1.06k
Stable Fast 3D
🎮
Generate a 3D mesh model from an image
Kacper Głombiewski
Clausss
·
AI & ML interests
None yet
Recent Activity
liked
a Space
2 days ago
stabilityai/stable-fast-3d
replied to
ProCreations's
post
4 days ago
60 followers,
yay
reacted
to
ProCreations's
post
with 🚀
4 days ago
60 followers,
yay
Organizations
None yet
Clausss's activity
liked
a
Space
2 days ago
replied to
ProCreations's
post
4 days ago
congrat
reacted to
ProCreations's
post with 🚀
4 days ago
Post
2267
60 followers,
yay
yay
-
- 2 replies
reacted to
ProCreations's
post with 🚀
10 days ago
Post
2877
Eyyyy 50 followers 🤯
- 1 reply
liked
a
Space
13 days ago
reacted to
ProCreations's
post with 🤯
13 days ago
Post
2422
Uggghhh what a busy week.
Been up all night fixing Intellite and I got some progress I wanted to share.
ALL errors we experienced (there’s a lot):
Gradient vanishing (AI dies)
Gradient explosion (AI barely learns and destabilizes)
Activation Explosion (AI dies)
Layer Scale Crushing Signal (AI dies)
Activation Explosion (again) (AI dies)
All fixed, but now it keeps overfitting on datasets due to a dataset handler error 😩
Been up all night fixing Intellite and I got some progress I wanted to share.
ALL errors we experienced (there’s a lot):
Gradient vanishing (AI dies)
Gradient explosion (AI barely learns and destabilizes)
Activation Explosion (AI dies)
Layer Scale Crushing Signal (AI dies)
Activation Explosion (again) (AI dies)
All fixed, but now it keeps overfitting on datasets due to a dataset handler error 😩
nihalgazi-flux-pro-unlimited.hf.space’s server IP address could not be found.
4
#9 opened 19 days ago
by
Clausss
Report
🤯
3
#2 opened 18 days ago
by
Clausss
reacted to
ProCreations's
post with 🤗
19 days ago
Post
3180
Eyyy thank you guys for 40 followers!
liked
a
Space
19 days ago
liked
a
Space
20 days ago
replied to
ProCreations's
post
20 days ago
fp8 is not required this is only 100m parameter(less than gpt2)so this can run even on mobile
error when paste api key
2
#14 opened 22 days ago
by
Clausss
liked
a
Space
22 days ago
reacted to
ProCreations's
post with 👀
22 days ago
Post
1627
WOULD YOU RATHER
part 2
All your GPUs you have suddenly vanish and any devices with a GPU turn to CPU only
Every time you use a HF space you randomly start dancing for 5 minutes
OR
Every HF model you’ve hearted / liked suddenly disappears and becomes inaccessible
part 2
All your GPUs you have suddenly vanish and any devices with a GPU turn to CPU only
Every time you use a HF space you randomly start dancing for 5 minutes
OR
Every HF model you’ve hearted / liked suddenly disappears and becomes inaccessible
- 4 replies
can I run it on rtx 4060ti with/without quantization?
reacted to
AdinaY's
post with 🔥
24 days ago
Post
2385
Step1X-3D 🔥 an open 3D generation framework by StepFun_ai
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets (2505.07747)
stepfun-ai/Step1X-3D
stepfun-ai/Step1X-3D
✨ 4.8B (1.3B geometry + 3.5B texture) & Apache2.0
✨ Multi-style texture generation (cartoon → photoreal)
✨ Seamless 2D-to-3D control via LoRA
✨ 800K curated 3D assets
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets (2505.07747)
stepfun-ai/Step1X-3D
stepfun-ai/Step1X-3D
✨ 4.8B (1.3B geometry + 3.5B texture) & Apache2.0
✨ Multi-style texture generation (cartoon → photoreal)
✨ Seamless 2D-to-3D control via LoRA
✨ 800K curated 3D assets
-
- 1 reply
upvoted
a
collection
about 1 month ago
liked
a
model
about 1 month ago
reacted to
ProCreations's
post with 🔥
about 1 month ago
Post
3100
Intellite Chat training script is working!
Training works fine, normal loss, no more gradient explosion or gradient vanishing, etc.
BUT, before I officially flip the switch and turn on training, I wanna make sure its the best possible 100m parameter model it can be, so I am working a bit more (probably an extra 3-5 days) to add even more innovative AI improvements to intellite.
Training works fine, normal loss, no more gradient explosion or gradient vanishing, etc.
BUT, before I officially flip the switch and turn on training, I wanna make sure its the best possible 100m parameter model it can be, so I am working a bit more (probably an extra 3-5 days) to add even more innovative AI improvements to intellite.