retro-cgi, Stable Diffusion 1.5 lora
- Prompt
- Bauernhof, (rtrcgi:1.2)
- Negative Prompt
- text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, (blurry), dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature, cloth
- Prompt
- (rtrcgi:1.3), woman
- Negative Prompt
- text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, (blurry), dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature, cloth
- Prompt
- rtrcgi, submarine
- Negative Prompt
- text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, deformed hands, watermark
- Prompt
- (rtrcgi:1.25), 25yo student sitting at her desk, green sweater, studying in a book, side profile, it is dark outside, window behind her, wearing headphones, ponytail
- Negative Prompt
- text, error, ugly, deformed, horror
- Prompt
- (rtrcgi:1.4), old school crt displays line up on wooden desks in rows with chairs, purple ceiling
- Negative Prompt
- text, error, ugly, deformed
- Prompt
- (rtrcgi:1.5), schoolgirl standing in front of a haunted house, back towards camera, zoomed out view, full body visible
- Negative Prompt
- text, error, ugly, deformed, horror
Model description
This is a LoRA that's trained on retro CGI images from the late 90s and early 2000s meant to reproduce the slightly surreal look of the renders of those times.
The model uses "rtrcgi" as a trigger word at the beginning of a prompt. It was trained on the base models and generalizes well over different checkpoints and in combination with other LoRAs. However, you might need to fiddle around with the strength of the trigger word and the LoRA model weights themselves to get a good result.
I've noticed some problems when the prompt gets too complicated and the scene too complex. I might come back to it in the future to try with an improved training set but for now the quality is good enough to be usable for interesting generations.
There is also a Stable Diffusion XL version of the LoRA available in the files. Use that for SDXL models, it is a bit less stable than the SD1.5 version and more fiddling with the parameters is required to get good generations.
Please note: the LoRA was trained on 512x512 resolution images. From my experience it is better to generate at 512x512 or 768x768 due to this limitation. Other resolutions also work, but might produce less coherent results
Trigger words
You should use rtrcgi to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 157