Stability AI Launches Stable Diffusion 3.5: Improved Realism and Diversity in AI Image Generation
9 Sources
[1]
Stable Diffusion 3.5 Can Generate Pictures of Women Lying Down on Grass
Stability AI has clapped back at its critics by announcing its latest AI image model Stable Diffusion 3.5 with a picture of a woman lying on grass. The girl lying on grass is a tongue-in-cheek acknowledgment of the chaos that engulfed the company's last product, Stable Diffusion 3, which was
[2]
Stability AI Releases Stable Diffusion 3.5 Text-to-Image AI Model
Stability AI Releases Stable Diffusion 3.5 Text-to-Image AI Model Snippet: The Stable Diffusion 3.5 allows users to easily fine-tune the model for specific creative projects or build custom workflows Stability AI has introduced Stable Diffusion 3.5 which includes multiple model variants. These
[3]
Stable Diffusion 3.5 follows your prompts more closely and generates more diverse people
It also tries to right the wrongs of the last version that excelled at (accidental) body horror. Stable Diffusion, an open-source alternative to AI image generators like Midjourney and DALL-E, has been updated to version 3.5. The new model tries to right some of the wrongs (which may be an
[4]
Stable Diffusion 3.5 Is Out with Better Performance & the Right Number of Limbs
Stability, the AI startup behind popular image generator Stable Diffusion, has announced a new generation of models that are designed to be more customizable and versatile while outputting more "diverse" and representative content. ✕ Remove Ads The new Stable Diffusion 3.5 is being made available
[5]
StabilityAI releases Stable Diffusion 3.5 -- a step up in realism
StabilityAI is today releasing its new Stable Diffusion 3.5 family of AI image models. It comes with improved realism, prompt adherence and text rendering compared to SD3. Like the first incarnation of SD3, Stable Diffusion 3.5 comes in three sizes -- Large (8B), Large Turbo (8B), and Medium
[6]
Stability AI releases next-gen open-source Stable Diffusion 3.5 text-to-image AI model family - SiliconANGLE
Stability AI releases next-gen open-source Stable Diffusion 3.5 text-to-image AI model family Generative artificial intelligence startup Stability AI Ltd. today announced the release of Stable Diffusion 3.5, which includes three next-generation open-source text-to-image AI model variants. "In
[7]
Stability claims its newest Stable Diffusion models generate more 'diverse' images | TechCrunch
Following a string of controversies stemming from technical hiccups and licensing changes, AI startup Stability AI has announced its latest family of image generation models. The new Stable Diffusion 3.5 series is more customizable and versatile than Stability's previous-generation tech, the
[8]
Stable Diffusion 3.5 debuts as Stability AI aims to improve open models for generating images
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Stability AI is out today with a major update for its text to image generative AI technology with the debut of Stable Diffusion 3.5. A key goal for the new update is
[9]
Stable Diffusion 3.5: Stability AI Redeems Itself With New Models and Expanded Features - Decrypt
Stability AI may be starting its very own redemption arc. After the disappointment that was SD3 Medium, they've come back swinging with the release of two new models that had been promised back in July: Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo. "In June, we released Stable
Share
Copy Link
Stability AI releases Stable Diffusion 3.5, addressing previous issues and offering enhanced image quality, prompt adherence, and diversity in AI-generated images.
Stability AI Introduces Stable Diffusion 3.5
Stability AI has unveiled Stable Diffusion 3.5, a significant upgrade to its open-source AI image generation model. This release aims to address the shortcomings of its predecessor, Stable Diffusion 3, which faced criticism for producing unrealistic and distorted images
1
2
.Key Improvements and Features
The new model boasts several enhancements:
- Improved Realism: Stable Diffusion 3.5 generates more realistic images, particularly in human representations
3
. - Enhanced Prompt Adherence: The model follows user prompts more accurately, a feature Stability AI claims leads the market
3
4
. - Diversity in Output: It produces more diverse images of people with various skin tones and features without requiring explicit prompts
3
5
. - Text Rendering: Improvements in text generation within images
5
.
Model Variants
Stable Diffusion 3.5 is available in three variants:
- Large (8B parameters): Highest quality output, suitable for professional use at 1 MP resolution
2
4
. - Large Turbo (8B parameters): Faster version, balancing speed and quality
2
4
. - Medium (2.6B parameters): Designed for consumer hardware, available from October 29
3
4
.
Technical Specifications and Accessibility
- The models are highly customizable and can run on consumer-grade hardware
2
4
. - They are free for both commercial and non-commercial use under the Stability AI Community License, with certain revenue restrictions
2
5
. - The Large and Large Turbo versions are available for download on Hugging Face, with inference code on GitHub
2
4
.
Industry Impact and Comparisons
Stable Diffusion 3.5 is positioned to compete with other major AI image generators:
- It aims to match or exceed the capabilities of models like Midjourney, DALL-E, and the recently released Flux 1.1 Pro
3
5
. - The model's ability to generate diverse images without extensive prompting sets it apart from competitors
3
.
Related Stories
Addressing Previous Concerns
Stability AI acknowledges the issues with Stable Diffusion 3, particularly its tendency to produce distorted images:
- The company admitted that SD3 "didn't fully meet our standards or our communities' expectations"
1
4
. - The new version aims to correct these issues, especially in rendering human features accurately
1
3
.
Future Implications
The release of Stable Diffusion 3.5 marks a significant step in AI image generation:
- It potentially democratizes access to high-quality AI image generation tools
2
5
. - The focus on diversity and representation in AI-generated images could have broader societal impacts
3
5
.
As AI image generation continues to evolve, Stable Diffusion 3.5 represents a notable advancement in the field, promising more realistic, diverse, and user-friendly AI-generated imagery.
References
Summarized by
Navi
[3]
Related Stories
Recent Highlights
1
OpenAI Launches Astra AI Model With Critical Cyber Abilities Amid Safety Debate
Technology
2
OpenAI Agents Escape Sandbox, Post 18,000 Messages on German Wiki to Share Hacking Techniques
Policy and Regulation
3
Anthropic AI Completes 10-Year Mathematical Proof Project in Just 11 Days Using Claude
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
