Image Generation With Wan 2.2 (Uncensored AI Image Generation) – Simple ComfyUI Workflow with Direct Download Links
Aug 11, 2025
CompareAI.AI
In this workflow, we are using the Wan 2.2 video AI model by generating just a single frame to create images — and the results are amazing. The outputs are highly realistic, visually impressive, and notably uncensored, making this one of the most powerful and open image generators currently available.
What is ComfyUI ? & How to set it up on your system? —> Click Here
Note : On clicking download button, It may open a json file in a new tab, Just save the json file and open it in comfy UI.
Here are some results from the above workflow
PROMPT 1
"3d cartoon Homer simpson Posing In dark rainy Dystopian city in the rain, on an empty street. Neon lights in the background. Cinematic, moody, blade runner tones. Ultra 4k, hyper realistic"
As we can see that the results are very impressive, however the time taken to generate an AI image on this workflow by Wan 2.2 is around 150 seconds on a 16gb VRAM setup. Which is slow with respect to other open source image generation AI models.
Models Used in This Workflow (with Download Links)
🟣 Unet Loader (GGUF)
Model: Wan2.2 T2V 14B HighNoise and LowNoise GGUF models
Download: [HERE]
Placement: ComfyUI/models/diffusion_models
🟣 Load CLIP
Model: umt5_xxl_fp8_e4m3fn_scaled.safetensors
Download: [HERE]
Placement: ComfyUI/models/clip
🟣 Load VAE
Model: wan_2.1_vae.safetensors
Download: [HERE]
Placement: ComfyUI/models/vae
Check out our comparisons on image and video generative AI tools like Leonardo AI, Ideogram etc. with results and analysis over each AI tool, Or just judge them yourself by comparing the results of each ai tool, go to home now!.
Image Generation With Wan 2.2 (Uncensored AI Image Generation) – Simple ComfyUI Workflow with Direct Download Links
Aug 11, 2025
CompareAI.AI
In this workflow, we are using the Wan 2.2 video AI model by generating just a single frame to create images — and the results are amazing. The outputs are highly realistic, visually impressive, and notably uncensored, making this one of the most powerful and open image generators currently available.
What is ComfyUI ? & How to set it up on your system? —> Click Here
Note : On clicking download button, It may open a json file in a new tab, Just save the json file and open it in comfy UI.
Here are some results from the above workflow
PROMPT 1
"3d cartoon Homer simpson Posing In dark rainy Dystopian city in the rain, on an empty street. Neon lights in the background. Cinematic, moody, blade runner tones. Ultra 4k, hyper realistic"
As we can see that the results are very impressive, however the time taken to generate an AI image on this workflow by Wan 2.2 is around 150 seconds on a 16gb VRAM setup. Which is slow with respect to other open source image generation AI models.
Models Used in This Workflow (with Download Links)
🟣 Unet Loader (GGUF)
Model: Wan2.2 T2V 14B HighNoise and LowNoise GGUF models
Download: [HERE]
Placement: ComfyUI/models/diffusion_models
🟣 Load CLIP
Model: umt5_xxl_fp8_e4m3fn_scaled.safetensors
Download: [HERE]
Placement: ComfyUI/models/clip
🟣 Load VAE
Model: wan_2.1_vae.safetensors
Download: [HERE]
Placement: ComfyUI/models/vae
Check out our comparisons on image and video generative AI tools like Leonardo AI, Ideogram etc. with results and analysis over each AI tool, Or just judge them yourself by comparing the results of each ai tool, go to home now!.
Image Generation With Wan 2.2 (Uncensored AI Image Generation) – Simple ComfyUI Workflow with Direct Download Links
Aug 11, 2025
CompareAI.AI
In this workflow, we are using the Wan 2.2 video AI model by generating just a single frame to create images — and the results are amazing. The outputs are highly realistic, visually impressive, and notably uncensored, making this one of the most powerful and open image generators currently available.
What is ComfyUI ? & How to set it up on your system? —> Click Here
Note : On clicking download button, It may open a json file in a new tab, Just save the json file and open it in comfy UI.
Here are some results from the above workflow
PROMPT 1
"3d cartoon Homer simpson Posing In dark rainy Dystopian city in the rain, on an empty street. Neon lights in the background. Cinematic, moody, blade runner tones. Ultra 4k, hyper realistic"
As we can see that the results are very impressive, however the time taken to generate an AI image on this workflow by Wan 2.2 is around 150 seconds on a 16gb VRAM setup. Which is slow with respect to other open source image generation AI models.
Models Used in This Workflow (with Download Links)
🟣 Unet Loader (GGUF)
Model: Wan2.2 T2V 14B HighNoise and LowNoise GGUF models
Download: [HERE]
Placement: ComfyUI/models/diffusion_models
🟣 Load CLIP
Model: umt5_xxl_fp8_e4m3fn_scaled.safetensors
Download: [HERE]
Placement: ComfyUI/models/clip
🟣 Load VAE
Model: wan_2.1_vae.safetensors
Download: [HERE]
Placement: ComfyUI/models/vae
Check out our comparisons on image and video generative AI tools like Leonardo AI, Ideogram etc. with results and analysis over each AI tool, Or just judge them yourself by comparing the results of each ai tool, go to home now!.