uploaded readme

README.md

@@ -0,0 +1,108 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+bloom-560m-RLHF-SD2-prompter - bnb 4bits
+- Model creator: https://huggingface.co/crumb/
+- Original model: https://huggingface.co/crumb/bloom-560m-RLHF-SD2-prompter/
+
+
+
+
+Original model description:
+---
+license: bigscience-bloom-rail-1.0
+tags:
+- stable-diffusion
+- diffusion
+model-index:
+- name: bloom-560m-RLHF-SD2-prompter
+  results: []
+  
+datasets:
+ - Gustavosta/Stable-Diffusion-Prompts
+
+widget:
+- text: "<s>Prompt: "
+
+inference:
+  parameters:
+    eos_token_id: 2
+    max_length: 128
+    do_sample: true
+---
+
+# 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](https://hf.co/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
+
+```python
+# 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*
+![](https://cdn.discordapp.com/attachments/1010693530181718146/1047831482808406067/image.png)
+
+*Prompt is now:   cool landscape, concept art, sharp focus, digital painting*
+![](https://cdn.discordapp.com/attachments/1010693530181718146/1047832480335536249/image.png)
+
+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*
+![](https://cdn.discordapp.com/attachments/1010693530181718146/1047843202050310174/image.png)
+
+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 ![](https://cdn.discordapp.com/attachments/1010693530181718146/1047846272096292925/image.png)
+