A New Era in Image and Video Generation!
Artius WAN is a lovingly crafted blend based on Wan 2.1 T2V 14b and a diverse collection of LoRAs, making it a versatile model with powerful NSFW capabilities.
This model excels at generating highly detailed images (1920x1080) as well as videos from text prompts—all in just 5 steps!
For optimal performance in ComfyUI, be sure to install this essential node:
👉 https://github.com/ClownsharkBatwing/RES4LYF
Also you need WAN VAE and Text Encoder: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged
Special thanks to the creators of these LoRAs:
Every generated image includes an embedded ComfyUI workflow, allowing you to open and test Artius WAN yourself. I’m confident you’ll love this model!
Recommended sampler settings:
Steps: 5
Sampler: Heun
Scheduler: beta57 (via RES4LYF node)
Model Shift: From 1 to 2 (less is more realistic)
If you'd like to support my work, consider joining me on Boosty or Patreon:
✨ Boosty
✨ Patreon
Description
FAQ
Comments (37)
Here's the google translation:
Let them throw feces at me, but I believe this is currently best checkpoint merge Wan2.1. Even the issue of the same face here is compensated by the ability to change silhouette figures, which already represents significant progress. It seems that 8 steps res-multistep work better than 5 steps heun in ComfyUI, or maybe I've overdone it with the settings :)."
yes, res sampler is better but slower, i found that heun is balanced between quality and speed
If they throw they're being petty, what you're saying is true, this is surprisingly good...
Just produced my first video with this and I'm impressed at what it can do without needing to manually load in a bunch of LoRAs!
Unfortunately, I'm on a 12GB VRAM 5070, and it took quite a bit longer than I'm used to for the generation to happen (480x838 @ 121 steps) - nothing extreme, just clearly all the merged loras etc demand quite a bit!
Doesn't help that ClownSharkSampler only seems to have Heun 2s and Heun 3s rather than standard good ol' single step Heun (sounds like a Chinese ballroom dancer...)
I'd be very interested to see if it's possible for this to be quantised as a GGUF for us poor VRAM peons!
Very promising though - nice work!
Also, this comes up in the terminal when running a generation - I don't have any LoRAs loaded, just the UNET, Text Encoder and VAE... is it all good or does it suggest an issue with the model?
unet missing: ['text_embedding.0.scale_input', 'text_embedding.2.scale_input', 'time_embedding.0.scale_input', 'time_embedding.2.scale_input', 'time_projection.1.scale_input', 'blocks.0.self_attn.q.scale_input', 'blocks.0.self_attn.k.scale_input', 'blocks.0.self_attn.v.scale_input', 'blocks.0.self_attn.o.scale_input', 'blocks.0.cross_attn.q.scale_input', 'blocks.0.cross_attn.k.scale_input', 'blocks.0.cross_attn.v.scale_input', 'blocks.0.cross_attn.o.scale_input', 'blocks.0.ffn.0.scale_input', 'blocks.0.ffn.2.scale_input', 'blocks.1.self_attn.q.scale_input', 'blocks.1.self_attn.k.scale_input', 'blocks.1.self_attn.v.scale_input', 'blocks.1.self_attn.o.scale_input', 'blocks.1.cross_attn.q.scale_input', 'blocks.1.cross_attn.k.scale_input', 'blocks.1.cross_attn.v.scale_input', 'blocks.1.cross_attn.o.scale_input', 'blocks.1.ffn.0.scale_input', 'blocks.1.ffn.2.scale_input', 'blocks.2.self_attn.q.scale_input', 'blocks.2.self_attn.k.scale_input', 'blocks.2.self_attn.v.scale_input', 'blocks.2.self_attn.o.scale_input', 'blocks.2.cross_attn.q.scale_input', 'blocks.2.cross_attn.k.scale_input', 'blocks.2.cross_attn.v.scale_input', 'blocks.2.cross_attn.o.scale_input', 'blocks.2.ffn.0.scale_input', 'blocks.2.ffn.2.scale_input', 'blocks.3.self_attn.q.scale_input', 'blocks.3.self_attn.k.scale_input', 'blocks.3.self_attn.v.scale_input', 'blocks.3.self_attn.o.scale_input', 'blocks.3.cross_attn.q.scale_input', 'blocks.3.cross_attn.k.scale_input', 'blocks.3.cross_attn.v.scale_input', 'blocks.3.cross_attn.o.scale_input', 'blocks.3.ffn.0.scale_input', 'blocks.3.ffn.2.scale_input', 'blocks.4.self_attn.q.scale_input', 'blocks.4.self_attn.k.scale_input', 'blocks.4.self_attn.v.scale_input', 'blocks.4.self_attn.o.scale_input', 'blocks.4.cross_attn.q.scale_input', 'blocks.4.cross_attn.k.scale_input', 'blocks.4.cross_attn.v.scale_input', 'blocks.4.cross_attn.o.scale_input', 'blocks.4.ffn.0.scale_input', 'blocks.4.ffn.2.scale_input', 'blocks.5.self_attn.q.scale_input', 'blocks.5.self_attn.k.scale_input', 'blocks.5.self_attn.v.scale_input', 'blocks.5.self_attn.o.scale_input', 'blocks.5.cross_attn.q.scale_input', 'blocks.5.cross_attn.k.scale_input', 'blocks.5.cross_attn.v.scale_input', 'blocks.5.cross_attn.o.scale_input', 'blocks.5.ffn.0.scale_input', 'blocks.5.ffn.2.scale_input', 'blocks.6.self_attn.q.scale_input', 'blocks.6.self_attn.k.scale_input', 'blocks.6.self_attn.v.scale_input', 'blocks.6.self_attn.o.scale_input', 'blocks.6.cross_attn.q.scale_input', 'blocks.6.cross_attn.k.scale_input', 'blocks.6.cross_attn.v.scale_input', 'blocks.6.cross_attn.o.scale_input', 'blocks.6.ffn.0.scale_input', 'blocks.6.ffn.2.scale_input', 'blocks.7.self_attn.q.scale_input', 'blocks.7.self_attn.k.scale_input', 'blocks.7.self_attn.v.scale_input', 'blocks.7.self_attn.o.scale_input', 'blocks.7.cross_attn.q.scale_input', 'blocks.7.cross_attn.k.scale_input', 'blocks.7.cross_attn.v.scale_input', 'blocks.7.cross_attn.o.scale_input', 'blocks.7.ffn.0.scale_input', 'blocks.7.ffn.2.scale_input', 'blocks.8.self_attn.q.scale_input', 'blocks.8.self_attn.k.scale_input', 'blocks.8.self_attn.v.scale_input', 'blocks.8.self_attn.o.scale_input', 'blocks.8.cross_attn.q.scale_input', 'blocks.8.cross_attn.k.scale_input', 'blocks.8.cross_attn.v.scale_input', 'blocks.8.cross_attn.o.scale_input', 'blocks.8.ffn.0.scale_input', 'blocks.8.ffn.2.scale_input', 'blocks.9.self_attn.q.scale_input', 'blocks.9.self_attn.k.scale_input', 'blocks.9.self_attn.v.scale_input', 'blocks.9.self_attn.o.scale_input', 'blocks.9.cross_attn.q.scale_input', 'blocks.9.cross_attn.k.scale_input', 'blocks.9.cross_attn.v.scale_input', 'blocks.9.cross_attn.o.scale_input', 'blocks.9.ffn.0.scale_input', 'blocks.9.ffn.2.scale_input', 'blocks.10.self_attn.q.scale_input', 'blocks.10.self_attn.k.scale_input', 'blocks.10.self_attn.v.scale_input', 'blocks.10.self_attn.o.scale_input', 'blocks.10.cross_attn.q.scale_input', 'blocks.10.cross_attn.k.scale_input', 'blocks.10.cross_attn.v.scale_input', 'blocks.10.cross_attn.o.scale_input', 'blocks.10.ffn.0.scale_input', 'blocks.10.ffn.2.scale_input', 'blocks.11.self_attn.q.scale_input', 'blocks.11.self_attn.k.scale_input', 'blocks.11.self_attn.v.scale_input', 'blocks.11.self_attn.o.scale_input', 'blocks.11.cross_attn.q.scale_input', 'blocks.11.cross_attn.k.scale_input', 'blocks.11.cross_attn.v.scale_input', 'blocks.11.cross_attn.o.scale_input', 'blocks.11.ffn.0.scale_input', 'blocks.11.ffn.2.scale_input', 'blocks.12.self_attn.q.scale_input', 'blocks.12.self_attn.k.scale_input', 'blocks.12.self_attn.v.scale_input', 'blocks.12.self_attn.o.scale_input', 'blocks.12.cross_attn.q.scale_input', 'blocks.12.cross_attn.k.scale_input', 'blocks.12.cross_attn.v.scale_input', 'blocks.12.cross_attn.o.scale_input', 'blocks.12.ffn.0.scale_input', 'blocks.12.ffn.2.scale_input', 'blocks.13.self_attn.q.scale_input', 'blocks.13.self_attn.k.scale_input', 'blocks.13.self_attn.v.scale_input', 'blocks.13.self_attn.o.scale_input', 'blocks.13.cross_attn.q.scale_input', 'blocks.13.cross_attn.k.scale_input', 'blocks.13.cross_attn.v.scale_input', 'blocks.13.cross_attn.o.scale_input', 'blocks.13.ffn.0.scale_input', 'blocks.13.ffn.2.scale_input', 'blocks.14.self_attn.q.scale_input', 'blocks.14.self_attn.k.scale_input', 'blocks.14.self_attn.v.scale_input', 'blocks.14.self_attn.o.scale_input', 'blocks.14.cross_attn.q.scale_input', 'blocks.14.cross_attn.k.scale_input', 'blocks.14.cross_attn.v.scale_input', 'blocks.14.cross_attn.o.scale_input', 'blocks.14.ffn.0.scale_input', 'blocks.14.ffn.2.scale_input', 'blocks.15.self_attn.q.scale_input', 'blocks.15.self_attn.k.scale_input', 'blocks.15.self_attn.v.scale_input', 'blocks.15.self_attn.o.scale_input', 'blocks.15.cross_attn.q.scale_input', 'blocks.15.cross_attn.k.scale_input', 'blocks.15.cross_attn.v.scale_input', 'blocks.15.cross_attn.o.scale_input', 'blocks.15.ffn.0.scale_input', 'blocks.15.ffn.2.scale_input', 'blocks.16.self_attn.q.scale_input', 'blocks.16.self_attn.k.scale_input', 'blocks.16.self_attn.v.scale_input', 'blocks.16.self_attn.o.scale_input', 'blocks.16.cross_attn.q.scale_input', 'blocks.16.cross_attn.k.scale_input', 'blocks.16.cross_attn.v.scale_input', 'blocks.16.cross_attn.o.scale_input', 'blocks.16.ffn.0.scale_input', 'blocks.16.ffn.2.scale_input', 'blocks.17.self_attn.q.scale_input', 'blocks.17.self_attn.k.scale_input', 'blocks.17.self_attn.v.scale_input', 'blocks.17.self_attn.o.scale_input', 'blocks.17.cross_attn.q.scale_input', 'blocks.17.cross_attn.k.scale_input', 'blocks.17.cross_attn.v.scale_input', 'blocks.17.cross_attn.o.scale_input', 'blocks.17.ffn.0.scale_input', 'blocks.17.ffn.2.scale_input', 'blocks.18.self_attn.q.scale_input', 'blocks.18.self_attn.k.scale_input', 'blocks.18.self_attn.v.scale_input', 'blocks.18.self_attn.o.scale_input', 'blocks.18.cross_attn.q.scale_input', 'blocks.18.cross_attn.k.scale_input', 'blocks.18.cross_attn.v.scale_input', 'blocks.18.cross_attn.o.scale_input', 'blocks.18.ffn.0.scale_input', 'blocks.18.ffn.2.scale_input', 'blocks.19.self_attn.q.scale_input', 'blocks.19.self_attn.k.scale_input', 'blocks.19.self_attn.v.scale_input', 'blocks.19.self_attn.o.scale_input', 'blocks.19.cross_attn.q.scale_input', 'blocks.19.cross_attn.k.scale_input', 'blocks.19.cross_attn.v.scale_input', 'blocks.19.cross_attn.o.scale_input', 'blocks.19.ffn.0.scale_input', 'blocks.19.ffn.2.scale_input', 'blocks.20.self_attn.q.scale_input', 'blocks.20.self_attn.k.scale_input', 'blocks.20.self_attn.v.scale_input', 'blocks.20.self_attn.o.scale_input', 'blocks.20.cross_attn.q.scale_input', 'blocks.20.cross_attn.k.scale_input', 'blocks.20.cross_attn.v.scale_input', 'blocks.20.cross_attn.o.scale_input', 'blocks.20.ffn.0.scale_input', 'blocks.20.ffn.2.scale_input', 'blocks.21.self_attn.q.scale_input', 'blocks.21.self_attn.k.scale_input', 'blocks.21.self_attn.v.scale_input', 'blocks.21.self_attn.o.scale_input', 'blocks.21.cross_attn.q.scale_input', 'blocks.21.cross_attn.k.scale_input', 'blocks.21.cross_attn.v.scale_input', 'blocks.21.cross_attn.o.scale_input', 'blocks.21.ffn.0.scale_input', 'blocks.21.ffn.2.scale_input', 'blocks.22.self_attn.q.scale_input', 'blocks.22.self_attn.k.scale_input', 'blocks.22.self_attn.v.scale_input', 'blocks.22.self_attn.o.scale_input', 'blocks.22.cross_attn.q.scale_input', 'blocks.22.cross_attn.k.scale_input', 'blocks.22.cross_attn.v.scale_input', 'blocks.22.cross_attn.o.scale_input', 'blocks.22.ffn.0.scale_input', 'blocks.22.ffn.2.scale_input', 'blocks.23.self_attn.q.scale_input', 'blocks.23.self_attn.k.scale_input', 'blocks.23.self_attn.v.scale_input', 'blocks.23.self_attn.o.scale_input', 'blocks.23.cross_attn.q.scale_input', 'blocks.23.cross_attn.k.scale_input', 'blocks.23.cross_attn.v.scale_input', 'blocks.23.cross_attn.o.scale_input', 'blocks.23.ffn.0.scale_input', 'blocks.23.ffn.2.scale_input', 'blocks.24.self_attn.q.scale_input', 'blocks.24.self_attn.k.scale_input', 'blocks.24.self_attn.v.scale_input', 'blocks.24.self_attn.o.scale_input', 'blocks.24.cross_attn.q.scale_input', 'blocks.24.cross_attn.k.scale_input', 'blocks.24.cross_attn.v.scale_input', 'blocks.24.cross_attn.o.scale_input', 'blocks.24.ffn.0.scale_input', 'blocks.24.ffn.2.scale_input', 'blocks.25.self_attn.q.scale_input', 'blocks.25.self_attn.k.scale_input', 'blocks.25.self_attn.v.scale_input', 'blocks.25.self_attn.o.scale_input', 'blocks.25.cross_attn.q.scale_input', 'blocks.25.cross_attn.k.scale_input', 'blocks.25.cross_attn.v.scale_input', 'blocks.25.cross_attn.o.scale_input', 'blocks.25.ffn.0.scale_input', 'blocks.25.ffn.2.scale_input', 'blocks.26.self_attn.q.scale_input', 'blocks.26.self_attn.k.scale_input', 'blocks.26.self_attn.v.scale_input', 'blocks.26.self_attn.o.scale_input', 'blocks.26.cross_attn.q.scale_input', 'blocks.26.cross_attn.k.scale_input', 'blocks.26.cross_attn.v.scale_input', 'blocks.26.cross_attn.o.scale_input', 'blocks.26.ffn.0.scale_input', 'blocks.26.ffn.2.scale_input', 'blocks.27.self_attn.q.scale_input', 'blocks.27.self_attn.k.scale_input', 'blocks.27.self_attn.v.scale_input', 'blocks.27.self_attn.o.scale_input', 'blocks.27.cross_attn.q.scale_input', 'blocks.27.cross_attn.k.scale_input', 'blocks.27.cross_attn.v.scale_input', 'blocks.27.cross_attn.o.scale_input', 'blocks.27.ffn.0.scale_input', 'blocks.27.ffn.2.scale_input', 'blocks.28.self_attn.q.scale_input', 'blocks.28.self_attn.k.scale_input', 'blocks.28.self_attn.v.scale_input', 'blocks.28.self_attn.o.scale_input', 'blocks.28.cross_attn.q.scale_input', 'blocks.28.cross_attn.k.scale_input', 'blocks.28.cross_attn.v.scale_input', 'blocks.28.cross_attn.o.scale_input', 'blocks.28.ffn.0.scale_input', 'blocks.28.ffn.2.scale_input', 'blocks.29.self_attn.q.scale_input', 'blocks.29.self_attn.k.scale_input', 'blocks.29.self_attn.v.scale_input', 'blocks.29.self_attn.o.scale_input', 'blocks.29.cross_attn.q.scale_input', 'blocks.29.cross_attn.k.scale_input', 'blocks.29.cross_attn.v.scale_input', 'blocks.29.cross_attn.o.scale_input', 'blocks.29.ffn.0.scale_input', 'blocks.29.ffn.2.scale_input', 'blocks.30.self_attn.q.scale_input', 'blocks.30.self_attn.k.scale_input', 'blocks.30.self_attn.v.scale_input', 'blocks.30.self_attn.o.scale_input', 'blocks.30.cross_attn.q.scale_input', 'blocks.30.cross_attn.k.scale_input', 'blocks.30.cross_attn.v.scale_input', 'blocks.30.cross_attn.o.scale_input', 'blocks.30.ffn.0.scale_input', 'blocks.30.ffn.2.scale_input', 'blocks.31.self_attn.q.scale_input', 'blocks.31.self_attn.k.scale_input', 'blocks.31.self_attn.v.scale_input', 'blocks.31.self_attn.o.scale_input', 'blocks.31.cross_attn.q.scale_input', 'blocks.31.cross_attn.k.scale_input', 'blocks.31.cross_attn.v.scale_input', 'blocks.31.cross_attn.o.scale_input', 'blocks.31.ffn.0.scale_input', 'blocks.31.ffn.2.scale_input', 'blocks.32.self_attn.q.scale_input', 'blocks.32.self_attn.k.scale_input', 'blocks.32.self_attn.v.scale_input', 'blocks.32.self_attn.o.scale_input', 'blocks.32.cross_attn.q.scale_input', 'blocks.32.cross_attn.k.scale_input', 'blocks.32.cross_attn.v.scale_input', 'blocks.32.cross_attn.o.scale_input', 'blocks.32.ffn.0.scale_input', 'blocks.32.ffn.2.scale_input', 'blocks.33.self_attn.q.scale_input', 'blocks.33.self_attn.k.scale_input', 'blocks.33.self_attn.v.scale_input', 'blocks.33.self_attn.o.scale_input', 'blocks.33.cross_attn.q.scale_input', 'blocks.33.cross_attn.k.scale_input', 'blocks.33.cross_attn.v.scale_input', 'blocks.33.cross_attn.o.scale_input', 'blocks.33.ffn.0.scale_input', 'blocks.33.ffn.2.scale_input', 'blocks.34.self_attn.q.scale_input', 'blocks.34.self_attn.k.scale_input', 'blocks.34.self_attn.v.scale_input', 'blocks.34.self_attn.o.scale_input', 'blocks.34.cross_attn.q.scale_input', 'blocks.34.cross_attn.k.scale_input', 'blocks.34.cross_attn.v.scale_input', 'blocks.34.cross_attn.o.scale_input', 'blocks.34.ffn.0.scale_input', 'blocks.34.ffn.2.scale_input', 'blocks.35.self_attn.q.scale_input', 'blocks.35.self_attn.k.scale_input', 'blocks.35.self_attn.v.scale_input', 'blocks.35.self_attn.o.scale_input', 'blocks.35.cross_attn.q.scale_input', 'blocks.35.cross_attn.k.scale_input', 'blocks.35.cross_attn.v.scale_input', 'blocks.35.cross_attn.o.scale_input', 'blocks.35.ffn.0.scale_input', 'blocks.35.ffn.2.scale_input', 'blocks.36.self_attn.q.scale_input', 'blocks.36.self_attn.k.scale_input', 'blocks.36.self_attn.v.scale_input', 'blocks.36.self_attn.o.scale_input', 'blocks.36.cross_attn.q.scale_input', 'blocks.36.cross_attn.k.scale_input', 'blocks.36.cross_attn.v.scale_input', 'blocks.36.cross_attn.o.scale_input', 'blocks.36.ffn.0.scale_input', 'blocks.36.ffn.2.scale_input', 'blocks.37.self_attn.q.scale_input', 'blocks.37.self_attn.k.scale_input', 'blocks.37.self_attn.v.scale_input', 'blocks.37.self_attn.o.scale_input', 'blocks.37.cross_attn.q.scale_input', 'blocks.37.cross_attn.k.scale_input', 'blocks.37.cross_attn.v.scale_input', 'blocks.37.cross_attn.o.scale_input', 'blocks.37.ffn.0.scale_input', 'blocks.37.ffn.2.scale_input', 'blocks.38.self_attn.q.scale_input', 'blocks.38.self_attn.k.scale_input', 'blocks.38.self_attn.v.scale_input', 'blocks.38.self_attn.o.scale_input', 'blocks.38.cross_attn.q.scale_input', 'blocks.38.cross_attn.k.scale_input', 'blocks.38.cross_attn.v.scale_input', 'blocks.38.cross_attn.o.scale_input', 'blocks.38.ffn.0.scale_input', 'blocks.38.ffn.2.scale_input', 'blocks.39.self_attn.q.scale_input', 'blocks.39.self_attn.k.scale_input', 'blocks.39.self_attn.v.scale_input', 'blocks.39.self_attn.o.scale_input', 'blocks.39.cross_attn.q.scale_input', 'blocks.39.cross_attn.k.scale_input', 'blocks.39.cross_attn.v.scale_input', 'blocks.39.cross_attn.o.scale_input', 'blocks.39.ffn.0.scale_input', 'blocks.39.ffn.2.scale_input', 'head.head.scale_input']
Having just made my second video (using res2s/beta57 as advised in another comment, 6 steps, CFG 2), I have to say... I'm blown away by this!
I've tried a fair few WAN 2.1 models and merges, and hundreds of LoRAs, and the result I just got is better and more prompt adherent than anything I've achieved with those (or WAN 2.2, dare I say it)...
If I had a hat, I'd be doffing it right now. Excellent work!
Seeker360 this terminal unet missing messages not affected final result, but I will fix this in next version
The actual video quality is amazing - even at 480p, I'm getting generations that are better quality than my 720p WAN 2.2 runs.... Maybe I should have been using Heun all this time!
Prompt adherence is a bit patchy. Simple prompts it does really well with, but anything slightly less simple and it falls apart ... Not sure if that's something to do with the balance of Lora Weights within the merge?
As a first draft though, this is definitely very impressive - can't wait to see the next version!
Thank you friends for the feedback, I myself enjoy the result, and I am glad that you liked it
sanchezvfx Seriously, your checkpoint is that good, I'm contemplating whether I even need all my other WAN 2.1 and 2.2 models and my huge folders of loras... It is literally better than WAN 2.2 ... You should be extremely proud of it!
Thank You! Good job and thanks for sharing it. Any possibility to have it in Image to video version?
Yes. And the author has examples
Image to video not so important if you have top image, but I2V is next :)
sanchezvfx That's right, but sometimes I start from a real photo or try to make more videos of the same imaginary character. Anyway I'm eagerly waiting for I2V, thanks a lot!
After being so impressed with the T2V, I too can't wait for an I2V if it works anywhere near as well!
Great model. Will there be an i2v model?
Image to video not so important if you have top image, but I2V is next :)
Wow! Checkpoint Merge of wan? really? you are the legend man!
very good and pretty fast. great work. quick question please, if i want to add extra loras do i add wan high or wan low?
this is wan 2.1 based model, so you need wan 2.1 loras
thank you, works so well.
Amazing and mind-blowing. Thanks for making it, thanks for sharing it.
Would it be possible to upload a diffusers folder to huggingface or another platform, like this one for the base model? https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers/tree/main/transformer
One of the only drawbacks I see is that my LoRas trained on the base model seem to work less with yours (characters, clothing). I would like to retrain them directly on the model.
is that method working with wan? I did exactly what you are trying to do with fine tuned flux models back in the days. output was bad. I came to conclusion it is best to train a lora with official base model.
actually great model.
Any chance to get an I2V model?
yes
@sanchezvfx any progress towards I2V with this?
Still getting better T2V results with this than other models.
+1 for i2v
Hi, thanks for making this. Do you happen to be planning a WAN2.2 update? I would love all the kijair/lightxv/moviigen loras wrapped in to one
Great work on this, I'm glad you liked the NSFW API model. I'm assuming you used the NSFW Wan 2.1 14b checkpoint as part of the base for this?
Thanks! Not a model but your wonderful lora is part of my mix
I thought I'd see how your checkpoint does at generating I2T using a single frame generation. And I was blown away especially for NSFW stuff. It literally blows everything else out of the water. I could quite happily uninstall pretty much every other SDXL, Flux, Qwen model... It's outstanding. I'm excited to see where this checkpoint goes next as well as what we can expect from an I2V version
Hi! V2 will be better!
@sanchezvfx Can't wait my friend! 😁
Hi. I have a human lora that I made on wan 2.2 in high and low noise. Can I use it with your model?
You can try low noise
Hello, is there a way, how to make long videos from continuous clips with this model?
Incredible work on this model! I've been using it for 3 days and I'm impressed!
Looking forward to an I2V like this, haha!
Thanks for sharing with us Sanchez !
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.