bloom-560m-RLHF-SD2-prompter

作者 crumb · 下载 5 · 点赞 11 · 更新 2023-11-01

stable-diffusion diffusion

BLOOM-560m RLHF SD2 Prompter

COLAB DEMO INCLUDING STABLE DIFFUSION: https://colab.research.google.com/github/aicrumb/doohickey/blob/main/rlhf_prompt_tuner.ipynb

Using RLHF (Reinforcement Learning from Human Feedback) to finetune mrm8488/bloom-560m-finetuned-sd-prompts further for SD2.0

batch_size = 16
learning_rate = 0.001 # this is why I didn't have to spend _forever_ on it

Generate extension with "<s>Prompt: " and whatever your normal prompt is.

I did this myself. I sat down and just ranked images for so long. It's gone through a couple iterations. Only the biases and layernorm weights were trained. The commit messages are a MESS. First iteration of this project

donate so i can do this on real hardware : https://github.com/aicrumb/aicrumb/blob/main/README.md

Example usage

# 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")
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

Prompt is now: cool landscape, concept art bloom-560m-RLHF-SD2-prompter 预览 1

Prompt is now: cool landscape, concept art, sharp focus, digital painting bloom-560m-RLHF-SD2-prompter 预览 2

short additions, they work though I guess (results vary)

It's also very good at generating prompts by itself, with just the "Prompt:" prompt.

<s>Prompt: 1 0 th century, highly detailed, concept art, cinematic lighting, unreal engine, trending on artstation, artstation hd, artstation hq, very very detailed bloom-560m-RLHF-SD2-prompter 预览 3

Further testing to be done in this area (automated training with aesthetic predicting models, larger data collection about prompt scores, better training in general)

Also, enjoy this graphic I had to make myself because I kept being indecisive of the reward methodology bloom-560m-RLHF-SD2-prompter 预览 4