Stable Diffusion Consistent Character Poses and Camera Angles Tutorial

CharTurner - Textual Inversion Embedding to make Consistent Character different poses and camera angles using Stable Diffusion v1.5. character turnarounds helper.

Helps create multiple full body views of a character. The intention is to get at least a front and back, and ideally, a front, 3/4, profile, 1/4 and back versions, in the same outfit.

This demo is tried on Anything v3 model.

❤️ If you want to support what we are doing ❤️
Support here:

[wrillywonka]

what if i have an image i love but it is only front the front view? can i use this to give me more views of the same character?

[sebasketball]

Hi, can this be achieved starting with only one pose (frontal) of a standing character? I try to find a way to turn around the character (cartoon illustration) image I have to profile and 3/4 view. Do you know a way to do this?

[omnibus]

how do i get the civitai tab in stable diffuion?and what folder do i put the charturner in when downloaded?

[kieroneil]

Key point he made was that it will generate new images every time. Using the same prompt never produces the same image. I consider this a feature. I can dial in the results I want through using "variations" and refining my prompt. I'm very impressed by DALL E so far.

[Ariana_VT]

any tips on helping create straight on images instead of ~10% turned front views?

[davidblissett]

Great video. I'm new to the AI/Python setup... Can you kindly explain what you meant by "download" while working with the Notebook??? You mention playing the "Download" in a specific folder, but when I click the Download button, nothing happens. Does it get stored in a Google Colab location??? Any help with understanding that step would be helpful. Also, very helpful video. Thanks.

[Beyondarmonia]

Instead of a textual inversion, wouldn't it make more sense to train further on a bunch of 3d models / NERFs where you've taken renders from each angle and composted them into a single image ( a character sheet ).

[brunolopezmosconi]

can we put controlnet in this anything 3 you showed up in this vieo?

[PosDami]

helloe there, thanks for this information, how did you have this civitai tab in stable diffusion ?

[abdullahalsulami]

Can this model work in img2img ( add a front image and create different poses)?

[giuseppegangi]

dafuq happened at 0:01, i almost got an heart attack from that jumpscare

[nrn]

can anyone plz tell me how to use it in local stabel diffusion