Downloads · 30 days
8
9% of all-time downloads
RichardErkhov/crumb_-_bloom-560m-RLHF-SD2-prompter-aesthetic-4bits
crumb_-_bloom-560m-RLHF-SD2-prompter-aesthetic-4bits is a text generation model from RichardErkhov. Use it when you need the model to write or continue text. It is set up for transformers.
Downloads · 30 days
8
9% of all-time downloads
All-time downloads
88
Public
Parameters
564M
699 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors684 MB · 98%
How the weights are stored.
U8302M · 54%
From the Hugging Face model README
Quantization made by Richard Erkhov.
bloom-560m-RLHF-SD2-prompter-aesthetic - bnb 4bits
license: bigscience-bloom-rail-1.0 tags:
datasets:
widget:
COLAB DEMO INCLUDING STABLE DIFFUSION: https://colab.research.google.com/github/aicrumb/doohickey/blob/main/rlhf_prompt_tuner.ipynb
This is a further finetuned version of crumb/bloom-560m-RLHF-SD2-prompter to optimize for aesthetic score with models from https://github.com/crowsonkb/simulacra-aesthetic-models instead of me hand scoring each image
donate so i can do this on real hardware : https://github.com/aicrumb/aicrumb/blob/main/README.md
trained at bs=32, lr=0.0001, only tuning biases and layernorm weights
# Install libraries needed to run the models
!pip install transformers diffusers accelerate -qq
# Import the libraries
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
from transformers import pipeline
import torch
# This is the model that the transformer was finetuned to generate prompts for
model_id = "stabilityai/stable-diffusion-2-base"
# Use the Euler scheduler here
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, revision="fp16", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
# Load the transformer model
prompt_pipe = pipeline("text-generation", model="crumb/bloom-560m-RLHF-SD2-prompter-aesthetic")
prompt = "cool landscape"
# Auto-complete prompt
prompt = "<s>Prompt: " + prompt + ","
extended_prompt = prompt_pipe(prompt, do_sample=True, max_length=42)[0]['generated_text']
extended_prompt = extended_prompt[10:]
print("Prompt is now: ", extended_prompt)
# Generate image
image = pipe(extended_prompt).images[0]
image.save("output.png")
image
Aesthetic scoring models have been shown to have very large biases, and one I noticed is it really likes images of women no matter the actual quality, so those were optimized for more than other things.
Also it fell into the trap of rlhf models, it gets kinda same-ey, so if you don't like the general "stable diffusion, trending on artstation" look this might not be for you.