image: 104 curated resources
image
104 resources · page 2 of 4
HunyuanImage 3.0 (+Instruct)
by Tencent
Hugging Face model card for tencent/HunyuanImage-3.0, Tencent's HunyuanImage 3.0 image generation model, with weights, usage and license details.
Ideogram 4.0 (Quality)
by Ideogram
Ideogram 4.0 technical details: 9.3B open-weight diffusion transformer image model trained from scratch.
Ideogram 4.5
by Ideogram
Ideogram 4.5 page: image editing model for multi-turn edits, available in app, MCP and API.
@ideogram_ai (Ideogram)
by Ideogram
X account of Ideogram: updates on its text-to-image model with typography rendering.
Real-ESRGAN
by Xintao
Real-ESRGAN GitHub repo: image restoration and super-resolution models with inference scripts.
Kandinsky 6.0 Image
Kandinsky Lab page for its Kandinsky Image models, including Kandinsky 6.0 Image Pro, a mixture-of-experts image generation and editing model.
kandinskylab GitHub
by kandinskylab
kandinskylab GitHub organisation: code for Kandinsky 5 image and video diffusion models.
Kling 3.0 Pro
by fal
fal.ai API page for Kling 3.0 Pro image-to-video generation, with parameters and pricing.
Kolors
by Kolors
Kwai Kolors GitHub repo: Kuaishou's text-to-image diffusion model and extensions.
Li v Liu, Beijing Internet Court (Kluwer Copyright Blog)
by Kluwer Copyright Blog (Wolters Kluwer)
Kluwer Copyright Blog post on Li v Liu, where the Beijing Internet Court granted copyright to an AI-generated image.
Li v Liu judgment with English translation (Internet Archive)
Li v Liu Beijing Internet Court judgment (2023) with English translation, on copyright in an AI-generated image.
MAI-Image-2
by Microsoft AI
Microsoft AI announcement of MAI-Image-2, its in-house image generation model.
MAI-Image-2.5
by Microsoft AI
Microsoft AI announcement of MAI-Image-2.5 image generation and editing model.
MAI-Image-2.6 launches at No. 2 on Arena
by Microsoft AI
Microsoft AI announcement of MAI-Image-2.6 image generation model.
MAI-Image-2.6
by Microsoft AI
Microsoft AI model page for MAI-Image-2.6, its text-to-image and image editing model, with a Flash variant.
Meshy 7
by Top 3D AI
Top 3D AI listing for Meshy 7 3D generation model with reviews and ratings.
Meshy 7.1
by Top 3D AI
Top 3D AI listing for Meshy 7.1 3D generation model with reviews and ratings.
@midjourney (Midjourney)
by Midjourney
X account of Midjourney: release notes and updates for the Midjourney image generator.
Midjourney updates
by Midjourney
Midjourney updates page with official release notes and announcements for Midjourney image and video models.
MiniMax H3
by MiniMax
MiniMax blog post launching H3, an open omni-modal generation model.
SoniTranslate
SoniTranslate GitHub repo: synchronised video translation and dubbing with speech models.
Neural4D
by Neural4D
Neural4D: AI generator converting text and images into 3D models.
NVIDIA Cosmos3-Super-Text2Image
by NVIDIA
Hugging Face model card for nvidia/Cosmos3-Super-Text2Image, NVIDIA's Cosmos text-to-image model, with weights, usage and license details.
Pixal3D
by Top 3D AI
Top 3D AI listing for TencentARC Pixal3D image-to-3D model with ratings.
protein design (RFdiffusion)
RosettaCommons RFdiffusion GitHub repo: code for designing proteins with RFdiffusion.
Qwen-Image-2.1
Qwen blog post on Qwen-Image-2.1 image generation model.
Qwen-Image-3.0-Pro
Alibaba Cloud Model Studio page for qwen-image-3.0-pro: input limits, capabilities and API usage.
Qwen-Image
by Qwen
QwenLM Qwen-Image GitHub repo: image generation foundation model with usage code.
Recraft V4.1
by Recraft
Recraft documentation for the V4.1 image model family, including Pro, Utility, Vector and Flash variants.
@recraftai (Recraft)
by Recraft
X account of Recraft: updates on its image and vector design generation model.
Reve 2.0
by Reve
Reve: image generation and editing model with natural-language and drag-and-drop editing.
Reve SDK and examples
by reve-ai
Reve SDK GitHub repo: official SDK and examples for the Reve image generation API.