Downloads · 30 days
0
GC-DPO-diagnostic-ckpts
XujuntaoFighting/GC-DPO-diagnostic-ckpts
GC-DPO-diagnostic-ckpts is a text-to-image model from XujuntaoFighting. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
Best-step UNet checkpoints for the GC-ST-DPO paper experiments (gradient-attributed spatio-temporal-token credit assignment for diffusion preference optimization). All models trained on Pick-a-Pic v2, seed=0, eff-batc…
Access
Public
Updated Aug 12, 2026
Repo size
238 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors242 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 12, 2026
- SHA
- 465e5e56
Model card
From the Hugging Face model README
GC-ST-DPO diagnostic checkpoints
Best-step UNet checkpoints for the GC-ST-DPO paper experiments (gradient-attributed spatio-temporal-token credit assignment for diffusion preference optimization). All models trained on Pick-a-Pic v2, seed=0, eff-batch 1024 x 500 steps, beta=2000.
Layout
| path | backbone | init | note |
|---|---|---|---|
sd15/gc_dpo_full/ | SD-1.5 | JaydenLu666/SD1.5-SFT | main method, best step 300 |
sd15/mask_dpo/ | SD-1.5 | SFT | spatial-mask-only ablation, step 400 |
sd15/diff_dpo/ | SD-1.5 | SFT | Diffusion-DPO reproduction, step 400 |
sd15/gc_dpo_full_random_w/ | SD-1.5 | SFT | falsification control (shuffled W), step 500 |
sdxl/gc_dpo_full/ | SDXL | base (bf16) | main method SDXL, step 500 |
sdxl/mask_dpo/ | SDXL | base (bf16) | ablation SDXL, step 100 |
sdxl/sft_winners/ | SDXL | base (bf16) | SFT-on-winners baseline (Wallace --sft) |
Each directory contains a bare UNet2DConditionModel (config.json +
diffusion_pytorch_model.safetensors, fp16). Load by overriding the UNet of
the matching base pipeline (runwayml/stable-diffusion-v1-5 /
stabilityai/stable-diffusion-xl-base-1.0).
Best-step was selected on held-out Pick-a-Pic validation prompts (500) by equal-weight mean rank of PickScore + HPS-v2.
Code + eval pipelines: https://github.com/JuntaoXu/GCPO
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Created
- Aug 6, 2026
- Updated
- Aug 12, 2026