Diffusers
Safetensors
latent-reasoning
arithmetic
image-editing
diffusion
mechanistic-interpretability
Instructions to use SuhaoYu1020/semantic-image-arith-ckpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SuhaoYu1020/semantic-image-arith-ckpts with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SuhaoYu1020/semantic-image-arith-ckpts", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu: Stage-2 floor: white TE-image + TE FROZEN (eval pending)
Browse files- vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu/meta.json +1 -0
- vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu/transformer/config.json +20 -0
- vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu/transformer/diffusion_pytorch_model.safetensors +3 -0
vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu/meta.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"global_step": 45000, "freeze_te": true, "te_image_mode": "white", "te_image_size": null}
|
vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu/transformer/config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "QwenImageTransformer2DModel",
|
| 3 |
+
"_diffusers_version": "0.39.0.dev0",
|
| 4 |
+
"attention_head_dim": 128,
|
| 5 |
+
"axes_dims_rope": [
|
| 6 |
+
16,
|
| 7 |
+
56,
|
| 8 |
+
56
|
| 9 |
+
],
|
| 10 |
+
"guidance_embeds": false,
|
| 11 |
+
"in_channels": 64,
|
| 12 |
+
"joint_attention_dim": 3584,
|
| 13 |
+
"num_attention_heads": 12,
|
| 14 |
+
"num_layers": 24,
|
| 15 |
+
"out_channels": 16,
|
| 16 |
+
"patch_size": 2,
|
| 17 |
+
"use_additional_t_cond": false,
|
| 18 |
+
"use_layer3d_rope": false,
|
| 19 |
+
"zero_cond_t": false
|
| 20 |
+
}
|
vistok/vistok_white828_frozenTE_seed42_noemit_MSEonly_DITonly_TEfrozen_scratch2B_10ep_1gpu/transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a47ec31738687d8000e745100f654b864c1d45c230cb8274a2609a05dfd9aa8
|
| 3 |
+
size 4105561640
|