modele/Stable Diffusion 3.5 Large - Large

Stable Diffusion 3.5 Large - Large

6/30/2025

1:25:07 PM

Powiązane słowa kluczowe i tagi

base model,checkpoint,large,multimodal diffusion transformer,sd 3.5 large,sd3.5,stability ai,stable diffusion,stable diffusion 3.5,stable diffusion 3.5 large,text-to-image model,theally

A solitary tall skeletal tower of corroded metal rising from cracked, dark ground under soft shimmering white light in a minimalist black and white composition.

Silhouette of a Parisian flâneur with a hat and cane standing on a cobblestone street, against a black background with faint geometric patterns and a tree on the side.

A small robot with smooth, rounded edges and large luminous eyes stands amidst a swirling mist of delicate pink cherry blossoms, illuminated by a single spotlight with ethereal shadows, evoking a serene and melancholic atmosphere.

Watercolor painting of a muscular female warrior with pale lavender skin wearing futuristic armor, standing with a sword in a minimalist, ethereal purple background.

A futuristic figure wearing mirrored sunglasses, depicted in a fragmented digital glitch style with vibrant neon colors and pixelated distortion against a dark background.

Minimalist digital illustration of a solitary woman with sleek blonde hair sitting on a chair, holding a glowing fuchsia coffee cup against a deep indigo background.

Minimalist silhouette of a young figure standing by a blooming desert flower at sunset, with bold black and white linework and soft warm gradient sky.

Impasto oil painting of a beautiful woman in an ethereal, flowing gown, surrounded by vibrant autumn and green trees with a celestial background, textured and detailed.

A colorful abstract portrait of an alien cyborg with mechanical details, inspired by expressionism and surrealism, featuring a complex geometric background.

A delicate celestial web of shimmering crimson threads intertwined with fine black tendrils holding spherical droplets that glow softly against a hazy blue background.

Digital illustration of a young woman with melancholic expression standing among crumbling photographs, featuring pastel and neon colors with dreamlike textures.

Hyper detailed biomorphic dystopian creature with large yellow eyes, blue organic textured skin, set against an abstract background inspired by Mark Rothko's color blocks.

Zalecane podpowiedzi

a detailed illustration of a cute rainbow colorful boba tea sitting in a window sill, tiki bar looking out onto a tropical oceanfront background, shallow depth of field, cinematic lighting, dappled sunlight, lens flare bokeh

Zalecane parametry

samplers

DPM++ 2M

steps

cfg

4.5

Sponsorzy twórcy

Please see our Quickstart Guide to Stable Diffusion 3.5 for all the latest info!

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Please note: This model is released under the Stability Community License. Visit Stability AI to learn or contact us for commercial licensing details.

Model Description

Developed by: Stability AI
Model type: MMDiT text-to-image generative model
Model Description: This model generates images based on text prompts. It is a Multimodal Diffusion Transformer that use three fixed, pretrained text encoders, and with QK-normalization to improve training stability.

License

Community License: Free for research, non-commercial, and commercial use for organizations or individuals with less than $1M in total annual revenue. More details can be found in the Community License Agreement. Read more at https://stability.ai/license.
For individuals and organizations with annual revenue above $1M: please contact us to get an Enterprise License.

Implementation Details

QK Normalization: Implements the QK normalization technique to improve training Stability.
Text Encoders：
- CLIPs: OpenCLIP-ViT/G, CLIP-ViT/L, context length 77 tokens
- T5: T5-xxl, context length 77/256 tokens at different stages of training
Training Data and Strategy:
This model was trained on a wide variety of data, including synthetic data and filtered publicly available data.

For more technical details of the original MMDiT architecture, please refer to the Research paper.

Współtwórca

theally

Civitai's Customer Engagement Manager! Civitai Support 📨 support@civitai.com 🆘 https://civitai.com/support

Poprzedni

Chroma - v.35-detail-calibrated

Następny

Dark Cinematic Style (Low-Key Lighting) - v1.0

Użyj tego modelu

Szczegóły modelu

Typ modelu

Checkpoint

Model bazowy

SD 3.5 Large

Wersja modelu

Large

Hash modelu

ffef7a279d

Twórca

theally

Dyskusja

Proszę się log in, aby dodać komentarz.

Kolekcja modeli - Stable Diffusion 3.5 Large

Close-up ink and watercolour portrait of a woman with expressive eyes, muted crimson lips, and a smudged charcoal background.

CheckpointMODELE

Stable Diffusion 3.5 Large - Large

Krótki Hash:

ffef7a279d

Obrazy autorstwa Stable Diffusion 3.5 Large - Large

A hooded mystical figure wearing a flowing dark cloak embedded with glowing cosmic star patterns, standing in ancient stone ruins with green plants.

A surrealistic low fantasy scene featuring a large ancient tree and a dark Japanese pagoda illuminated with a red glow, with reflections on water in a wabi sabi style.

A finely dressed couple stands in a lavish ballroom with a golden candlelit ambiance. The woman wears an off-shoulder Victorian white dress and looks toward the viewer, while the man in formal black attire stands beside her, with guests and chandeliers in the background.

$A delicate ethereal woman enveloped in shattered fractal blooms and luminescent mist, suspended in an impossible geometry with glowing botanical elements.$