Loading video...

Video Failed to Load

Go Home

Qwen Image 2.1 is here! 🖼️ A 7B params native image generation and editing model, with up to 10 image references The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI ▶️ on Spaces

HuggingApps's profile picture

Hugging Apps

4,512 subscribers

86,083 views • 6 days ago •via X (Twitter)

ArtsScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

2 Comments

Hugging Apps's profile picture
Hugging Apps6 days ago

Model: Diffusers implementation: ComfyUI:

Ramanpal Singh's profile picture
Ramanpal Singh6 days ago

I’d test this with a fixed 10-image product-scene suite before judging it. 10 references + native prompt enhancement makes consistency the real benchmark—not one impressive edit. Then I’d run the same prompts through Spaces, Diffusers, and ComfyUI and compare edit success rate + latency.

Related Videos

Qwen-Image-2.1 in 4 steps is here ⚡ ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model ▶️ on Spaces
0:28

Qwen-Image-2.1 in 4 steps is here ⚡ ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model ▶️ on Spaces

Hugging Apps

92,238 views • 4 days ago

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included
0:36

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included

ComfyUI

187,951 views • 6 days ago

Qwen-Image-2.1-viggle-turbo v0.2 is out on Hugging Face Text-to-image and image editing in 6 steps about 5× faster than the 40-step Qwen-Image-2.1 model:
0:47

Qwen-Image-2.1-viggle-turbo v0.2 is out on Hugging Face Text-to-image and image editing in 6 steps about 5× faster than the 40-step Qwen-Image-2.1 model:

AK

40,731 views • 1 day ago

Okay this is crazy.... Qwen Image 2.1 can generatively upscale its own images. original image was a 1024x1024 output. second image is a 2x upscale using Qwen Image 2.1s editing capability. Prompt: "Upscale the image"
0:28

Okay this is crazy.... Qwen Image 2.1 can generatively upscale its own images. original image was a 1024x1024 output. second image is a 2x upscale using Qwen Image 2.1s editing capability. Prompt: "Upscale the image"

Rebel AI

29,732 views • 5 days ago

KREA 2 Image is now a Partner Node in ComfyUI KREA's first foundation image model — trained from scratch — with tunable creativity, style references, and moodboard conditioning.
0:25

KREA 2 Image is now a Partner Node in ComfyUI KREA's first foundation image model — trained from scratch — with tunable creativity, style references, and moodboard conditioning.

ComfyUI

15,106 views • 4 months ago

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.
2:07

1/4 🚀We are launching Qwen-Image-2.0, a next-generation foundational image generation model. The key highlights of Qwen-Image-2.0 include: Professional Typography Rendering: Supports 1k-token instructions for direct generation of professional infographics, including PPTs, posters, comics, and more. Stronger Semantic Adherence: Native 2K resolution support for finely detailed realistic scenes, including people, nature, and architecture. Improved Text Rendering: Integrated understanding and generation capabilities, unifying image generation and editing in a single mode Lighter Model Architecture: Smaller model size with faster inference speed.

Tongyi Lab

164,097 views • 7 months ago

Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by Qwen up to 6.3× faster for image generation and editing. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images. - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG. 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘫𝘶𝘴𝘵 𝘰𝘶𝘳 𝘧𝘪𝘳𝘴𝘵 𝘳𝘦𝘭𝘦𝘢𝘴𝘦, 𝘸𝘪𝘵𝘩 𝘦𝘷𝘦𝘯 𝘣𝘦𝘵𝘵𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘯 𝘵𝘩𝘦 𝘸𝘢𝘺. 🚀 Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API:
0:27

Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by Qwen up to 6.3× faster for image generation and editing. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images. - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG. 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘫𝘶𝘴𝘵 𝘰𝘶𝘳 𝘧𝘪𝘳𝘴𝘵 𝘳𝘦𝘭𝘦𝘢𝘴𝘦, 𝘸𝘪𝘵𝘩 𝘦𝘷𝘦𝘯 𝘣𝘦𝘵𝘵𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘯 𝘵𝘩𝘦 𝘸𝘢𝘺. 🚀 Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API:

Pruna AI

85,115 views • 2 days ago

introducing Seedream 5.0 Pro. this new multimodal model brings advance reasoning, precise image editing, and support for up to 10 image references. try it now on Krea.
0:20

introducing Seedream 5.0 Pro. this new multimodal model brings advance reasoning, precise image editing, and support for up to 10 image references. try it now on Krea.

Krea

38,896 views • 2 months ago

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇
0:32

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇

ComfyUI

14,756 views • 2 months ago

Chinese AI lab just killed Photoshop with its opensource AI image editing model. Qwen Image can perfectly edit any image while keeping everything else pixel-perfect. 100% free, local and Opensource.
0:39

Chinese AI lab just killed Photoshop with its opensource AI image editing model. Qwen Image can perfectly edit any image while keeping everything else pixel-perfect. 100% free, local and Opensource.

Shubham Saboo

101,849 views • 1 year ago

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.
0:56

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.

OpenAI Developers

182,154 views • 5 months ago

OpenAI just dropped GPT-Image 1, the model behind ChatGPT-4o’s image generation, now available via API — and ComfyUI already supports it with new API Nodes (Beta)! Here’s how it works 👇
0:34

OpenAI just dropped GPT-Image 1, the model behind ChatGPT-4o’s image generation, now available via API — and ComfyUI already supports it with new API Nodes (Beta)! Here’s how it works 👇

ComfyUI

29,853 views • 1 year ago

The video is a Llama v1 7B model implemented in MLX and running on an M2 Ultra. More here: * Train a Transformer LM or fine-tune with LoRA * Text generation with Mistral * Image generation with Stable Diffusion * Speech recognition with Whisper
1:35

The video is a Llama v1 7B model implemented in MLX and running on an M2 Ultra. More here: * Train a Transformer LM or fine-tune with LoRA * Text generation with Mistral * Image generation with Stable Diffusion * Speech recognition with Whisper

Awni Hannun

66,585 views • 2 years ago

Pruna-Qwen-Image-2.1 a set of a few-step LoRA adapters that make Qwen-Image-2.1 up to 6.3× faster for image generation and editing Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance HF workflow:
0:27

Pruna-Qwen-Image-2.1 a set of a few-step LoRA adapters that make Qwen-Image-2.1 up to 6.3× faster for image generation and editing Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance HF workflow:

AK

21,278 views • 2 days ago

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.
0:21

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.

AI Search

14,690 views • 2 months ago

FLUX 3 Video is live in ComfyUI via Partner Nodes Black Forest Labs FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog
0:31

FLUX 3 Video is live in ComfyUI via Partner Nodes Black Forest Labs FLUX 3 Model highlights: → 20s in a single generation → native audio, not dubbed on after → text-to-video, image-to-video, keyframes, continuation → multi-scene and multi-angle in one prompt → multilingual dialogue with lipsync that holds → typography that sits in the scene → chain clips agentically for longer stories One model across video, audio, image, and action. Click the link below to download the workflows and learn more with blog

ComfyUI

25,715 views • 1 month ago

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:
1:39

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,392 views • 1 year ago

Seedream v4.5 is HERE! ByteDance’s new-generation image creation model that combines image generation + image editing in one unified architecture. Cleaner text, sharper details, smarter edits, all in a single model. Pair it with ImagineArt’s 71% OFF Cyber Monday deal + give access to 40 creators on your plan. Follow+ RT + like + reply with “ImagineArt Seedream” to get 250 credits in DMs.
0:24

Seedream v4.5 is HERE! ByteDance’s new-generation image creation model that combines image generation + image editing in one unified architecture. Cleaner text, sharper details, smarter edits, all in a single model. Pair it with ImagineArt’s 71% OFF Cyber Monday deal + give access to 40 creators on your plan. Follow+ RT + like + reply with “ImagineArt Seedream” to get 250 credits in DMs.

ImagineArt

535,008 views • 9 months ago