Miso-diffusion-m
Collection
4 items • Updated • 2
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("suzushi/miso-diffusion-m-1.0", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
An attempt to fine tune sd3.5 medium
Version History
| Version | Base Training | Aesthetic Training | Total Epochs |
|---|---|---|---|
| alpha | 250K images | 0 images | 1 |
| beta | 160K images | 0 images | 3 |
| 1.0 | 600k images | 0 images | 2 + (3 from beta) |
Training Methodology
Training is done on gh200 with 96gb vram
Training setting: Adafactor with a batchsize of 40, lr_scheduler: cosine
SD3.5 Specific setting:
enable_scaled_pos_embed = true
pos_emb_random_crop_rate = 0.2
weighting_scheme = "flow"
learning_rate = 3e-6
learning_rate_te1 = 2e-6
learning_rate_te2 = 2e-6
Train Clip: true, Train t5xxl: false
- Downloads last month
- 9
Model tree for suzushi/miso-diffusion-m-1.0
Base model
stabilityai/stable-diffusion-3.5-medium