FinePo*n - v6 int8

FinePo*n

CHECKPOINT
Reprint


Updated:

FinePo*n by CMR Swaglin on Tensor.Art

From CivitAI:

A turbo checkpoint merged for the perfect balance between three things: NSFW capability, prompt adherence, and a "smartphone-like" look. The goal is a balanced crisp, casual image. This is the goal, and this checkpoint is the starting point; expect many updates with high frequency.

About FinePorn

This is an approachable but functional starting point. To hit the target, I baked in LoRAs with balanced weights + INT8 and CONVROT to achieve faster speed and good quality, with the plan to scale up future versions by adding new LoRAs, rebalancing weights and hunting for the optimal settings.

Baked LoRAs Changelog (v4):

  • — balanced

  • — removed due to dark contrast

  • — balanced

  • — removed due to a variation issue

  • — added

  • — added at very low strenght

  • — added at very low strenght

  • — added at low strenght to enforce interactions

  • — added at negative strenght to reduce dropplets

All baked LoRAs will credit their creators.

⚙️ Recommended Settings

V1

  • res_2s + beta -> More Quality

  • er_sde + beta -> More Speed

  • CFG: 1

  • Steps: 8–10

V2

  • SamplerER_SDE + beta -> Fast and Stable

  • CFG: 1

  • Steps: 8–12

V3

  • euler + simple

  • euler + beta (my favorite)

  • er_sde + simple

  • er_sde + beta

  • or

V4

  • euler + beta

  • er_sde + simple

  • or

📐 Resolutions

I found that scaling resolutions by x1.25 and x1.5 gives better results:

- 832x1216 standard → 1040x1520 optimal 1248x1824 recommended

- 896x1152 standard → 1120x1440 optimal 1344x1728 recommended

- 1024x1024 standard → 1280x1280 optimal 1536x1536 recommended

💡 Notes

Good results are achievable without a face detailer or extra passes. With the right config, some patience, and a bit of seed luck, you can get great things. I highly recommend start all your prompts using a phrase like this or similar.

This is a casual, low-quality photo

this is an amateur photo taken from smartphone, casual photo

⚠️ Important disclaimer

This is NOT trained by me and is NOT my own work, my job here is using my experience to bake balanced weights of my personal taste to achieve desired images using my prompt style. My only role is to share with you what, to my eye, is the best style and quality achievable with this model. All baked LoRAs credit their creators.

ABOUT PROMPTS

I'm a bit dissapointed tbh, i've seen a dozen of 'big' creators and model makers just copying my hand-made prompts and spiting them on their showcase photos, with zero quotes to me or at least a small comment or a dm, it feels bad and very lazy coming from them. so, from now on, complex prompts will be shared only on DMs freely, but i'll keep simpler prompts public.

The model already exists. If you are the creator, please contact us to claim it.
View duplicate model

Version Detail

KREA_2
From CivitAI: Different technique this time. Until V5, FinePorn was LoRAs baked into Krea 2 Turbo. V6 is an actual checkpoint merge: Krea 2 Turbo merged with LoveInTheAir (a Kroma based finetune) + FinePorn V5, block by block instead of a flat 50/50. Krea handles the composition and the prompt, FinePorn v5 and LoveInTheAir handles the bodies and the skin. On top of that, a few LoRAs baked in for realism, NSFW and expressions. Each one picked by testing same seed, with and without. Everything merged in BF16 and quantized only once at the end, so you get less artifacts. Settings: er_sde + beta, 10 steps, CFG 1 Merged models: LoveInTheAir by mqblbhai Krea 2 Turbo Official FinePorn V5 (very small percentage) Baked LoRAs: Realistic Snapshot by MonkeyForever SNOFS (Sex, Nudes, Other Fun Stuff) by Ashen3 Detailed Emotions and Expressions by DerekG2 Does it work with my character LoRA? No idea. Is V6 better than V5? For me yes, but taste changes.

Project Permissions

Model reprinted from : https://civitai.red/models/2762538/

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts