16. No reason to compress. 12–16 GB (3060 12GB, 4070, 4080) — FP8 Scaled or Q8_0 GGUF. Near-FP16 quality with headroom for LoRAs. 8–12 GB (3060, 4060 Ti, 2080) — FP8 Scaled or Q8_0 GGUF. Solid quality, comfortable VRAM use. 6–8 GB (3050, 2060, 1660) — Q4_0 GGUF. Smallest file, makes SDXL actually work on entry-level cards. CPU only or 4 GB cards — Q4_0 GGUF in ComfyUI-GGUF. Slow but functional. DMD2_Fp16 variant. 4 steps instead of 25–30. Recommended Settings For FP32, FP16, BF16, FP8 Scaled, and GGUF variants: Sampler — DPM++ 2M Karras, Euler a, or Restart Steps — 25 to 30 CFG — 4 to 7 Resolution — Native SDXL (1024×1024 or aspect-ratio buckets) For DMD2 specifically: Sampler — LCM Steps — 4 (not 25+) CFG — 1.2 (not 7) Result — Comparable quality to a 25-step generation in roughly 1/6 the time Quants Explained — Which File Do I Pick? If you've ever seen FP16, BF16, FP8, Q4, Q8 and just downloaded the biggest one, this section is for you. What's a quant ? Same model, smaller file. Weights are compressed so they fit on less VRAM. Some quality loss vs FP16, but smart compression (Q8_0) is so close you won't see a difference in normal use. Quality Ladder FP16 ≈ BF16 ≈ Q8_0 > FP8 > Q4_0. Above Q4_0 the differences are basically invisible in normal generation. About Speed Smaller quants are NOT always faster. Generation speed is mostly compute-bound on most cards — quants help with VRAM fit, not raw iterations per second. Where they DO help speed: avoiding system-RAM offload, which is what kills speed on small cards when the model doesn't fit. Three Reasons to Use a Quant - VRAM fit. A 6 GB card cannot load a 6.5 GB FP16 SDXL — your UI will try to offload to system RAM and generation crawls to under 0.1 iterations per second. A Q4_0 fits with room to spare. - Speed via avoiding offload. Once a model fits in VRAM, speed depends on your card's compute, not file size. But the second it doesn't fit, speed drops 10 to 100 times. Quants are insurance against that cliff. - More room for LoRAs, ControlNet, hires fix. Even if FP16 technically fits, loading a couple of LoRAs and a ControlNet on top can push you over. Q8_0 leaves you 2–3 GB of headroom for the rest of your stack. How to Load GGUF Files GGUFs need a loader, since most UIs don't natively support them yet. For ComfyUI — install the ComfyUI-GGUF custom node: For Forge or Forge Neo — install my Forge SDXL GGUF extension: After installing, GGUFs load straight from the standard checkpoint dropdown. No external module picker, no extra setup. All my GGUFs are bundled (UNet + CLIP-L + CLIP-G + VAE in one file) so they load without picking separate components. Pro Version Available This is the standard version of V6.5. The Pro version is trained on more data for longer, producing a more polished and refined output. Found Anything Off? Drop it in the comments or on Discord. V7's fix list starts now. Want to contribute to checkpoint feedback, signup here Loving this model? for exclusive perks and early access to unique resources. To discuss custom LoRa's or models, feel free to connect on - 👍 Like this model to keep me motivated and inspired to create more! - 💬 Drop a comment and let me know what you'd love to see next. - 🌟 Review this model to help me improve and make even better creations. - 🔔 Hit that notification bell to stay updated with my latest models and updates! Important Usage Tips - Add at the beginning of your prompt section. - Add at the beginning of your negative prompt section.
1,418 descargas · 94 me gusta en Civitai
SHA256
17E97BCFB79D9192773AAB0390F9023AFA7B110F58E2AE31F1DED10056382F90
ID de modelo de ModelTrends.ai
#12705
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Sampler
DPM++ 2M SDE
Pasos
27
Guidance
4.5
Semilla
2083773293
Tamaño
720x1260
Clip skip
2
Prompt
24. A woman sitting on the edge of a dock overlooking a calm lake at dusk, sky glowing softly, mountains reflected in the water, ultra_detailed, 8k, peaceful and calming, wide-angle shot
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
DPM++ SDE
Pasos
27
Guidance
4.5
Semilla
4059040205
Tamaño
810x1260
Clip skip
2
Prompt
Old faded polaroid photo, a woman lying on a bed, messy wavy hair, tired after a long day, business atire, analog film, chiaroscuro, sharp focus, 8k, UHD, award winning photography, ultra high res, DSLR, masterpiece, ultra detailed, intricate details, 35mm photograph, kodachrome, masterpiece, natural lighting
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
DPM++ 2M SDE
Pasos
27
Guidance
4.5
Semilla
4182820267
Tamaño
720x1260
Clip skip
2
Prompt
21. A young woman standing on the edge of a cliff, overlooking a forest valley at sunset, sky painted in shades of orange and pink, ultra_detailed, 8k, majestic and serene, wide-angle shot
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
DPM++ SDE
Pasos
27
Guidance
4.5
Semilla
2871673859
Tamaño
810x1260
Clip skip
2
Prompt
Cozy winter, woman with icy blue highlights, soft smile, chunky knit sweater, snowflakes outside, warm cafe, steaming hot chocolate on the table.
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
DPM++ SDE
Pasos
27
Guidance
4.5
Semilla
2286744612
Tamaño
810x1260
Clip skip
2
Prompt
cinematic photo analog style portrait of Close-up of ((woman)) in Hellblade: Senua's Sacrifice, emerging from black mud, long hair with dreads, war blue paint, paint fading, angry expression, dirty face, finely detailed eyes, moody, viking clothes, epic scene, epic composition, Photography, Cinematic Lighting, Volumetric Lighting, ethereal light, intricate details, extremely detailed volumetric rays . Analog-style aesthetic, Retro, scanlines, Video noise, Vignette effect, Color bleeding, Chromatic aberration, Low-resolution, Retro color palette
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
Euler
Pasos
27
Guidance
4.5
Semilla
2660184390
Tamaño
810x1260
Clip skip
2
Prompt
Midjourney style, cinematic quality, macro, Cinematic style, High quality, Beauty, Realism, Film still, Chiaroscuro, Photorealism, Still Film, (Masterpiece), Close-up, 8k, a striking and surreal scene that combines elements of both the natural world and fantasy. Dominating the composition is a massive, reptilian eye, filling almost the entire frame. The eye is highly detailed, with a slit-like pupil that suggests it belongs to a large, powerful creature, perhaps a dragon or another mythical being. The texture around the eye is rugged and scaly, giving the impression of ancient, weathered skin. In the lower portion of the image, a solitary human figure stands before the eye, dressed in a flowing black robe. The figure is tiny in comparison to the colossal eye, emphasizing the vast difference in scale and power between the two. The person stands on a surface that appears to be water or mist, which reflects the eerie, otherworldly light that surrounds the scene. The atmosphere is misty and dreamlike, adding to the sense of mystery and awe. Overall, the image is both dramatic and thought-provoking, blending cultural elements with a fantastical imagination to create a visually captivating scene.
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
DPM++ SDE
Pasos
27
Guidance
4.5
Semilla
2545295981
Tamaño
810x1260
Clip skip
2
Prompt
close-up of a roaring white tiger with black stripes, open mouth showing sharp teeth, intense blue eyes, green foliage and rocks blurred in the background, photorealistic detailing, natural sunlight highlighting whiskers and fur texture, animal portrait photography, masterpiece
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Ajustes
Sampler
Euler
Pasos
27
Guidance
4.5
Semilla
3650894864
Tamaño
810x1260
Clip skip
2
Prompt
(in Krenz Cushart style:1.4), high quality, masterpiece, BREAK A female warrior-poet clad in ornate ceremonial armor, standing atop a cliff overlooking a battlefield with a blood-red sky, depicted in a style with bold brushstrokes, intense contrasts, and dynamic compositions, BREAK illuminated by the fiery glow of a setting sun, Painterly Romanticism Style, focusing on dramatic, emotional intensity and vivid contrasts between light and shadow,(elaborately detailed attire with extraordinary elements:1.1), (hyperdetailed:1.1), (intricate details:1.0), (Refined details:1.1), (best quality:1.1), (high resolution:1.2)
Prompt negativo
Stable_Yogis_PDXL_Negatives-neg
Modelos de IA para generar imagen, vídeo y texto
stableyogi realism3 xl es un modelo base para la familia Stable Diffusion XL 1.0 listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Stable Diffusion XL 1.0, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Explorar por familia de modelos
Ver todos los modelos