T-Shirt Diffusion
by ModelsLabnew test model v 1.1 - try it, it is mainly for testing purposes. Let me know in the comments what you think, I can tune it more in case of problems
MAGIFACTORY model is trained to generate t-shirt logos based on text input. The model takes in a text description of the desired t-shirt logo and generates a corresponding image. It is trained on a dataset of t-shirt logos with resolution 640x640px. Ideally use hires-fix rescale to 1280x1280 in automatic1111 WebUI with "Latents antialiased" and finally upscale to 5120x5120 with SwinIR_4x. Euler a scheduler preferred. I am running Instagram with top designs, so you can download and use them.
prompts:
cyberpunk astronaut flying in space (on a black background:1.4) as a t-shirt logo in the style of <MAGIFACTORY> art
a symbol of a car (on a black background:1.2) as t-shirt logo in the style of <MAGIFACTORY> art
negative prompt:
badly drawn, noisy, noise, blurred, ugly, cropped, out of frame, (double:1.4), (repeated:1.4), (repeating:1.4), signature, text, font, watermark
t-shirt-diffusionInput
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Unknown content type
Related Models
Discover similar models you might be interested in
![Goku Super Saiyan 4 (Dragon Ball) [Illustrious & SD1.5] - v1.0](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bf41979e-846c-4e1d-9268-78f3fa54a1c4/width=768/3750134.jpeg)
![Spider-Man (Peter B. Parker) from Into the Spider-Verse [LoRA] - v1.0 SD v1.5](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d4f0d246-ec53-470d-85a6-fd839a0c50da/width=768/6568811.jpeg)
![Kakudate Karin | (Blue Archive) [Illustrious] - v1.0](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/eed32afb-a16a-483a-b202-117f9393a92d/width=1024/30607845.jpeg)
T-Shirt Diffusion Readme
new test model v 1.1 - try it, it is mainly for testing purposes. Let me know in the comments what you think, I can tune it more in case of problems
MAGIFACTORY model is trained to generate t-shirt logos based on text input. The model takes in a text description of the desired t-shirt logo and generates a corresponding image. It is trained on a dataset of t-shirt logos with resolution 640x640px. Ideally use hires-fix rescale to 1280x1280 in automatic1111 WebUI with "Latents antialiased" and finally upscale to 5120x5120 with SwinIR_4x. Euler a scheduler preferred. I am running Instagram with top designs, so you can download and use them.
prompts:
cyberpunk astronaut flying in space (on a black background:1.4) as a t-shirt logo in the style of <MAGIFACTORY> art
a symbol of a car (on a black background:1.2) as t-shirt logo in the style of <MAGIFACTORY> art
negative prompt:
badly drawn, noisy, noise, blurred, ugly, cropped, out of frame, (double:1.4), (repeated:1.4), (repeating:1.4), signature, text, font, watermark