any idea how to fix this?
I often get videos with this screen distortion...unwanted spots appear in the video I use "ltxv-13b-0.9.7-distilled-Q6_K.gguf" to create the video with 8 steps...this only happens with "distilled"...but "distilled" is the best in time...the video is created in less than 2 minutes only while it takes about 6.5 minutes with 30 steps the non distilled version...these video distortions happen in approximately 40% of the videos...and I use your workflow...Image to Video.. Video Example attached ⬇︎
Yeah i have those issues too, its a config/prompting issue, you might ask the people on the ltxv discord, ive had not too much time to find out what helps sadly /:
The issue was fixed by using the official workflow... Base one ... and modifying the nodes required to load the VAE, model and clip......The good point is also that the video creation time has been reduced to 54 seconds...8 steps...using the official Workflow....this one https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/13b-distilled/ltxv-13b-dist-i2v-base.json
Same problem here.
The issue was fixed by using the official workflow... Base one ... and modifying the nodes required to load the VAE, model and clip......The good point is also that the video creation time has been reduced to 54 seconds...8 steps...using the official Workflow....this one https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/13b-distilled/ltxv-13b-dist-i2v-base.json
Thanks for the tip. I did the same but i still get some underised text on the video.
The issue was fixed by using the official workflow... Base one ... and modifying the nodes required to load the VAE, model and clip......The good point is also that the video creation time has been reduced to 54 seconds...8 steps...using the official Workflow....this one https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/13b-distilled/ltxv-13b-dist-i2v-base.json
Thanks for the tip. I did the same but i still get some underised text on the video.
I think the underised text is caused by the prompt... modify it and it will disappear
The issue was fixed by using the official workflow... Base one ... and modifying the nodes required to load the VAE, model and clip......The good point is also that the video creation time has been reduced to 54 seconds...8 steps...using the official Workflow....this one https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/13b-distilled/ltxv-13b-dist-i2v-base.json
Thanks for the tip. I did the same but i still get some underised text on the video.
I think the underised text is caused by the prompt... modify it and it will disappear
you are right. i noticed that the prompt was erratict, maybe the reason the undesired text appeared.
But i do have a question, did you kept the optimizations, like teacache in your workflow?
The official workflow that i uses now does not have optmization.
you can download this video and drag it inside comfyui for workflow i use (official workflow)