This is a first try, so don't expect too much. Wanted to keep it bloody simple, I like dark theme.
Steps: 28 (more should give slightly better quality, but loong gen time)
CFG: 4
Sampler: euler
Scheduler: normal
Im also using CFGZeroStar, RescaleCFG: 0.3, Self-Attention Guidance: default)
Upscaling helps a lot and I couldn't live without inpainting. :3
That's what i use so far, you can try what works for you the best..
Positive prompt:
number of characters (1girl/1boy), character name, artist prompt, scene/environment/camera angle, action, expression, items, quality prompts (masterpiece, best quality)
Negative prompt:
lowres, worst quality
Make sure to use UI that supports v-prediction, otherwise you will get a noisy blob!
v1:
Started fresh, with similar base, but different weights, i liked it more, merged a few LoRAs with base NOOBAI-XL v-pred and then with 2DN checkpoint. (see about version for credits)
Seems to be better overall, keeping the dark esthetic.
Prototype:
Merged a few LoRAs with base NOOBAI-XL v-pred. (see about version for credits)
Enjoy!
[BPM] Blink's paradise merge (v-pred) is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user blinkdotleh. Derived from the powerful Stable Diffusion (NoobAI) model, [BPM] Blink's paradise merge (v-pred) has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that [BPM] Blink's paradise merge (v-pred) is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as base model, merge, vpred.
With a rating of 0 and over 0 ratings, [BPM] Blink's paradise merge (v-pred) is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of [BPM] Blink's paradise merge (v-pred) from here.
To use [BPM] Blink's paradise merge (v-pred), download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like [BPM] Blink's paradise merge (v-pred), check out our crash course in AI image generation.
New custom lora, better weights on blocks, more semi-realism, not as dark.
Models used, go like them!
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.