Text to image
Qwen Image-Layered: revolutionary text-to-image generation with layered synthesis. Perfect for generative AI & computer vision.
Image-Text-to-Image • 20B • Updated • 106k • 1.2kNote A companion to text-to-image workflows, Qwen-Image-Layered separates an existing image into editable RGBA layers. Use it after prompt-based generation to prepare artwork for compositing, resizing or recoloring individual elements.
zai-org/GLM-Image
Text-to-Image • 7B • Updated • 15.9k • • 1.13kNote Turn descriptive text prompts into visuals with GLM-Image, Z.ai's image generation model. Its emphasis on text rendering makes it relevant for posters, illustrated explanations and compositions that combine imagery with written content.
Tongyi-MAI/Z-Image-Turbo
Text-to-Image • 6B • Updated • 783k • • 5.61kNote For rapid prompt-to-image exploration, Z-Image-Turbo is Tongyi-MAI's distilled Z-Image variant. Built for accelerated generation, it suits visual ideation, photorealistic scenes and designs incorporating English or Chinese text.
Qwen/Qwen-Image-2512
Text-to-Image • 20B • Updated • 38.1k • • 995Note Explore portraits, natural scenes and text-rich layouts with Qwen-Image-2512. This December update of the Qwen-Image text-to-image foundation model focuses on human realism, finer natural detail and improved text rendering.
Tongyi-MAI/Z-Image
Text-to-Image • 6B • Updated • 53.7k • • 1.31kNote The undistilled foundation behind the Turbo variant, Z-Image offers a starting point for text-to-image customization and LoRA training. Negative prompts and guidance controls support experimentation across photographic and illustrated styles. For the full img2img base-model set (FLUX.2, HunyuanImage, Qwen LoRAs) see the Image-to-Image collection: https://huggingface.co/collections/Goenzilla/image-to-image
black-forest-labs/FLUX.1-Krea-dev
Text-to-Image • 12B • Updated • 23.1k • • 964Note Photography-led image generation is the focus of FLUX.1-Krea-dev. This open-weight, guidance-distilled FLUX.1 developer checkpoint turns text descriptions into images and works with tools that support the original FLUX.1 dev model.
black-forest-labs/FLUX.1-schnell
Text-to-Image • 12B • Updated • 280k • • 6.81kNote Sketch out visual ideas quickly with FLUX.1-schnell, Black Forest Labs' speed-focused FLUX.1 model. Distillation enables few-step text-to-image generation, making it useful for exploring alternate prompts, compositions and concepts.
FLUX.2 [Klein] 9B
💻945Generate or edit images from text prompts
Note FLUX.2-klein-9B brings distilled FLUX.2 image generation to text-prompt workflows. This 9B checkpoint targets fast creative iteration, helping creators explore scenes and visual concepts and developers integrate prompt-to-image features.
Z Image Turbo
🖼3.95kGenerate images from text prompts in seconds
Note A community access point for Tongyi-MAI's accelerated image generator, mrfakename/Z-Image-Turbo rehosts the upstream Turbo model. Choose it for convenient repository access in text-to-image workflows; its role here is distribution of the existing model.
Viggle/Qwen-Image-2.1-viggle-turbo
Text-to-Image • 7B • Updated • 186k • 819Note Viggle accelerates Qwen-Image-2.1 prompt-to-image workflows with its Turbo release. The repository provides a distillation LoRA and merged transformer formats, offering routes for experimenting with faster generation in compatible tools.
zai-org/CogView4-6B
Text-to-Image • 6B • Updated • 5.9k • • 259Note CogView4-6B from zai-org generates images from text prompts with strong bilingual (Chinese/English) prompt understanding - a flexible open text-to-image base for posters, concept art and multi-language creative workflows.