Click the blue text to follow us
01
Effect Display
Effect Display
<span>Prompt:</span><p><span>Qwen-Image-EliGen Magic Café promotional poster, featuring a girl holding two cups of magic coffee, one with flames and the other with ice spikes, set against a light blue mist background, with the poster text reading "Qwen-Image-EliGen Magic Café", "Super Noodle Dad | New Product Launch"</span></p><pre><code>Workflow Simplified
02
User Guide
For usage, please refer to previous articles, no further elaboration needed
Qwen-Image can now draw wherever you point (includes beginner-friendly production tutorial)
03
Source Code Acquisition Method
After following, send a private message in the backend with “QwenImageDiffSynth” to obtain it
04
Previous Highlights
The Qwen-Image distilled 5x accelerated workflow is here, starting with 8GB of VRAM, the 4090 graphics card can produce images in 15 seconds for 10 steps (includes beginner-friendly production tutorial)
The open-source Qwen-Image text-to-image workflow is here, starting with 8GB of VRAM, the 4090 graphics card can produce images in 30 seconds for 20 steps (includes beginner-friendly production tutorial)
The ThinkSound video magic sound effect dubbing workflow is here (includes beginner-friendly production tutorial)
The OmniAvatar 1.3B image-to-digital human workflow is here (includes beginner-friendly production tutorial)
The PosterCraft text-to-poster workflow is now live on Chenyu Zhiyun (includes beginner-friendly production tutorial)
Text-to-poster? The PosterCraft workflow is here (includes beginner-friendly production tutorial)
This digital human can sing “Great Ambition”, what do you think of the effect? (includes beginner-friendly production tutorial)
The MutiTalk ComfyUI plugin now supports Teacache, 81 frames in just 287 seconds, with int8 quantization sage2 acceleration, video can be produced in 5 steps
The MutiTalk ComfyUI plugin is here, supporting two-person dialogue, with int8 quantization acceleration, video can be produced in 5 steps
The MutiTalk ComfyUI plugin is now live on Xian Palace Cloud, 1 image + 1 audio = realistic digital human speaking video, with int8 quantization acceleration, video can be produced in 5 steps
The HunyuanAvatar ComfyUI plugin is now live on Xian Palace Cloud, 1 image + 1 audio = realistic digital human/animal speaking video
The HunyuanAvatar is powerful, 1 image + 1 audio = realistic digital human/animal speaking video
A step-by-step guide to replacing characters in viral videos and changing lines for fun
The 520 sweet gesture dance workflow, perfect hand replacements for short videos, can also sync with lyrics
The HeyGem+WACE image digital human workflow is now live on Xian Palace Cloud, 1 image + 1 text + 1 gesture video = digital human with gestures
The HeyGem digital human ComfyUI workflow is now live on Xian Palace Cloud